Optimal Gabor filter-based edge detection of high spatial resolution remotely sensed images

Abstract. Edge extraction from high spatial resolution (HSR) remotely sensed images is one of the essential tasks for image segmentation and object identification. We present an optimal Gabor-based edge detection method which mainly focuses on selecting optimal parameters, including central frequency and spectrum scale, for Gabor filter. The central frequency is automatically optimized by phase randomization and the human visual system-based structure similarity index. Next, the optimal spectrum scale is determined based on two-dimensional power spectrum density. The edge detection method is comprehensively discussed in the analysis of parameter sensitivity, overall performance, and comparative tests with several widely used methods. Qualitative and quantitative experimental studies, performed on six test images with various spatial resolution, show that the proposed method provides a promising solution to edge detection from HSR remotely sensed images.

[1]  Javier Martinez-Baena,et al.  A multi-channel autofocusing scheme for gray-level shape scale detection , 1997, Pattern Recognit..

[2]  Miguel García-Silvente,et al.  The novel scale-spectrum space for representing gray-level shape , 1997, Pattern Recognit..

[3]  Mark D. Fairchild,et al.  On Contrast Sensitivity in an Image Difference Model , 2002, PICS.

[4]  Min Zhang,et al.  Scale parameter selection by spatial statistics for GeOBIA: Using mean-shift based multi-scale segmentation as an example , 2015 .

[5]  Miguel García-Silvente,et al.  A multi-channel-based approach for extracting significant scales on gray-level images , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[6]  Viktor Vegh,et al.  Modified human contrast sensitivity function based phase mask for susceptibility-weighted imaging , 2014, NeuroImage: Clinical.

[7]  Lester C. Loschky,et al.  The importance of information localization in scene gist recognition. , 2007, Journal of experimental psychology. Human perception and performance.

[8]  Xue Yang,et al.  An Extreme Learning Machine based on Cellular Automata of edge detection for remote sensing images , 2016, Neurocomputing.

[9]  Dennis F. Dunn,et al.  Optimal Gabor filters for texture segmentation , 1995, IEEE Trans. Image Process..

[10]  Pedro M. Q. Aguiar,et al.  Optimized filters for efficient multi-texture discrimination , 2013, Pattern Analysis and Applications.

[11]  William E. Higgins,et al.  Texture Segmentation using 2-D Gabor Elementary Functions , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Xosé R. Fernández-Vidal,et al.  The Selection of Natural Scales in 2D Images Using Adaptive Gabor Filtering , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Ke Wang,et al.  Image feature detection from phase congruency based on two-dimensional Hilbert transform , 2011, Pattern Recognit. Lett..

[14]  Felice Andrea Pellegrino,et al.  Edge detection revisited , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[15]  Mahmod Reza Sahebi,et al.  Edge detection based on the Shannon Entropy by piecewise thresholding on remote sensing images , 2015, IET Comput. Vis..

[16]  Gang Sun,et al.  Gabor filter-based edge detection: A note , 2014 .

[17]  D. Pelli,et al.  The role of spatial frequency channels in letter identification , 2002, Vision Research.

[18]  Bedrich J. Hosticka,et al.  Unsupervised texture segmentation of images using tuned matched Gabor filters , 1995, IEEE Trans. Image Process..

[19]  Francesc S. Beltran,et al.  Face perception: An integrative review of the role of spatial frequencies , 2006, Psychological research.

[20]  Zengzhou Hao,et al.  Edge-Guided Image Object Detection in Multiscale Segmentation for High-Resolution Remotely Sensed Imagery , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Kin-Man Lam,et al.  Efficient Edge Detection Using Simplified Gabor Wavelets , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[22]  Duan Juan.  Image Quality Assessment Based on Structural Information Extraction , 2008 .

[23]  Yao Zhao,et al.  Scale multiplication in odd Gabor transform domain for edge detection , 2007, J. Vis. Commun. Image Represent..

[24]  R. Näsänen,et al.  Utilisation of spatial frequency information in face search , 2003, Vision Research.

[25]  Benoit Tremblais,et al.  A fast multi-scale edge detection algorithm , 2004, Pattern Recognit. Lett..

[26]  Jian Yang,et al.  Improved Multiscale Edge Detection Method for Polarimetric SAR Images , 2016, IEEE Geoscience and Remote Sensing Letters.

[27]  Da-Zheng Feng,et al.  Edge Detector of SAR Images Using Crater-Shaped Window With Edge Compensation Strategy , 2016, IEEE Geoscience and Remote Sensing Letters.

[28]  Anil K. Jain,et al.  Unsupervised texture segmentation using Gabor filters , 1990, 1990 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings.

[29]  Du-Ming Tsai,et al.  Optimal Gabor filter design for texture segmentation using stochastic optimization , 2001, Image Vis. Comput..

[30]  Il Hong Suh,et al.  Oriented edge-selective band-pass filtering , 2014, Inf. Sci..

[31]  Rosa Rodriguez-Sánchez,et al.  Scale selection using three different representations for images , 1997, Pattern Recognit. Lett..

[32]  N. Ranganathan,et al.  Gabor filter-based edge detection , 1992, Pattern Recognit..

[33]  Moon-Cheol Kim,et al.  Fourier-Domain Analysis of Display Pixel Structure for Image Quality , 2016, Journal of Display Technology.

[34]  Tianxu Zhang,et al.  Contour detection based on contextual influences , 2007, Image Vis. Comput..

[35]  Jitendra Malik,et al.  Learning to detect natural image boundaries using local brightness, color, and texture cues , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.