| 19 | 0 | 18 |
| 下载次数 | 被引频次 | 阅读次数 |
目的 基于初级视觉皮层非经典感受野亚区外周抑制特性机理，提出一种新型轮廓检测方法。方法 模拟初级视皮层经典感受野受到外部刺激的响应特性，构建多方位二维Gabor滤波器模型，实现初级轮廓的提取。之后基于初级皮层非经典感受野亚区的结构特性，提出非经典感受野亚区侧抑制模型，实现纹理抑制。对于视觉信息传递的前馈机制，采用二维Gaussian函数模拟神经节细胞对信息的处理，信息跨层级传递，提高响应速率。模拟人眼捕捉全局信息的特性，进行轮廓修正，最终得到轮廓图。结果 针对RUG40图像库的测试，与其他轮廓检测算法进行定性和定量分析比较；BSDS500中任意200张图像的平均准确度（AP）达0.703。结论 新型轮廓检测方法能更有效突显主体轮廓并且抑制纹理背景。
Abstract：Objective This paper proposes a novel contour detection method inspired by the surround inhibition mechanism of the primary visual cortex. Methods The method involves simulating the response characteristics of the classical receptive field in the primary visual cortex to external stimuli and constructing a multi-directional two-dimensional Gabor filter model for extracting primary contours. A non-classical receptive subfield surround suppression model is proposed based on the structural characteristics of the non-classical receptive subfield for texture suppression. Additionally,a two-dimensional Gaussian function is used to simulate information processing by ganglion cells, and information is transmitted across levels to improve the response rate. Finally, the characteristics of capturing global information by the human eye are simulated to correct the contours and obtain the final contour map. Results Qualitative and quantitative analysis compared with other existing contour detection algorithms; The average accuracy(AP) of any 200 images in the BSDS500 reached 0.703. Conclusion the results show that the proposed algorithm can more effectively highlight the contour of the subject and suppress the texture background.
[1] Zhong H, Wang R. A visual-degradation-inspired model with HSV color-encoding for contour detection[J]. Journal of Neuroscience Methods, 2022, 369:109423.
[2] Fang T, Fan Y, Wu W. Salient contour detection on the basis of the mechanism of bilateral asymmetric receptive fields[J]. Signal, Image and Video Processing, 2020, 14:1461-1469.
[3] Lin C, Zhang Q, Cao Y. Multi-scale contour detection model based on fixational eye movement mechanism[J]. Signal, Image and Video Processing, 2020, 14:57-65.
[4]李健，范影乐.基于信息流多级结构响应的轮廓检测模型[J].传感技术学报，2024,37(2):288-296.
[5] Chen Z, Cai R. Contour detection by simulating the curvature cell in the visual cortex and its application to object classification[J]. IEEE Access, 2020, 8:74472-74484.
[6] Zhang Q, Lin C, Li F. Application of binocular disparity and receptive field dynamics:A biologically-inspired model for contour detection[J]. Pattern Recognition, 2021, 110:107657.
[7]武薇，韩显修，范影乐.基于双视通路交互感知的轮廓检测方法[J].电子与信息学报，2022,44(7):2512-2521.
[8]杨鑫，朱恒亮，毛国君.双特征流融合和边界感知的显著性目标检测[J].计算机工程与应用，2024,60(10):227-236.
[9]张贞光.基于视觉通路生理机制的轮廓检测模型[D].柳州：广西科技大学，2023.
[10] Wei M, Chaofan G, Shibiao X, et al. Top-down guided fusion network for object contour detection[J]. Journal of Computer-Aided Design&Computer Graphics, 2021, 33(6):855-863.
[11]杨谦，齐翔林，汪云九.简单细胞方位选择性感受野组织形成的神经网络模型[J].中国科学：C辑，2000,30(4):412-420.
[12] Hubel DH, Wiesel TN. Receptive fields of single neurones in the cat's striate cortex[J]. The Journal of Physiology, 1959, 148(3):574.
[13] Jones HE, Grieve KL, Wang W, et al. Surround suppression in primate V1[J]. Journal of Neurophysiology, 2001, 86(4):2011-2028.
[14] Gilbert C D, Li W. Top-down influences on visual processing[J]. Nature Reviews Neuroscience, 2013, 14(5):350-363.
[15]张明琦，范影乐，武薇.基于初级视通路视觉感知机制的轮廓检测方法[J].自动化学报，2020,46(2):264-273.
[16]杨开富.前端视觉通路信息加工的计算模型及应用研究[D].成都：电子科技大学，2016.
[17] Pingping C, Zhefei C, Yingle F, et al. Image contour detection based on visual pathway information transfer mechanism[J]. Neural Processing Letters,2024,56(1):825-829.
[18]杜仕荣，范影乐，蔡哲飞，等.结合双视通路与尺度信息融合的轮廓检测方法[J].中国图象图形学报，2024.
[19] Lin C, Wen Z Q, Xu G L, et al. A bio-inspired contour detection model using multiple cues inhibition in primary visual cortex[J].Multimedia Tools and Applications, 2022, 81(8):11027-11048.
[20] Elharrouss O, Hmamouche Y, Idrissi A K, et al. Refined edge detection with cascaded and high-resolution convolutional network[J].Pattern Recognition, 2023, 138:109361.
基本信息:
DOI：10.16289/j.cnki.1002-0837.2025.01011
中图分类号:TP391.41
引用信息:
[1]章敬艳,范影乐,房涛.基于非经典感受野亚区的轮廓检测方法[J].航天医学与医学工程,2025,36(01):65-68+74.DOI:10.16289/j.cnki.1002-0837.2025.01011.
基金信息: