|
|
A Hierarchical Image Edge Detection Method Based on Orientation Sensitivity of Visual Pathway with Synaptic Connections |
Laboratory of Pattern Recognition and Image Processing, Hangzhou DianZi University, Hangzhou 310018 |
|
|
Abstract The orientation sensitivity of human visual pathway plays a key role in contour perception, and this feature provides vital information for image understanding. In this paper, a new method of image edge detection based on visual direction sensitive mechanism was proposed. Using the physical structure feature of ganglion cells and LGN neurons receptive field distributing centripetal, a subcortex multidirection sensitive function layer was constructed to transform visual incentive to pulse sequence, and neural spiking information were fused to get an edge sensitive image; then a primary visual cortex function layer with removing optical direction receptive field was built to code on the spike sequence generated by the former layer according to first spike time. The edge detection result was obtained through lateral inhibition and threshold processing. In this paper, colony images with fuzzy hierarchy and rich details were taken for processing. The results of hierarchical edge detection were assessed by the confidence of edge, reconstruction similarity and weighted sum of them. It was proved that our method can completely detect image edge and effectively filter out texture noise. And the mean value of weighted sum index was 0.7468, significantly higher than other methods compared. The new method of edge detection proposed in the paper provides a new idea for the image processing and understanding based on orientation sensitivity of visual pathway.
|
|
|
|
|
[1]Maini R, Aggarwal H. Study and comparison of various image edge detection techniques [J]. International Journal of Image Processing (IJIP), 2009, 3(1): 1-11.
[2]Sadagopan S, Ferster D. Feedforward origins of response variability underlying contrast invariant orientation tuning in cat visual cortex [J]. Neuron, 2012, 74(5): 911-923.
[3]Kerr D, Coleman S, Mcginnity M, et al. Biologically inspired edge detection [C] //2011 11th International Conference on Intelligent Systems Design and Applications (ISDA). Cordoba: IEEE, 2011: 802-807.
[4]Petkov N, Subramanian E. Motion detection, noise reduction, texture suppression, and contour enhancement by spatiotemporal Gabor filters with surround inhibition [J]. Biological Cybernetics, 2007, 97(5-6): 423-439.
[5]Wei Hui, Lang Bo, Zuo Qingsong. Contour detection model with multiscale integration based on nonclassical receptive field [J]. Neurocomputing, 2013, 103(0): 247-262.
[6]Yang Kaifu, Gao Shaobing, Li Chaoyi, et al. Efficient color boundary detection with coloropponent mechanisms [C] //2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Portland: IEEE, 2013: 2810-2817.
[7]Yang Kaifu, Li Chaoyi, Li Yongjie. Multifeature based surround inhibition improves contour detection in natural images [J]. IEEE Transactions on Image Processing, 2014, 23(12): 5020-5032.
[8]罗佳骏,武薇,范影乐,等. 基于视觉感光层功能的菌落图像多强度边缘检测研究 [J]. 中国生物医学工程学报, 2014, 33(6): 677-686.
[9]廖进文,范影乐,武薇,等. 基于点阵神经元响应时空信息的菌落图像边缘检测 [J]. 航天医学与医学工程, 2014, 27(2): 94-100.
[10]Rivlin-Etzion M, Wei Wei, Feller MB. Visual stimulation reverses the directional preference of directionselective retinal ganglion cells [J]. Neuron, 2012, 76(3): 518-525.
[11]Naito T, Okamoto M, Sadakane O, et al. Effects of stimulus spatial frequency, size, and luminance contrast on orientation tuning of neurons in the dorsal lateral geniculate nucleus of cat [J]. Neuroscience Research, 2013, 77(3): 143-154.
[12]Chouhan AS. An analytical study of leaky integrate\|andfire neuron model using MATLAB simulation [J]. Int J Eng Res Technol, 2013, 2(4): 2242-2245.
[13]Venkataramani S, Taylor WR. Orientation selectivity in rabbit retinal ganglion cells is mediated by presynaptic inhibition [J]. The Journal of Neuroscience, 2010, 30(46): 15664-15676.
[14]寿天德. 视觉信息处理的脑机制 [M]. 2版. 合肥: 中国科学技术大学出版社, 2010.
[15]Zhao Xinyu, Chen Hui, Liu Xiaorong, et al. Orientationselective responses in the mouse lateral geniculate nucleus [J]. The Journal of Neuroscience, 2013, 33(31): 12751-12763.
[16]Suematsu N, Naito T, Miyoshi T, et al. Spatiotemporal receptive field structures in retinogeniculate connections of cat [J]. Frontiers in Systems Neuroscience, 2013, 7(103): 1-13.
[17]Tanabe S. Population codes in the visual cortex [J]. Neuroscience Research, 2013, 76(3): 101-105.
[18]Gollisch T, Meister M. Rapid neural coding in the retina with relative spike latencies [J]. Science, 2008, 319(5866): 1108-1111.
[19]Isaacson JS, Scanziani M. How inhibition shapes cortical activity [J]. Neuron, 2011, 72(2): 231-243.
[20]Zi Fang, Zhao Dawei, Zhang Ke. Image preprocessing algorithm based on lateral inhibition [C] // The 8th International Conference on Electronic Measurement and Instruments. Xi’an: IEEE, 2007: 2-701-2-705.
[21]Govindarajani B, Panetta KA, Agaian S. Image reconstruction for quality assessment of edge detectors [C] //IEEE International Conference on Systems, Man and Cybernetics. Singapore City: IEEE, 2008: 691-696.
[22]Wang Zhou, Bovik AC, Sheikh HR, et al. Image quality assessment: from error visibility to structural similarity [J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612.
[23]Meer P, Georgescu B. Edge detection with embedded confidence [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(12): 1351-1365.
[24]磨少清. 边缘检测及其评价方法的研究 [D]. 天津: 天津大学, 2011. |
|
|
|