基于复合感受野的轮廓检测算法

杜晓凤; 李翠华; 李晶

doi:10.3724/SP.J.1146.2008.01164

基于复合感受野的轮廓检测算法

doi: 10.3724/SP.J.1146.2008.01164

杜晓凤^{①;李翠华},
李翠华,
李晶

基金项目:

国家973计划项目(2007CB311005)，国家863计划项目(2006AA01Z129)，福建省自然科学基金(A0710020)和厦门大学985二期信息创新平台项目资助课题

计量
- 文章访问数: 3200
- HTML全文浏览量: 110
- PDF下载量: 1254
- 被引次数: 0
出版历程
- 收稿日期: 2008-09-16
- 修回日期: 2009-03-12
- 刊出日期: 2009-07-19

Contour Detection Based on Compound Receptive Field

Du Xiao-feng^{①;李翠华},
Li Cui-hua,
Li Jing

摘要

摘要: 自然场景自动检测目标轮廓是非常困难的。该文提出了一种基于复合感受野的图像轮廓检测仿生模型。在传统的基于抑制模型的基础上引入去抑制机制，在减少背景纹理干扰的同时，保护较弱的轮廓，从而尽量保持轮廓的完整性。实验结果表明，这种仿生模型可以有效地抑制纹理边缘，减少对轮廓的破坏，提高了自然背景中轮廓检测的性能。
- 目标识别;轮廓检测;初级视皮层;复合感受野
Abstract: Contour detection from natural scenes is a tough task in computer vision. This paper proposes a visual model of contour detection based on compound receptive field. By inducing dis-inhibition mechanism to traditional model that was based on inhibition mechanism, inferences are suppressed while weak edges are preserved, so that the integrity of contour is improved. Experiment results show that this approach can suppress edges due to texture, protect object contour and improve the performance of contour detection from nature scene.

HTML全文

参考文献(1)

Grigorescu C, Petkov N, and Westenberg M A. Contourdetection based on nonclassical receptive field inhibition [J].IEEE Transactions on Image Processing.2003, 12(7):729-739[2]Grigorescu C, Petkov N, and Westenberg M A. Contour andboundary detection improved by surround suppression oftexture edges [J].Image and Vision Computing.2004, 22(8):609-622[3]Papari G, Campisi P, Petkov N, and Neri A. A biologicallymotivated multiresolution approach to contour detection [J].EURASIP Journal on Advances in Signal Processing, 2007,1(Article ID 71828): 119.[4]Ursino M and La Cara G E. A model of contextualinteractions and contour detection in primary visual cortex[J].Neural Networks Archive.2004, 17(5-6):719-735[5]La Cara G E and Ursino M. A model of contour extractionincluding multiple scales, flexible inhibition and attention [J].Neural Networks.2008, 21(5):759-773[6]桑农, 唐奇伶, 张天序. 基于初级视皮层抑制的轮廓检测方法[J]. 红外与毫米波学报, 2007, 26(1): 47-51.Sang Nong, Tang Qi-ling, and Zhang Tian-xu. Contourdetection based on inhibition of primary visual cortex [J].Journal of Infrared and Millimeter Waves, 2007, 26(1): 47-51.[7]寿天德, 周逸峰. 视觉系统皮层下细胞的方位和方向敏感性[J]. 生物物理学报, 1996, 48(2): 105-112.Shou Tian-de and Zhou Yi-feng. Orientation and directionsensitivity of cells in subcortical structures of the visualsystem [J]. Acta Physiologica Sinica, 1996, 48(2): 105-112.[8]操安, 周逸峰, 寿天德. 视皮层细胞方位选择性研究的新进展[J]. 生理科学进展, 1998, 29(1): 71-73.Cao An, Zhou Yi-feng, and Shou Tian-de. A new progress oforientation sensitivity of cells in visual cortical [J]. Progressin Physiological Sciences, 1998, 29(1): 71-73.[9]邱志诚, 黎臧, 顾凡及等. 视网膜神经节细胞感受野的一种新模型II [J]. 生物物理学报, 2000, 16(2): 296-302.Qiu Zhi-cheng, Li Zang, and Gu Fan-ji, et al.. A newcomputational model of retinal ganglion cell receptive fieldsII[J]. Acta Biophysica Sinica, 2000, 16(2): 296-302.[10]Cai Chao-feng, Liang Pei-ji, and Zhang Pu-ming. Asimulation study on the encoding mechanism of retinalganglion cell [J].Lecture Notes in Computer Science.2007,4689:470-479[11]Kapadia M K, Westheimer G, and Gilbert C D. Spatialdistribution of contextual interactions in primary visualcortex and in visual perception [J]. Neurophysiol, 2000, 84(4):2048-2062.

施引文献

资源附件(0)

访问统计