@book{nelson_khorram_2018, title={Image Processing and Data Analysis with ERDAS IMAGINE®}, ISBN={9781315269948}, url={http://dx.doi.org/10.1201/b21969}, DOI={10.1201/b21969}, publisher={CRC Press}, author={Nelson, Stacy A. C. and Khorram, Siamak}, year={2018}, month={Oct} }
 @article{khorram_yuan_van der wiele_2011, title={Development of a modified neural network-based land cover classification system using automated data selector and multiresolution remotely sensed data}, volume={26}, ISSN={1010-6049 1752-0762}, url={http://dx.doi.org/10.1080/10106049.2011.600462}, DOI={10.1080/10106049.2011.600462}, abstractNote={Integrating multiple images with artificial neural networks (ANN) improves classification accuracy. ANN performance is sensitive to training datasets. Complexity and errors compound when merging multiple data, pointing to needs for new techniques. Kohonen's self-organizing mapping (KSOM) neural network was adapted as an automated data selector (ADS) to replace manual training data processes. The multilayer perceptron (MLP) network was then trained using automatically extracted datasets and used for classification. Two hypotheses were tested: ADS adapted from the KSOM network provides adequate and reliable training datasets, improving MLP classification performance; and fusion of Landsat thematic mapper (TM) and SPOT images using the modified ANN approach increases accuracy. ADS adapted from the KSOM network improved training data quality and increased classification accuracy and efficiency. Fusion of compatible multiple data can improve performance if appropriate training datasets are collected. This proved to be a viable classification scheme particularly where acquiring sufficient and reliable training datasets is difficult.}, number={6}, journal={Geocarto International}, publisher={Informa UK Limited}, author={Khorram, Siamak and Yuan, Hui and Van Der Wiele, Cynthia F.}, year={2011}, month={Sep}, pages={435–457} }
 @article{krish_heinrich_snyder_cakir_khorram_2010, title={Global registration of overlapping images using accumulative image features}, volume={31}, ISSN={0167-8655}, url={http://dx.doi.org/10.1016/j.patrec.2009.09.016}, DOI={10.1016/j.patrec.2009.09.016}, abstractNote={This paper introduces a new feature-based image registration technique which registers images by finding rotation- and scale-invariant features and matching them using a novel feature matching algorithm based on an evidence accumulation process reminiscent of the generalized Hough transform. Once feature correspondence has been established, the transformation parameters are then estimated using non-linear least squares (NLLS) and the standard RANSAC (random sample consensus) algorithm. The technique is evaluated under similarity transforms – translation, rotation and scale (zoom) and also under illumination changes.}, number={2}, journal={Pattern Recognition Letters}, publisher={Elsevier BV}, author={Krish, Karthik and Heinrich, Stuart and Snyder, Wesley E. and Cakir, Halil and Khorram, Siamak}, year={2010}, month={Jan}, pages={112–118} }
 @article{hester_nelson_cakir_khorram_cheshire_2010, title={High-resolution land cover change detection based on fuzzy uncertainty analysis and change reasoning}, volume={31}, ISSN={0143-1161 1366-5901}, url={http://dx.doi.org/10.1080/01431160902893493}, DOI={10.1080/01431160902893493}, abstractNote={Land cover change detection is an important research and application area for analysts of remote sensing data. The primary objective of the research described here was to develop a change detection method capable of accommodating spatial and classification uncertainty in generating an accurate map of land cover change using high resolution satellite imagery. As a secondary objective, this method was designed to facilitate the mapping of particular types and locations of change based on specific study goals. Urban land cover change pertinent to surface water quality in Raleigh, North Carolina, was assessed using land cover classifications derived from pan-sharpened, 0.61 m QuickBird images from 2002 and 2005. Post-classification map errors were evaluated using a fuzzy logic approach. First, a ‘change index’ representing a quantitative gradient along which land cover change is characterized by both certainty and relevance, was created. The result was a continuous representation of change, a product type that retains more information and flexibility than discrete maps of change. Finally, fuzzy logic and change reasoning results were integrated into a binary change/no change map that quantified the most certain, likely, and relevant change regions within the study area. A ‘from-to’ change map was developed from this binary map inserting the type of change identified in the raw post-classification map. A from-to change map had an overall accuracy of 78.9% (κ = 0.747) and effectively mapped land cover changes posing a threat to water quality, including increases in impervious surface. This work presents an efficient fuzzy framework for transforming map uncertainty into accurate and practical change analysis.}, number={2}, journal={International Journal of Remote Sensing}, publisher={Informa UK Limited}, author={Hester, D. B. and Nelson, S. A. C. and Cakir, H. I. and Khorram, S. and Cheshire, H.}, year={2010}, month={Jan}, pages={455–475} }
 @article{cakir_khorram_nelson_2006, title={Correspondence analysis for detecting land cover change}, volume={102}, ISSN={0034-4257}, url={http://dx.doi.org/10.1016/j.rse.2006.02.023}, DOI={10.1016/j.rse.2006.02.023}, abstractNote={The correspondence analysis (CA) method was applied to two multitemporal Landsat images of Raleigh, North Carolina for land use land cover (LULC) change detection. After the spectral transformation of the individual date images into component space using CA, the first component (PC1) of the date 1 image was subtracted from the PC1 of the date 2 image to produce difference image highlighting change areas. Accuracy curves based on the cumulative Producer's and User's accuracies were then used to optimally locate threshold (cutoff) values in the high-end and low-end tails of the difference image's histogram. Results were then compared to the standardized and non-standardized Principal Component Analysis (PCA) differencing and Normalized Difference Vegetation Index (NDVI) differencing methods for change detection. Results showed that there was 6.8% increase in urban related cover types in Raleigh metropolitan area between 1993 and 1999. Also, maps based on the CA differencing method were found to be thematically more accurate than maps based on PCA component differencing methods. Overall accuracy of change map produced by the CA method for the Raleigh metropolitan area was 92.5% with overall Kappa value of 0.88. In general, CA was found to be a powerful multivariate analysis technique when applied to change detection.}, number={3-4}, journal={Remote Sensing of Environment}, publisher={Elsevier BV}, author={Cakir, Halil Ibrahim and Khorram, Siamak and Nelson, Stacy A.C.}, year={2006}, month={Jun}, pages={306–317} }