Contour detection based on nonclassical receptive field inhibition
Contour detection based on nonclassical receptive field inhibition
复制标题
DOI：
10.1109/tip.2003.814250
复制
发表时间：
2003-07-01
影响因子：
10.6
通讯作者：
Westenberg, MA
中科院分区：
文献类型：
--
作者：
Grigorescu, C;Petkov, N;Westenberg, MA
我们提出了一个生物动机的计算步骤，称为非经典感受野（非CRF）抑制，更一般地说，围绕抑制或抑制，以提高机器视觉中的轮廓检测。非CRF抑制在猴的初级视皮层中的80%的方向选择性神经元中表现出，并且已被证明也影响人的视觉感知。这种机制的本质是，在某一点上的边缘检测器的响应被操作者支持区域之外的区域中的操作者的响应所抑制。我们结合联合收割机经典的边缘检测与两种类型的抑制机制，各向同性和各向异性抑制，这两种抑制机制在生物学中有对应的。对于边缘检测，我们还使用了生物动机的方法（Gabor能量算子）。由此产生的运营商强烈响应孤立的线条，边缘和轮廓，但表现出较弱的或没有响应的边缘，使部分texture.We使用自然图像与相关的地面实况等高线图评估性能的建议运营商的轮廓检测，同时抑制纹理边缘。结果表明，我们的方法提高了轮廓检测在混乱的视觉场景更有效地比经典的边缘检测器用于机器视觉（Canny边缘检测器）。因此，建议的运营商是更有用的轮廓为基础的对象识别任务，如形状比较，比传统的边缘检测器，不区分轮廓和纹理边缘。然而，传统的边缘检测算法也可以通过环绕抑制来扩展。除了机器视觉中轮廓检测的进步之外，这项研究还有助于理解生物学中的抑制机制。
We propose a biologically motivated computational step, called nonclassical receptive field (non-CRF) inhibition, more generally surround inhibition or suppression, to improve contour detection in machine vision. Non-CRF inhibition is exhibited by 80% of the orientation-selective neurons in the primary visual cortex of monkeys and has been demonstrated to influence the visual perception of man as well. The essence of this mechanism is that the response of an edge detector in a certain point is suppressed by the responses of the operator in the region outside the area of operator support. We combine classical edge detection with two types of inhibitory mechanism, isotropic and amsotropic inhibition, both of which have counterparts in biology. For edge detection, we also use a biologically motivated method (the Gabor energy operator). The resulting operator responds strongly to isolated lines, edges, and contours, but exhibits a weaker or no response to edges that make part of texture.We use natural images with associated ground truth contour maps to assess the performance of the proposed operator regarding the detection of contours while suppressing texture edges. The results show that our method enhances contour detection in cluttered visual scenes more effectively than classical edge detectors used in machine vision (Canny edge detector). Therefore, the proposed operator is more useful for contour-based object recognition tasks, such as shape comparison, than traditional edge detectors, which do not distinguish between contour and texture edges. Traditional edge detection algorithms can, however, also be extended with surround suppression. Next to the advancement of contour detection in machine vision, this study contributes to the understanding of inhibitory mechanisms in biology.