RESEARCH ARTICLE Effectiveness of SID as Spectral Similarity Measure to Develop Crop Spectra from Hyperspectral Image Hasmukh J. Chauhan 1 • B. Krishna Mohan 2 Received: 30 May 2015 / Accepted: 23 August 2018 Ó Indian Society of Remote Sensing 2018 Abstract The present study was undertaken with the objective to check effectiveness of spectral information divergence (SID) to develop spectra from image for crop classes based on spectral similarity with field spectra. In multispectral and hyper- spectral remote sensing, classification of pixels is obtained by statistical comparison (by means of spectral similarity) of known field or library spectra to unknown image spectra. Though these algorithms are readily used, little emphasis has been placed on use of various spectral similarity measures to develop crop spectra from the image itself. Hence, in this study methodology suggested to develop spectra for crops based on SID. Absorption features are unique and distinct; hence, validation of the developed spectra is carried out using absorption features by comparing it with field spectra and finding average correlation coefficient r = 0.982 and computed SID equivalent r = 0.989. Effectiveness of developed spectra for image classification was computed by probability of spectral discrimination (PSD) and resulted in higher probability for the spectra developed based on SID. Image classification was carried out using field spectra and spectra assigned by SID. Overall classification accuracy of the image classified by field spectra is 78.30% and for the image classified by spectra assigned through SID-based approach is 91.82%. Z test shows that image classification carried out using spectra developed by SID is better than classification carried out using field spectra and significantly different. Validation by absorption features, effectiveness by PSD and higher classification accuracy show possibility of new approach for spectra development based on SID spectral similarity measure. Keywords Spectral similarity Á Probability of spectral discrimination (PSD) Á Visually inseparable classes Introduction Spectral similarity measures are successfully applied for differentiating among vegetation and surroundings soil (Chang 2000; Du et al. 2004), to differentiate among mineral spectral response (Van der Meer 2005) and to separate crop types (Kong Xiangbing et al. 2010). In the present study, spectral similarity measure is efficiently used to find out similarity between the field spectra and endmembers spectra derived from image to develop crop spectra. Van der Meer (2005) used probability of spectral discrimination (PSD) to assess the performance of the spectral angle mapper (SAM), spectral correlation mapper (SCM), Euclidian distance (ED) and spectral information divergence (SID). PSD narrates the capability of the chosen set of spectra to map a target spectrum. In this study based on PSD, it was found that SID is more effectively mapping discrepancy between two pixel vectors. Hence, to accu- rately define the discrepancy between two pixel vectors SID (Chang, 2000) is used as spectral similarity evaluator. The SID evaluator calculates similarity among the proba- bility distributions resulted by the spectral response of two pixels given as, SID r i ; r j   ¼ Dr i jj r j   þ Dr j jj r i   ð1Þ & Hasmukh J. Chauhan hjchauhan@bvmengineering.ac.in B. Krishna Mohan bkmohan@csre.iitb.ac.in 1 Civil Engg, Deptt, BVM Engineering College, V.V. Nagar, Gujarat, India 2 Centre of Studies in Resources Engineering, IIT, Bombay, India 123 Journal of the Indian Society of Remote Sensing https://doi.org/10.1007/s12524-018-0845-4