# Introduction he image classification plays an important role in environmental and socioeconomic applications. In order to improve the classification accuracy, scientists have laid path in developing the advanced classification techniques. [1-9] However, classifying a remotely sensed data into a thematic map is still a nightmare because of the following factors such as landscape complexity, image sensing and processing and classification approaches. The review concentrates on recent classification approaches and techniques which are often not available. # a) Remote sensing classification process RS classification is generally a complex procedure which needs many factors to be considered. This procedure includes following steps that begins with the identification of suitable classification system, choosing appropriate training samples, processing of an image and extracting its features, applying a right and indeed classification method, post classification and accuracy assessments. Airborne and space borne sensor data comes under RS data stream, which varies in spatial, radiometric, spectral and temporal resolutions. In order to have better image classification a suitable RS data needs to be collected, which depends upon strength and weakness of sensor data. In literature the characteristics of remotely sensed data is summarized by [10], [11] in spectral, radio metric, spatial and temporal resolutions with polarization and angularity. It is preferred to consider the factors while selecting suitable sensor data as per the user's need, which includes scaling, study area characteristics, availability of various image data and their characteristics, cost, time constraints and analyst's experience in using selected images. Scaling determines the study area; earlier research encountered a problem of image resolution of remotely sensed data in classification. In regular practice, a fine-scale classification system is adopted in order to achieve high spatial resolution data. For example, IKONS and SPOT 5 HRG are at regional level medium spatial resolution data. However, the influence of atmospheric conditions in moist and tropical regions cannot be neglected and they are often an obstacle for capturing the high quality sensor data. Therefore, it always proves to be beneficiary to have multiple sources of sensor data. # c) Selection of classification system and training samples A better classification can be achieved only when we consider a suitable classification system with sufficient number of training samples. Generally, in a wide variety of applications we adopt hierarchy classification systems because different conditions are taken into account. A classification system should consider spatial resolution of selected RS data, compatibility with its previous work, image processing and classification algorithm availability and time constraints. The ultimate goal of choosing any classification system is to satisfy the need of an end user. The image classification broadly depends on number of training samples and their representativeness. Training samples can be prepared by fieldwork or it can also be obtained from other means such as aerial photographs of fine spatial resolution and satellite images. The results of the classification are affected by the selection of training data, which generally may be based on single pixel, seed or polygon, also affected by fine spatial resolution image data if proper care is not taken. If coarse resolution data is used for classification data then the selection of TS becomes tedious under complex and heterogeneous case studies as it contains large volumes of mixed pixels. # d) Data Preprocessing The image preprocessing is a technique which includes detection, restoration of bad lines, geometric rectification, radio metric calibration, atmospheric and topographic correction. If data is collected from different sources, it is necessary to check the quality before stepping into classification. If the single data image is utilized in classification atmospheric corrections may not be required but on the other hand it becomes mandatory for a multi-sensor data. A variety of correction techniques are presented [12][13][14][15][16][17][18][19][20][21][22][23].If the study area includes rugged or mountainous regions a topographic correction is needed, which is detailed [24][25][26][27][28][29][30]. # e) Feature Extraction and Selection The quality of an image classification depends on the selection of suitable variables. A variety of variables used in classification includes spectrum signature, vegetation indices, transformed images, textual information, multi temporal images, multi sensor images and ancillary data. The process of feature extraction is needed in order to minimize data redundancy in remotely sensed data or to excavate specific land cover information, that includes principle component analysis, minimum noise fraction transform discriminant analysis, decision boundary, feature extraction, non parametric weighted feature extraction, wavelet transform and spectral mixture analysis. # f) Selection of suitable classification method The question of choosing a classification method is ambiguous because many factors such as spatial resolution of RD, multi-sensor data, availability of different classification software are involved. Each classification method has its own merits and demerits. # g) Post classification processing Classification confusions arise in the regions such as urban areas, for example, consider between commercial and high intensity residential areas or between recreational grass and crops. In present example to reduce classification confusions we need to consider the property of spectral signature because it is similar to commercial and high intensity residential areas but on the other hand their population densities are different. Pasture and crops are largely located away from residential areas with sparse houses and low population densities, at this stage expert knowledge can be developed based on the relationship between housing or population densities and urban land use classes to help separate recreational grass from pasture and crops. # II. # Evaluation of Classification Performance Evaluating the classified results is an important step in classification procedure. The evaluation process may include qualitative evaluation based on expert knowledge to quantitative accuracy based on sampling strategies. The classification accuracy assessment is the most common approach for the evaluation of classification performance [31][32]. # a) Classification of accuracy assessment By the knowledge of sources of errors, classification accuracy assessment can be implemented in addition to classification error, position error, which resulting from registration, interpolating error and poor quality of training which may affect the classification accuracy. The classification accuracy assessment includes three basic steps 1.Sampling design, 2.Response design,3. Estimation and Analysis procedures # b) Advanced classification procedures The advanced classification procedures such as neural networks, fuzzy sets and expert systems are highly applied for image classification. In general image classification approaches it can be grouped as supervised or unsupervised, parametric and nonparametric or hard and soft classifiers or per pixel, sub pixel, per field. Table provides brief description of these categories. # c) Use of multiple features of remote sensed data Any remote sensed data generally contains many unique and special spectral radio metric temporal and polarization characteristics; the effective use of these features can improve the classification accuracy. The summary of table 3 presents the research efforts in order to improve the classification accuracy by considering the features of remote sensed data. # III. # Discussions a) Uncertainties in image classification Uncertainties in image classification occur at different stages, influence classification accuracy. Improving and understanding the stages those contribute to uncertainty results in quality image classification. # b) Impact of spatial resolution Spatial resolution is an important factor that affects classification details and accuracy, which influences the selection of a classification approach. Various reduction techniques have been developed and presented by different authors in their literature. # c) Selection of suitable variables In practice, making a complete use of multiple features of different sensor data, implementing feature extraction and selecting variables as input for a classification procedure becomes important. IV. # Conclusion This study helps upcoming scientists and researchers for opting a suitable classification procedure in their specific study. In our presentation we have concentrated extensively on the work done from the past decade that includes 1. Development and advanced classification algorithms such as sub pixel, per field and acknowledged based classification algorithms; 2. We have considered various remote sensing features including spectral, spatial, multi temporal and multi sensor information; 3. Incorporating an ancillary data into classification procedures that includes topography, soil, road and census data. [124], [125] [107], [126], [97], [127], [128] Visual fuzzy classification based on use of exploratory and interactive visualization techniques [129] Multi temporal classification based on decision fusion [130] Supervised classification with ongoing learning capability based on nearest neighbor rule [131] Combinative approaches of multiple classifiers Multiple classifier system (BAGFS: combines bootstrap aggregating with multiple feature subsets) [132] A consensus builder to adjust classification output (MLC, expert system, and neural network) [133] Integrated expert system and neural network classifier [133] Improved neuro-fuzzy image classification system, Spectral and contextual classifiers, Mixed contextual and per-pixel classification, Combination of iterated contextual probability classifier and MLC [134],[116], [135], [136] Combination of neural network and statistical consensus theoretic classifiers [137] Combination of MLC and neural network using Bayesian techniques [138] Combining # Use of textures First-, second-, and third-order statistics in the spatial domain; texture features from the texture spectrum and from grey level different vector [144] Grey-level co-occurrence matrices(GLCM) [145], [146], [147], [148], [149] Co-occurrence matrices, grey-level difference, texture-tone analysis ,features derived from Fourier spectrum, and Gabor filters [150] GLCM, grey level difference histogram, sum and different histogram [151], [152] Fractal information [153], [154] Triangulated primitive neighborhood method, Semi variogram, Geo statistical analysis, Gabor filtering [155], [156], [157], [158] [194], [195], [109], [196], [197], [97], [198], [199] Hyper -spectral data AVIRIS [200], [201], [202], [203], [204], [205] HyMap hyper spectral digital data, DAIS hyper spectral data, EO-1 Hyperion, Data obtained from Field Spec Pro FR spectro radiometer [127] [206] [207], [208] Based on topography, Based on census data, Based on illumination and ecological zone, Based on shape index of the Patches [215], [210], [216], [217] Post classification processing Kernel-based spatial reclassification [218] Using zoning and housing density data to modify the initial classification result, Using contextual correction, [213], [219] Using filtering based on co occurrence Matrix, Using polygon and rectangular mode filters, Using expert system to perform post classification sorting, Using knowledge-based system to correct misclassification [220], [221], [222], [223] Use of multisource data Spectral, texture, and ancillary data (such as DEM, soil, existing GIS-based maps) [123], [224], [225], [137],[226], [227],[7], [228] References Références Referencias 1CriteriaCategoriesCharacteristicsExample ofclassifiersWhetherSupervisedLand cover classes are defined. SufficientMaximum likelihood,trainingclassificationreference data is available and used asminimum distance,samples areapproachestraining samples. The signaturesartificial neural network,used or notgenerated from the training samples aredecision treethen used to train the classifier to classifyclassifier.the spectral data into a thematic mapUnsupervisedClustering-based algorithms are used toISODATA, K-meansclassificationpartition the spectral image into a numberclustering algorithmapproachesof spectral classes based on thestatistical information inherent in theimage. No prior definitions of the classesare used. The analyst is responsible forlabeling and merging the spectral classesinto meaningful classes.WhetherParametricGaussian distribution is assumed. TheMaximum likelihood,parametersclassifiersparameters (e.g. mean vector andlinear discriminantsuch ascovariance matrix) are often generated fromanalysis.mean vectortraining samples. When landscape isandcomplex, parametric classifiers oftencovarianceproduce 'noisy' results. Another majormatrix aredrawback is that it is difficult to integrateused or notancillary data, spatial and contextualattributes, and non-statistical information intoa classification procedure.Non-ParametricNo assumption about the data is required.Artificial neural network,classifiersNon-parametric classifiers do not employdecision tree classifier,statistical parameters to calculate classevidential reasoning,separation and are especially suitable forsupport vector machine,incorporation of non-remote-sensing dataexpert system.into a classification procedure.Which kind ofPer-pixelTraditional classifiers typically develop aMost of the classifiers,pixelclassifierssignature by combining the spectra of allsuch as maximuminformation istraining-set pixels from a given feature. Thelikelihood, minimumusedresulting signature contains thedistance, artificial neuralcontributions of all materials present in thenetwork, decision tree,training-set pixels, ignoring the mixed pixeland support vectorproblemsmachine.Sub pixelThe spectral value of each pixel is assumedFuzzy-set classifiers,classifiersto be a linear or non-linear combination ofsub pixel classifier,defined pure materials (or end members),spectral mixtureproviding proportional membership of eachanalysis.pixel to each end member.Which kind ofObject-orientedImage segmentation merges pixels intoE Cognitionpixelclassifiersobjects and classification is conductedinformation isbased on the objects, instead of anusedindividual pixel. No GIS vector data are used.Per-fieldGIS plays an important role in per-fieldGIS-basedclassifiersclassification, integrating raster and vectorclassificationdata in a classification. The vector data areapproachesoften used to subdivide an image intoparcels, and classification is based on theparcels, avoiding the spectral variationinherent in the same class.WhetherHardMaking a definitive decision about the landMost of the classifiers, 2CategoryAdvanced classifiersReferencesPer-pixelNeural network[33], [34], [35],[36], [37], [38], [39], [40],algorithms[41], [42], [43]Decision tree classifier, Spectral angle classifier,[44], [45], [46],[47],Supervised iterative classification (multistage[32],[8],[48],[49],[50], [51],[4]classification)Enhancement-classification approach,MFM-5-Scale[52],[53](Multiple-Forward-Mode approach to running the 5-Scalegeometric-optical reflectance model)Iterative partially supervised classification based on a[54]combined use of a Radial Basis Function network and aMarkov Random Field approachClassification by progressive generalization Support[31],[55], [56], [57], [58],[59],[60], [61],vector machine[62], [63]Unsupervised classification based on independent[64],[65], [66]componentanalysis mixture model, Optimal iterative unsupervisedModel-based unsupervised classification, Linear[67], [68] ,[69], [70]constrained discriminant analysisMultispectral classification based on probability density[71],[72],[73][74],[75],[76], [77]functions,Layered classification, Nearest-neighbor classification,Selected pixel classificationSub pixelalgorithmsImagine sub pixel classifier, Fuzzy classifier, Fuzzy expert system [78], [3],[79],[80],[81], [82] Fuzzy neural network, Fuzzy-based multi sensor data fusion classifier, Rule-based machine-version approach [3], [83],[84], [80], [85], [86], [87] Linear regression or linear least squares inversion [88],[89] [120],[121],[122], [123],[7], 3MethodFeaturesReferences 4FeaturesReferencesMethodUse of ancillaryDEM Topography, land use, and soil Maps[209] [210]dataRoad density, Road coverage, Census data[211] [212] [213], [214] [173]Stratification Techniques in Image Classification; A Survey Techniques in Image Classification; A Survey Techniques in Image Classification; A Survey Techniques in Image Classification; A Survey Techniques in Image Classification; A Survey Techniques in Image Classification; A Survey Techniques in Image Classification; A SurveyGlobal Journal of Researches in Engineering ( ) Volum Year 2015 22 F e XV Issue VI Version I F e XV Issue VI Version I Year 2015 Year 2015 26 32 Global Journal of Researches in Engineering ( ) Volum F e XV Issue VI Version I I I e XV Issue VI Version e XV Issue VI Version F Global Journal of Researches in Engineering ( ) Volum Fvector identification. Photogrammetric Engineering and Remote Sensing, reduction for land-use 58, pp. 423-437. 3. FOODY, G.M., 1996, Approaches for the production and evaluation of fuzzy land cover classification from remotely-sensed data. International Journal of Remote Sensing, 17, pp. 1317-1340. 4. SAN MIGUEL-AYANZ, J. and BIGING, G.S., 1997, Comparison of single-stage and multi-stage classification approaches for cover type mapping with TM and SPOT data. Remote Sensing of Environment, 59, pp. 92-104. 5. APLIN, P., ATKINSON, P.M. and CURRAN, P.J., 1999a, Per-field classification of land use using the forthcoming very fine spatial resolution satellite sensors: problems and potential solutions. In P.M. Atkinson and N.J. Tate (Eds), Advances in Remote Sensing and GIS Analysis, pp. 219-239 (New York: John Wiley and Sons). 6. STUCKENS, J., COPPIN, P.R. and BAUER, M.E., 2000, Integrating contextual information with per-pixel classification for improved land cover classification. Remote Sensing of Environment, 71, pp. 282-296. 7. FRANKLIN, S.E. and WULDER, M.A., 2002, Remote sensing methods in medium spatial resolution satellite data land cover classification of large areas. Progress in Physical Geography, 26, pp. 173-205. 8. PAL, M. and MATHER, P.M., 2003, An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sensing of Environment, 86, pp. 554-565. 9. GALLEGO, F.J., 2004, Remote sensing and land cover area estimation. International Journal of Remote Sensing, 25, pp. 3019-3047. 10. BARNSLEY, M.J., 1999, Digital remote sensing data and their characteristics. In P. Longley, M. Goodchild, D.J. Maguire and D.W. Rhind (Eds), Geographical Information Systems: Principles, techniques, applications, and management, 2nd edn, pp. 451-466 (NewYork: John Wiley and Sons). 11. LEFSKY, M.A. and COHEN, W.B., 2003, Selection of remotely sensed data. In M.A. Wulder and S.E. Franklin (Eds), Remote Sensing of Forest Environments: Concepts and case studies, pp. 13-46 (Boston: Kluwer Academic Publishers). 12. MARKHAM, B.L. and BARKER, J.L.,1987, Thematic Mapper bandpass solar exoatmospheric irradiances. International Journal of Remote Sensing, 8, pp. 517-523. 13. GILABERT, M.A., CONESE, C. and MASELLI, F., 1994, An atmospheric correction method for the automatic retrieval of surface reflectance from TM images. International Journal N of Remote Sensing, 15, pp. 2065-2086. 14. CHAVEZ, P.S. JR, 1996, Image-based atmospheric corrections-revisited and improved. Photogrammetric Engineering and Remote Sensing, 62, pp. 1025-1036. 27. MEYER, P., ITTEN, K.I., KELLENBERGER, T., SANDMEIER, S. and SANDMEIER, R., 1993, Radiometric corrections of topographically induced effects on Landsat TM data in alpine environment. ISPRS Journal of Photogrammetry and Remote Sensing, 48, pp.17-28. 28. RICHTER, R., 1997, Correction of atmospheric and topographic effects for high spatial resolution satellite imagery. International Journal of Remote Sensing, 18, pp. 1099-1111. 29. GU, D. and GILLESPIE, A., 1998, Topographic normalization of Landsat TM images of forest based on subpixel sun-canopy-sensor geometry. Remote Sensing of Environment, 64, pp. 166-175. 30. HALE, S.R. and ROCK, B.N., 2003, Impacts of topographic normalization on land-cover classification accuracy. Photogrammetric Engineering and Remote Sensing, 69, pp. 785-792. 31. CIHLAR, J., XIAO, Q., CHEN, J., BEAUBIEN, J., FUNG, K. and LATIFOVIC, R., 1998, Classification by progressive generalization: a new automated methodology for remote sensing multispectral data. International Journal of Remote Sensing, 19, pp.2685-2704. 32. DEFRIES, R.S. and CHAN, J.C., 2000, Multiple criteria for evaluating machine learning algorithms for land cover classification from satellite data. Remote Sensing of Environment, 74, pp. 503-515. 33. CHEN, K.S., TZENG, Y.C., CHEN, C.F. and KAO, W.L., 1995, Land-cover classification of multispectral imagery using a dynamic learning neural network. Photogrammetric Engineering and Remote Sensing, 61, pp. 403-408. 34. FOODY, G.M., MCCULLOCH, M.B. and YATES, W.B., 1995, Classification of remotely sensed data by an artificial neural network: issues related to training data characteristics. Photogrammetric Engineering and Remote Sensing, 61, pp. 391-401. 35. ATKINSON, P.M. and TATNALL, A.R.L., 1997, Neural networks in remote sensing. International Journal of Remote Sensing, 18, pp. 699-709. 36. FOODY, G.M. and ARORA, M.K., 1997, An evaluation of some factors affecting the accuracy of classification by an artificial neural network. International Journal of Remote Sensing, 18, pp. 799-810. 37. PAOLA, J.D. and SCHOWENGERDT, R.A., 1997, The effect of neural-network structure on amultispectral land-use/land-cover classification. Photogrammetric Engineering and Remote Sensing, 63, pp. 535-544. 38. FOODY, G.M., 2002a, Hard and soft classifications by a neural network with a nonexhaustively defined set of classes. International Journal of Remote Sensing, 23, pp.3853-3864. 39. OZKAN, C. and ERBEK, F.S., 2003, The comparison of activation functions for multispectral Landsat TM natural resources from satellite imagery. International Journal of Remote Sensing, 17, pp. 957-982. 52. BEAUBIEN, J., CIHLAR, J., SIMARD, G. and LATIFOVIC, R., 1999, Land cover from multiple Thematic Mapper scenes using a new enhancement-classification methodology. Journal of Geophysical Research, 104, pp. 27909-27920. 53. PEDDLE, D.R., JOHNSON, R.L., CIHLAR, J. and LATIFOVIC, R., 2004, Large area forest classification and biophysical parameter estimation using the 5-Scale canopy reflectance model in Multiple-Forward-Mode. Remote Sensing of Environment, 89,pp. 252-263. 54. FERNA´ NDEZ-PRIETO, D., 2002, An iterative approach to partially supervised classification problems. International Journal of Remote Sensing, 23, pp. 3887-3892. 55. BROWN, M., GUNN, S.R. and LEWIS, H.G., 1999, Support vector machines for optimal classification and spectral unmixing. Ecological Modeling, 120, pp. 167-179. 56. HUANG, C., DAVIS, L.S. and TOWNSHEND, J.R.G., 2002, An assessment of support vector machines for land cover classification. International Journal of Remote Sensing, 23, pp. 725-749. 57. HSU, C. and LIN, C., 2002, A comparison of methods for multi-class support vector machines. IEEE Transactions on Neural Networks, 13, pp. 415-425. 58. ZHU, G. and BLUMBERG, D.G., 2002, Classification using ASTER data and SVM algorithms: the case study of Beer Sheva, Israel. Remote Sensing of Environment, 80, pp. 233-240. 59. KEUCHEL, J., NAUMANN, S., HEILER, M. and SIEGMUND, A., 2003, Automatic land cover analysis for Tenerife by supervised classification using remotely sensed data. Remote Sensing of Environment, 86, pp. 530-541. 60. KIM, H., PANG, S., JE, H., KIM, D. and BANG, S.Y., 2003, Constructing support vector machine ensemble. Pattern Recognition, 36, pp. 2757-2767. 61. FOODY, G.M. and MATHUR, A., 2004a, A relative evaluation of multiclass image classification by support vector machines. IEEE Transactions on Geoscience and Remote Sensing, 42, pp. 1336-1343. 62. FOODY, G.M. and MATHUR, A., 2004b, Toward intelligent training of supervised image classifications: directing training data acquisition for 51. SAN MIGUEL-AYANZ, J. and BIGING, G.S., 1996, An iterative classification approach for mapping SVM classification. Remote Sensing of Environment, 93, pp. 107-117. 63. MITRA, P., SHANKAR, B.U. and PAL, S.K., 2004, Segmentation of multispectral remote sensing Pattern Recognition Letters, 25, pp. 1067-1074. images using active support vector machines. land use classes using nearest neighbor methods. Remote Sensing of Environment, 89, pp. 265-271. 77. EMRAHOGLU, N., YEGINGIL, I., PESTEMALCI, V., SENKAL, O. and KANDIRMAZ, H.M., 2003, Comparison of a new algorithm with the supervised classifications. International Journal of Remote Sensing, 24, pp. 649-655. 78. HUGUENIN, R.L., KARASKA, M.A., BLARICOM, D.V. and JENSEN, J.R., 1997, Subpixel classification of Bald Cypress and Tupelo Gum trees in Thematic Mapper imagery. Photogrammetric Engineering and Remote Sensing, 63, pp. 717-725. 79. MASELLI, F., RODOLFI, A. and CONESE, C., 1996, Fuzzy classification of spatially degraded Thematic Mapper data for the estimation of sub-pixel components. International Journal of Remote Sensing, 17, pp. 537-551. 80. ZHANG, J. and FOODY,G.M.,2001, Fully fuzzy supervised classification of sub-urban land cover from remotely sensed imagery: statistical neural network approaches. International Journal of Remote Sensing, 22, pp. 615-628. 81. SHALAN, M.A., ARORA, M.K. and GHOSH, S.K., 2003, An evaluation of fuzzy classifications from IRS 1C LISS III imagery: a case study. International Journal of Remote Sensing, 24, pp. 3179-3186. 82. PENALOZA, M.A. and WELCH, R.M., 1996, Feature selection for classification of polar regions using a fuzzy expert system. Remote Sensing of Environment, 58, pp. 81-100. 83. FOODY, G.M., 1999, Image classification with a neural network: from completely-crisp to fully-fuzzy situation. In P.M. Atkinson and N.J. Tate (Eds), Advances in Remote Sensing and GIS Analysis, pp. 17-37 (New York: John Wiley and Sons). 84. KULKARNI, A.D. and LULLA, K., 1999, Fuzzy neural network models for supervised classification: multispectral image analysis. Geocarto International, 14, pp. 42-50. 85. MANNAN, B. and RAY, A.K., 2003, Crisp and fuzzy competitive learning networks for supervised classification of multispectral IRS scenes. International Journal of Remote Sensing, 24, pp. 3491-3502. 86. SOLAIMAN, B., PIERCE, L.E. and ULABY, F.T., 1999, Multisensor data fusion using fuzzy concepts: application to land-cover classification using ERS-1/JERS-1 SAR composites. IEEE Transactions on Geoscience and Remote Sensing, 37, pp. 1316-1326. 100. GITAS, I.Z., MITRI, G.H. and VENTURA, G., 2004, Object-based image classification for burned area mapping of Creus Cape Spain, using NOAA-AVHRR imagery. Remote Sensing of Environment, 92, pp. 409-413. 101. WALTER, V., 2004, Object-based classification of remote sensing data for change detection. ISPRS Journal of Photogrammetry & Remote Sensing, 58, pp. 225-238. 102. BARNSLEY,MJ,andBARR,SL,1997recognitionsyste m.Computers, Distinguishing Urban Land Use Categories Environments and Urban Systems, 21, pp. 209-225. 103. CARLOTTO, M.J., 1998, Spectral shape classification of Lands at Thematic Mapper imagery. Photogrammetric Engineering and Remote Sensing, 64, pp. 905-913. 104. BIEHL, L. and LANDGREBE, D., 2002, MultiSpec-a 87. FOSCHI, P.G. and SMITH, D.K., 1997, Detecting subpixel woody vegetation in digital imagery using two artificial intelligence approaches. Photogrammetric Engineering and Remote Sensing, 63, pp. 493-500. 88. SETTLE, J. and CAMPBELL, N., 1998, On the errors of two estimators of subpixel fractional cover when tool for multispectral-hyperspectral image data analysis. Computers and Geosciences, 28, pp. 1153-1159. 105. LANDGREBE, D.A., 2003, Signal Theory Methods in Multispectral Remote Sensing (Hoboken,NJ: John Wiley and Sons). 106. LU, D. and WENG, Q., 2004, Spectral mixture analysis of the urban landscapes in Indianapolis with Landsat ETM+ imagery. Photogrammetric Engineering and Remote Sensing, 70, pp. 1053-1062. 107. KONTOES, C.C. and ROKOS, D., 1996, The integration of spatial context information in an experimental knowledge based system and the supervised relaxation algorithm: two successful approaches to improving SPOT-XS classification. International Journal of Remote Sensing, 17, pp. 3093-3106. 108. GONG, P. and HOWARTH, P.J., 1992, Frequency-based contextual classification and gray-levelvector reduction for land-use identification. Photogrammetric Engineering and Remote Sensing, 58, pp. 423-437. 109. XU, B., GONG, P., SETO, E. and SPEAR, R., 2003, Comparison of gray-level reduction and different texture spectrum encoding methods for land-use classification using a panchromatic IKONOS image. Photogrammetric Engineering and Remote Sensing, 69,pp. 529-536. 110. KARTIKEYAN, B., GOPALAKRISHNA, B., KALUBARME, M.H. and MAJUMDER, K.L., 1994, 111. Tate (Eds), Advances in Remote Sensing and GIS sensing of agriculture. International Journal of Geographical Information Systems, 7, pp. 247-262. 15. STEFAN, S. and ITTEN, K.I., 1997, A physically-based model to correct atmospheric and illumination effects in optical satellite data of rugged terrain. IEEE Transactions on Geoscience and Remote Sensing, 35, pp. 708-717. 16. VERMOTE, E., TANRE, D., DEUZE, J.L., HERMAN, M. and MORCRETTE, J.J., 1997, Second simulation of the satellite signal in the solar spectrum, 6S: an overview. IEEE Transactions on Geoscience and Remote Sensing, 35, pp. 675-686.\ 17. TOKOLA, T., LO¨ FMAN, S. and ERKKILA¨, A., 1999, Relative calibration of multitemporal Landsat data for forest cover change detection. Remote Sensing of Environment, 68, pp. 1-11. 18. HEO, J. and FITZHUGH, T.W., 2000, A standardized radiometric normalization method for change detection using remotely sensed imagery. Photogrammetric Engineering and Remote Sensing, 66, pp. 173-182. 19. SONG, C., WOODCOCK, C.E., SETO, K.C., LENNEY, M.P. and MACoMBER, S.A., 2001, Classification and change detection using Landsat TM data: when and how to correct atmospheric effect. Remote Sensing of Environment, 75, pp. 230-244. 20. DU, Y., TEILLET, P.M. and CIHLAR, J., 2002, Radiometric normalization of multitemporal high-resolution satellite images with quality control for land cover change detection. Remote Sensing of Environment, 82, pp. 123-134. 21. MCGOVERN, E.A., HOLDEN, N.M., WARD, S.M. and COLLINS, J.F., 2002, The radiometric normalization of multitemporal Thematic Mapper imagery of the midlands of Ireland-a case study. International Journal of Remote Sensing, 23, pp. 751-766. 22. CANTY, M.J., NIELSEN, A.A. and SCHMIDT, M., 2004, Automatic radiometric normalization of multitemporal satellite imagery. Remote Sensing of Environment, 91, pp. 441-451. 23. HADJIMITSIS, D.G., CLAYTON, C.R.I. and HOPE, V.S., 2004, An assessment of the effectiveness of atmospheric correction algorithms through the remote sensing of some reservoirs. International Journal of Remote Sensing, 25, pp. 3651-3674. 24. TEILLET, P.M., GUINDON, B. and GOODENOUGH, D.G., 1982, On the slope-aspect correction of multispectral scanner data. Canadian Journal of Remote Sensing, 8, pp. 84-106. 25. CIVCO, D.L., 1989, Topographicssa normalization of Landsat Thematic Mapper digital imagery. Photogrammetric Engineering and Remote Sensing, 55, pp. 1303-1309. 26. COLBY, J.D., 1991, Topographic normalization in rugged terrain. Photogrammetric Engineering and Remote Sensing, 57, pp. 531-537. image classification. Photogrammetric Engineering and Remote Sensing,69, pp. 1225-1234. 40. FOODY, G.M., 2004b, Supervised image classification by MLP and RBF neural networks with and without an exhaustively defined set of classes. International Journal of Remote Sensing, 25, pp. 091-3104. 41. ERBEK, F.S., OZKAN, C. and TABERNER, M., 2004, Comparison of maximum likelihood classification method with supervised artificial neural network algorithms for land use activities. International Journal of Remote Sensing, 25, pp. 1733-1748. 42. KAVZOGLU, T. and MATHER, P.M., 2004, The use of backpropagating artificial neural networks in land cover classification. International Journal of Remote Sensing, 24, pp. 4907-4938. 43. VERBEKE, L.P.C., VABCOILLIE, F.M.B. and DE WULF, R.R., 2004, Reusing back-propagating artificial neural network for land cover classification in tropical savannahs. International Journal of Remote Sensing, 25, pp. 2747-2771. 44. HANSEN, M., DUBAYAH, R. and DEFRIES, R., 1996, Classification trees: an alternative to traditional land cover classifiers. International Journal of Remote Sensing, 17, pp. 1075-1081. 45. FRIEDL, M.A. and BRODLEY, C.E., 1997, Decision tree classification of land cover from remotely sensed data. Remote Sensing of Environment, 61, pp. 399-409. 46. DEFRIES, R.S., HANSEN, M., TOWNSHEND, J.R.G. and SOHLBERG, R., 1998, Global land cover classification at 8 km spatial resolution: the use of training data derived from Landsat imagery in decision tree classifiers. International Journal of Remote Sensing, 19, pp. 3141-3168. 47. FRIEDL, M.A., BRODLEY, C.E. and STRAHLER, A.H., 1999, Maximizing land cover classification accuracies produced by decision trees at continental to global scales. IEEE Transactions on Geoscience and Remote Sensing, 37, pp. 969-977. 48. LAWRENCE, R., BUNN, A., POWELL, S. and ZMABON, M., 2004, Classification of remotely sensed imagery using stochastic gradient boosting as a refinement of classification tree analysis. Remote Sensing of Environment, 90, pp. 331-336. 49. SOHN, Y., MORAN, E. and GURRI, F., 1999, Deforestation in north-central Yucatan (1985-1995): mapping secondary succession of forest and agricultural land use in Sotuta using the cosine of the angle concept. Photogrammetric Engineering and Remote Sensing, 65, pp. 947-958. 50. SOHN, Y. and REBELLO, N.S., 2002, Supervised and unsupervised spectral angle classifiers. Photogrammetric Engineering and Remote Sensing, 68, pp. 1271-1281. 64. LEE, T.W., LEWICKI, M.S. and SEJNOWSKI, T.J., 2000, ICA mixture models for unsupervised classification of non-gaussian classes and automatic context switching in blind signal separation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22, pp. 1078-1089. 65. SHAH, C.A., ARORA, M.K. and VARSHNEY, P.K., 2004, Unsupervised classification of hyperspectral data: an ICA mixture model based approach. International Journal of Remote Sensing, 25, pp. 481-487. 66. JIANG, H., STRITTHOLT, J.R., FROST, P.A. and SLOSSER, N.C., 2004, The classification of late seral forests in the Pacific Northwest USA using Landsat ETM+ imagery. Remote Sensing of Environment, 91, pp. 320-331. 67. KOLTUNOV, A. and BEN-DOR, E., 2001, A new approach for spectral feature extraction and for unsupervised classification of hyperspectral data based on the Gaussian mixture model. Remote Sensing Reviews, 20, pp. 123-167. 68. KOLTUNOV, A. and BEN-DOR, E., 2004, Mixture density separation as a tool for high-quality interpretation of multi-source remote sensing data and related issues. International Journal of Remote Sensing, 25, pp. 3275-3299. 69. DU, Q. and CHANG, C., 2001, A linear constrained distance-based discriminant analysis for hyperspectral image classification. Pattern Recognition, 34, pp. 361-373. 70. DU, Q. and REN, H., 2003, Real-time constrained linear discriminant analysis to target detection and classification in hyperspectral imagery. Pattern Recognition, 36, pp. 1-12. 71. EROL, H. and AKDENIZ, F., 1996, A multi-spectral classification algorithm for classifying parcels in an agricultural region. International Journal of Remote Sensing, 17, pp. 3357-3371. 72. EROL, H. and AKDENIZ, F., 1998, A new supervised classification method for quantitative analysis of remotely sensed multi-spectral data. International Journal of Remote Sensing, 19, pp. 775-782. 73. JENSEN, J.R., 1996, Introduction to Digital Image Processing: A remote sensing perspective, 2nd edn (Piscataway, NJ: Prentice Hall). 74. HARDIN, P.J., 1994, Parametric and nearest-neighbor methods for hybrid classification: a comparison of pixel assignment accuracy. Photogrammetric Engineering and Remote Sensing, 60, pp. 1439-1448. 75. COLLINS, M.J., DYMOND, C. and JOHNSON, E.A., 2004, Mapping subalpine forest types using networks of nearest neighbor classifiers. International Journal of Remote Sensing, 25, pp. 1701-1721. 76. HAAPANEN, R., EK, A.R., BAUER, M.E. and FINLEY, A.O., 2004, Delineation of forest/nonforest mixing is linear. IEEE Transactions on Geosciences and Remote Sensing, 36, pp. 163-169. 89. FERNANDES, R., FRASER, R., LATIFOVIC, R., CIHLAR, J., BEAUBIEN, J. and DU, Y., 2004, Approaches to fractional land cover and continuous field mapping: a comparative assessment over the BOREAS study region. Remote Sensing of Environment, 89, pp. 234-251. 90. LOBO, A., CHIC, O. and CASTERAD, A., 1996, Classification of Mediterranean crops with multisensor data: per-pixel versus per-object statistics and image segmentation. International Journal of Remote Sensing, 17, pp. 2385-2400. 91. DEAN, A.M. and SMITH, G.M., 2003, An evaluation of per-parcel land cover mapping using maximum likelihood class probabilities. International Journal of Remote Sensing, 24, pp. 2905-2920. 92. APLIN, P. and ATKINSON, P.M., 2001, sub-pixel land cover mapping for per-field classification. International Journal of Remote Sensing, 22, pp. 2853-2858. 93. SMITH, G.M. and FULLER, R.M., 2001, An integrated approach to land cover classification: an example in the Island of Jersey. International Journal of Remote Sensing, 22, pp. 3123-3142. 94. CHALIFOUX, S., CAVAYAS, F. and GRAY, J.T., 1998, Mapping-guided approach for the automatic detection on Landsat TM images of forest stands damaged by the spruce budworm. Photogrammetric Engineering and Remote Sensing, 64, pp. 629-635. 95. HEROLD, M., LIU, X. and CLARKE, K.C., 2003, Spatial metrics and image texture for mapping urban land use. Photogrammetric Engineering and Remote Sensing, 69, pp. 991-1001. 96. GENELETTI, D. and GORTE, B.G.H., 2003, A method for object-oriented land cover classification combining Landsat TM data and aerial photographs. International Journal of Remote Sensing, 24, pp. 1273-1286. 97. THOMAS, N., HENDRIX, C. and CONGALTON, R.G., 2003, A comparison of urban mapping methods using high-resolution digital imagery. Photogrammetric Engineering and Remote Sensing, 69, pp. 963-972. 98. VAN DER SANDE, C.J., DE JONG, S.M. and DE ROO, A.P.J., 2003, A segmentation and classification approach of IKONOS-2 imagery for land cover mapping to assist flood risk and flood damage assessment. International Journal of Applied Earth Observation and Geoinformation, 4, pp. 217-229. 99. BENZ, U.C., HOFMANN, P., ILLHAUCK, G., LINGENFELDER, I. and HEYNEN, M., 2004, Multi-pp. 239-258. Engineering and Remote Sensing, 62, pp. 513-523. Journal of Photogrammetry & Remote Sensing, 58, for geological mapping. Photogrammetric sensing data for GIS ready information. ISPRS reasoning and artificial neural network techniques resolution, object-oriented fuzzy analysis of remote Analysis, pp. 135-146 (New York: John Wiley and Sons). 119. KARTIKEYAN, B., SARKAR, A. and MAJUMDER, K.L., 1998, A segmentation approach to classification of remote sensing imagery. International Journal of Remote Sensing, 19, pp. 1695-1709. 120. Canadian Journal of Remote Sensing, 20, pp. 380-395. 122. PEDDLE, D.R., 1995, Knowledge formulation for supervised evidential 226. BRUZZONE, L., PRIETO, D.F. and SERPICO, S.B., classification. Contextual techniques for classification of high and low resolution remote sensing data. International Journal of Remote Sensing, 15, pp. 1037-1051. 1999, A neural-statistical approach to multitemporal Photogrammetric Engineering and Remote Sensing, from multiple sources: using evidential and Remote Sensing, 37, pp. 1350-1359. 123. GONG, P., 1996, Integrated analysis of spatial data classification. IEEE Transactions on Geoscience 61, pp. 409-417. sensing image and multisource remote-Year 2015 F Global Journal of Researches in Engineering ( ) Volume XV Issue VI Version I 25 Year 2015 F Year 2015 27 Global Journal of Researches in Engineering VI Version I ( ) Volume XV Issue F© 2015 Global Journals Inc. (US)© 20 15 Global Journals Inc. (US)1. GONG, P. and HOWARTH, P.J., 1992, Frequencybased contextual classification and gray-level 2. KONTOES, C., WILKINSON, G.G., BURRILL, A., GOFFREDO, S. and MEGIER, J., 1993, An experimental system for the integration of GIS data in knowledge-based image analysis for remote © 2015 Global Journals Inc. (US) © 20 15 Global Journals Inc. (US) 227. TSO, B.C.K. and MATHER, P.M., 1999, Classification of multisource remote sensing imagery using a genetic algorithm and Markov © 20 15 Global Journals Inc. (US) © 2015 Global Journals Inc. (US) F e XV Issue VI Version I Techniques in Image Classification; A Survey * International Journal of Remote Sensing 25 * Classification of multisource and hyperspectral data based on decision fusion JABenediktsson IKanellopoulos IEEE Transactions on Geoscience and Remote Sensing 37 1999 * Fusion of image classification using Bayesian techniques with Markov random fields CEWarrender MFAugusteihn International Journal of Remote Sensing 20 1999 * Combining multiple classifiers: an application using spatial and remotely sensed information for land cover type mapping BMSteele Remote Sensing of Environment 74 2000 * A quantitative assessment of a combined spectral and GIS rulebased land-cover classification in the Neuse river basin of North Carolina RSLunetta JEdiriwckrema JIiames DMJohnson JGLyon AMckerrow APilant Photogrammetric Engineering and Remote Sensing 69 2003 * Spectral mixture analysis of the urban landscapes in Indianapolis with Landsat ETM+ imagery DLu QWeng Photogrammetric Engineering and Remote Sensing 70 2004 * Combining nonparametric models for multisource predictive forest mapping ZHuang BGLees Photogrammetric Engineering and Remote Sensing 70 2004 * A hybrid approach to urban land use/cover mapping using Landsat 7 CPLo JChoi 2004 * Enhanced Thematic Mapper Plus (ETM + ) images International Journal of Remote Sensing 25 * Evaluation of speckle filtering and texture analysis methods for land cover classification from SAR images ANyoungui ETonye AAkono International Journal of Remote Sensing 23 2002 * An investigation of the textural characteristics associated with gray level cooccurrence matrix statistical parameters ABaraldi FParmiggiani IEEE Transactions on Geoscience and Remote Sensing 33 1995 * Land use classification with textural analysis and the aggregation technique using multi-temporal TKurosu SYokoyama KChiba 2001 * Optimization of multisource data analysis: an example using evidential reasoning for GIS data classification DRPeddle DTFerguson Computers &Geosciences 28 2002 * Applying evidential reasoning methods to agricultural land cover classification JKLein International Journal of Remote Sensing 24 2003 * A subpixel classifier for urban land-cover mapping based on a maximum-likelihood approach and expert system rules MHung MKRidd Photogrammetric Engineering and Remote Sensing 68 2002 * Mapping coastal vegetation using an expert system and hyperspectral imagery KSSchmidt AKSkidmore EHKloosterman HVan Oosten LKumar JA MJanssen Photogrammetric Engineering and Remote Sensing 70 2004 * Designing a rulebased classifier using syntactical approach HMOnsi International Journal of Remote Sensing 24 2003 * Interactive and visual fuzzy classification of remotely sensed imagery for exploration of uncertainty ALucieer MKraak International Journal of Geographic Information Science 18 2004 * Decision fusion approaches for multitemporal classification BJeon DALandgrebe IEEE Transactions on Geoscience and Remote Sensing 37 1999 * Supervised classification of remotely sensed data with ongoing learning capability RBarandela MJuarez International Journal of Remote Sensing 23 2002 * Textural and contextual land-cover classification using single and multiple classifier systems ODebeir Van Den ISteen PLatinne PVan Ham EWolff Photogrammetric Engineering and Remote Sensing 68 2002 * Integration of classification methods for improvement of land-cover map accuracy XLiu AKSkidmore HVOosten ISPRS Journal of Photogrammetry and Remote Sensing 56 2002b * Opening the black box of neural networks for remote sensing image classification FQiu JRJensen International Journal of Remote Sensing 25 2004 * Evaluation of contextual, per-pixel and mixed classification procedures applied to a subtropical landscape CConese FMaselli Remote Sensing Reviews 9 1994 * Classification of forest volume resources using ERS JERS -1 L -band SAR images KJTansey AJLuckman LSkinner HBalzter TStrozzi WWagner International Journal of Remote Sensing 22 2004 * Textural analysis of IRS-1D panchromatic data for land cover classification Narasimha PVRao MV RSesha Sai KSreenivas MVRao BR MRao RSDwivedi LVenkataratnam International Journal of Remote Sensing 23 2002 * Application of multiscale texture in classifying JERS-1 radar data over tropical vegetation EPodest SSaatchi International Journal of Remote Sensing 23 2002 * OBButusov Textural classification of forest types from Land sat 7 imagery. Mapping Sciences and Remote Sensing 2003 40 * Performance evaluation of texture measures for ground cover identification in satellite images by means of a neural network classifier MFAugusteijn LEClemens KAShaw IEEE Transactions on Geo science and Remote Sensing 33 1995 * An investigation of the selection of texture features for crop discrimination using SARimagery JVSoares CDRenno ARFormaggio CC FYanasse ACFrery Remote Sensing of Environment 59 1997 * Improvement of classification in urban areas by the use of textural features: the case study of Lucknow city MAShaban ODikshit International Journal of Remote Sensing 22 2001 * Neural classification of SPOT imagery through integration of intensity and fractal information KSChen SKYen DWTsay International Journal of Remote Sensing 18 1997 * A neural network land use classifier for SAR images using textural and fractal information HKLow HTChuah HTEwe Geocarto International 14 1999 * An object-specific image-texture analysis of H-resolution forest imagery GJHay KONiemann GFMclean Remote Sensing of Environment 55 1996 * The semivariogram in comparison to the co-occurrence matrix for classification of image texture JRCarr FPMiranda IEEE Transactions on Geoscience and Remote Sensing 36 1998 * A comparison oftexture measures for the per-field classification of Mediterranean land cover CDLloyd SBerberoglu PJCurran PMAtkinson International Journal of Remote Sensing 25 2004 * Geostatistical and texture analysis of airborneacquired images used in forest classification CZhang SEFranklin MAWulder 2004 * GHurtt XXiao MKeller MPalace GPAsner RBraswell ESBrondizio MCardoso CJ RCarvalho MGFearon LGuild DLu QWeng Hagen SHetrick SMoore Iii BNobre CRead JMSa TSchloss AVourlitis GWickel AJ 2003 88 IKONOS imagery for the Large ScaleBiosphere-Atmosphere Experiment in Amazonia (LBA). Remote Sensing of Environment * A segmentation and classification approach of IKONOS-2 imagery for land cover mapping to assist flood risk and flood damage assessment CJVan Der Sande SMDe Jong AP JRoo International Journal of Applied Earth Observation and Geo information 4 2003 * A rule-based urban land use inferring method for fine resolution multispectral imagery QZhang JWang Canadian Journal of Remote Sensing 29 2003 * Comparison of IKONOS and Quick Bird images for mapping mangrove species on the Caribbean coast of panama. remote Sensing of Environment LWang WPSousa PGong GSBiging 2004 91 * Synergistic use lidar and color aerial photography for mapping urban parcel imperviousness. photogrammetric Engineering and Remote Sensing MEHodgson JRJensen JATullis KDRiordan CMArcher 2003 69 * Species classification of individually segmented tree crowns in high resolution aerial images using radiometric and morphologic image measures MErikson Remote Sensing of Environment 91 2004 * Classification and feature extraction of AVIRIS data JABenediktsson JRSveinsson KArnason IEEE Transactions on Geo science and Remote Sensing 33 1995 * Classification of hyper dimensional data based on feature and decision fusion approaches using projection pursuit, majority voting, and neural networks LOJimenez AMorales-Morell ACreus analysis of AVIRIS data. Remote Sensing of Environment 37 1999 IEEE Transactions on Geo science and Remote Sensing * Fusion of spectral and shapefeatures for identification of urban surface cover types using reflective and thermalhyperspectral data KSegl SRoessner UHeiden HKaufmann ISPRS Journal of Photogrammetry and Remote Sensing 58 2003 * A comparison of AVIRIS and Land sat for land use classification at the urban fringe RVPlatt AF HGoetz Photogrammetric Engineering and Remote Sensing 70 2004 * Assessment of the effectiveness of support vector machines for hyper spectral data MPal PMMather Future Generation Computer System 20 2004 * Detecting sugarcane 'orange rust'disease using EO-1 Hyperion hyperspectral imagery AApan AHeld SPhinn JMarkley International Journal of Remote Sensing 25 2004 * Accuracy assessments of hyperspectral waveband performance for vegetation analysis applications PSThenkabail EAEnclona MSAshton BVan Der Meer Remote Sensing of Environment 91 2004a * Classification of Mediterranean vegetation by TM and ancillary data for the evaluation of fire risk FMaselli ARodolfi LBottai SRomanelli CConese International Journal of Remote Sensing 21 2000 * Mapping land use/cover distribution on amountainous tropical island using remote sensing and GIS SM JBaban KWYusof International Journal of Remote Sensing 22 2001 * Urban built-up land change detection with road density and spectral information from multitemporal LandsatTM data QZhang JWang XPeng PGong PShi International Journal of Remote Sensing 23 2002 * Techniques for mapping suburban sprawl JEpstein KPayne EKramer Photogrammetric Engineering and Remote Sensing 68 2002 * Practical limits on hyperspectral vegetation discrimination in arid and semiarid environments PMHarris SJVentura GSOkin DARoberts BMurray WJOkin Remote Sensing of Environment 77 1995. 2001 The integration of geographic data with remotelysensed 202 * Mapping vegetation in Yellowstone National Park using spectral feature imagery to improve classification in an urban area RFKokalya DGDespain RNClark KELivo Photogrammetric Engineering and Remote Sensing 61 2003 * The use of census data in urban image classification VMesev Photogrammetric Engineering and Remote Sensing 64 1998 * Mapping boreal vegetation using Landsat TM and topographic mapdata in a stratified approach LBBronge Canadian Journal of Remote Sensing 25 1999 * Mapping montane tropical forest successional stage and land use with multi-date Landsat imagery EHHelmer SBrown WBCohen International Journal of Remote Sensing 21 2000 * Utilizing geometric attributes of spatial linformation to improve digital image classification SNarumalani YZhou DEJelinski Remote Sensing Reviews 16 1998 * Inferring urban land use from satellite sensor imagesusing kernel-based spatial reclassification MJBarnsley SLBarr 1996 * Photogrammetric Engineering and Remote Sensing 62 * Contextual correction: techniques for improving land cover mapping from remotely sensed images GBGroom RMFuller ARJones International Journal of Remote Sensing 17 1996 * Optimisation of building detection in satellite images by combining multispectral classification and texture filtering YZhang ISPRS Journal of Photogrammetry and Remote Sensing 54 1999 * Incorporating ancillary data into alogical filter for classified satellite imagery CStallings SKhorram RLHuffman Geocarto International 14 1999 * Monitoring urban land coverchange: an expert system approach to land cover classification of semiarid to aridurban centers WLStefanov MSRamsey PRChristensen Remote Sensing of Environment 77 2001 * Remote sensing image analysis using a neural network and knowledge-based processing HMurai SOmatu International Journal of Remote Sensing 18 1997 * A Markov random field model for classification of multisource satellite imagery AH SSolberg TTaxt AKJain IEEE Transactions on Geoscience andRemote Sensing 34 1996 * Multisource classification of complex rural areas by statistical and neural-network approaches LBruzzone CConese FMaselli FRoli IEEE Transactions on Geoscience and Remote Sensing 63 1997 Photogrammetric Engineering and Remote Sensing * Data fusion and multisource image classification DAmarsaikhan TDouglas International Journal of Remote Sensing 25 2004