期刊文献+

基于突触连接视通路方位敏感的图像分级边缘检测方法 被引量:4

A Hierarchical Image Edge Detection Method Based on Orientation Sensitivity of Visual Pathway with Synaptic Connections
下载PDF
导出
摘要 视觉通路上的多级方位敏感特性对于视觉轮廓感知起着关键作用,将为更高层次的视皮层图像理解提供重要的特征信息。从视觉方位敏感机制出发,提出一种图像边缘检测的新方法。利用神经节细胞以及外膝体神经元感受野向心分布的生理结构特性,构建具有突触连接和多方向敏感特性的视皮层下功能层,融合多方向上的神经元脉冲发放信息,将视觉激励映射为边缘敏感图像;构建具有去最优方位感受野特性的初级视皮层的功能层,对前级结构生成的脉冲序列按时间信息进行神经编码,经过感受野内侧向抑制和阈值处理,获得边缘检测结果。对层次模糊而细节丰富的菌落图像进行处理,并以边缘置信度和重构相似度以及两者的加权和作为边缘检测评价指标。结果表明,该方法在完整检测图像边缘的同时,并不引入纹理噪声,有着明显的优势,其对12幅图像的加权和指标均值为0.746 8,显著高于其他对比方法。所提出的方法可以模拟视通路中初级视皮层及视皮层下的方向敏感特性,提供一种基于视觉机制的图像处理和理解新思路。 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 sub-cortex multi-direction 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.
出处 《中国生物医学工程学报》 CAS CSCD 北大核心 2015年第5期522-532,共11页 Chinese Journal of Biomedical Engineering
基金 国家自然科学基金(60872090) 浙江省大学生科技创新活动计划项目(2014R407013)
关键词 边缘检测 视通路 突触连接 方位敏感 侧向抑制 edge detection visual pathway synaptic connections orientation sensitivity lateral inhibition
  • 相关文献

参考文献24

  • 1Maini R, Aggarwal H. Study and comparison of various imageedge detection techniques [ J ]. International Journal of ImageProcessing ( IJIP),2009,3(1): 1 -11. 被引量:1
  • 2Sadagopan S, Ferster D. Feedforward origins of responsevariability underlying contrast invariant orientation tuning in catvisual cortex [ J]. Neuron, 2012,74(5 ) : 911 -923. 被引量:1
  • 3Kerr D, Coleman S, Mcginnity M, et al. Biologically inspirededge detection [ C ] //2011 11th International Conference onIntelligent Systems Design and Applications (ISDA). Cordoba:IEEE,2011: 802 -807. 被引量:1
  • 4Petkov N, Subramanian E. Motion detection, noise reduction,texture suppression,and contour enhancement by spatiotemporalGabor filters with surround inhibition [ J ]. BiologicalCybernetics, 2007,97(5 -6) : 423 -439. 被引量:1
  • 5Wei Hui,Lang Bo, Zuo Qingsong. Contour detection model withmulti-scale integration based on non-classical receptive field [ J].Neurocomputing,2013 , 103(0) : 247 - 262. 被引量:1
  • 6Yang Kaifu, Gao Shaobing, Li Chaoyi, et al. Efficient colorboundary detection with color-opponent mechanisms [ C ] //20131EEE Conference on Computer Vision and Pattern Recognition(CVPR). Portland: IEEE, 2013: 2810 -2817. 被引量:1
  • 7Yang Kaifu, Li Chaoyi, Li Yongjie. Multi-feature based surroundinhibition improves contour detection in natural images [J].IEEE Transactions on Image Processing, 2014,23( 12) : 5020 -5032. 被引量:1
  • 8罗佳骏,武薇,范影乐,高云园.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,2014,31(6):677-686. 被引量:3
  • 9廖进文,范影乐,武薇,高云园,李轶.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. 被引量:3
  • 10Rivlin - Etzion M, Wei Wei, Feller MB. Visual stimulationreverses the directional preference of direction-selective retinalganglion cells [J]. Neuron, 2012,76(3) : 518 -525. 被引量:1

二级参考文献36

  • 1Maini R, Aggarwal H. Study edge detection techniques[ J] and comparison of various image International Journal of Image Processing (HIP), 2009, 3(1): 1-11. 被引量:1
  • 2Juneja M, Sandhu PS. Performance evaluation of edge detec- tion techniques for images in spatial domain [ J ]. methodolo- gy, 2009, 1(5) : 614-621. 被引量:1
  • 3Rokem A,Silver MA. A model of encoding and decoding in V1 and MT accounts for motion perception anisotropies in the human visual system[J]. Brain research, 2009, 1299: 3-16. 被引量:1
  • 4Raudies F, Neumann H. A model of neural mechanisms in monocular transparent motion perception[J]. Journal of Phys- iology-Paris, 2010, 104(1 ): 71-83. 被引量:1
  • 5Webb BS,Ledgeway T, McGraw PV. Relating spatial and temporal orientation pooling to population decoding solutions in human vision[ J]. Vision research, 2010, 50(22) : 2274- 2283. 被引量:1
  • 6Basttirk A, Gtlnay E Efficient edge detection in digital images using a cellular neural network optimized by differential evolu- tion algorithm[ J ]. Expert Systems with Applications, 2009, 36(2) : 2645-2650. 被引量:1
  • 7Waldemark K, Lindblad T, Beranovi6 V, et al. Patterns fromthe sky: satellite image analysis using pulse coupled neural networks for pre-processing, segmentation and edge detection [ J ]. Pattern recognition letters, 2000, 21 (3) : 227-237. 被引量:1
  • 8Liu B, Li P. Li Y, et al. Visual receptive fielc1 structure of cortical inhibitory neurons revealed by two-photon imaging guided recording[J]. The Journal of Neuroscicnce, 2009, 29 (34) : 10520-10532. 被引量:1
  • 9Sadagopan S, Ferster D. Feedforward origins of response vari- ability underlying contrast invariant orientation tuning in cat visual cortex[J]. Neuron, 2012, 74(5): 911-923. 被引量:1
  • 10Avila-Akerberg O, Chacrun MJ. Nonrenewal spike train sta- tistics: causes and functional consequences on neural coding [J]. Experimental brain research, 2011, 210(3-4): 353- 371. 被引量:1

共引文献4

同被引文献8

引证文献4

二级引证文献6

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部