Backpropagation neural networks have been developed for detection of geological lineaments in Landsat Thematic Mapper (TM) imagery of the Canadian Shield using edge images as input and digitized lineament maps as the desired output. Lineament detection is a challenging problem for traditional image processing and pattern recognition techniques. Many linear features observable in geological image data do not represent lineaments and the presence mnd extent of lineaments must be inferred from contextual information. In order to compare the ability of neural networks and conventional classifiers to recognize lineaments prior to performing edge/line element grouping operations, we first extracted various gradient and curvature features from the image data set. Selected features from this group formed the inputs to backpropagation neural networks, linear discriminant classifiers, and nearest neighbor classifiers. The neural network results were compared with the results obtained using conventional classifiers for sample training and test sets. The trained neural network was then applied to the edge image to mask out those edge points which had been classified as non-lineament points.
The method of Phase Diversity is used to measure the aberrations caused by atmosphere and system distortions. Two images are taken: one at a focused position and the other at a known defocused position. By minimizing the Gonsalves metric, the Zernike coefficients are estimated and thus the aberration that produced the distortion in the original image is computed. Being a nonlinear optimization technique involving several variables, the method is very computationally intensive. We introduce a method using nonlinear optimization involving only a single variable to independently, and potentially concurrently, evaluate the different Zernike coefficients to obtain the wavefront error. The method of independent evaluation of Zernike coefficients can be further speeded up by using parallel processing and neural network techniques. Our method is demonstrated for both for point source objects as well as extended objects.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.