空间统一调制模型的轮廓检测

Contour detection based on spatially unified modulation model

目的在人类大脑初级视皮层上,神经元不仅受到位于经典感受野中刺激的影响,同样也受到周边环境相应非经典感受野中刺激的影响。这种上下文的调制是通过视皮层的水平连接来实现的。基于初级视皮层的视觉机制,本文提出了一个轮廓提取模型。方法首先利用局部能量计算初级视皮层上单个神经元的响应;然后通过构建一个新颖的空间统一调制算子获得周边刺激对于中央神经元的增强和抑制影响(上下文调制);最后整合上下文调制影响和中央神经元本身的能量响应,获得完整输出。结果本文所提模型,无需在非经典感受野中划分增强域和抑制域,同时能够有效抑制背景纹理,突出目标轮廓,保留交点和角点信息。结论通过对合成图像和自然图像的测试表明了本文算法的准确性和优越性,能够极大地提高复杂背景中轮廓检测的性能。

Objective The response of the central neuron in the primary visual cortex （ V1 ） is not only affected by the stim- ulus inside the classical receptive field but also modulated by the surrounding stimulus （NCRF）. Contextual modulation is mediated by horizontal connections across the visual cortex. This study proposes a contour detection method based on the visual mechanism in V1. Method First, the response of every visual neuron in V1 is computed by local energy. Second, facilitation and suppression （contextual influence） on a neuron through horizontal interactions are obtained by constructing a spatially unified modulating function. Finally, the total output response of one neuron to complex visual stimuli is ac- quired by combining the influence of local visual context on the neuron and energy response. Result Unlike previous stud- ies, the present work unified the facilitation and suppression modulated by surrounding elements in the image without sepa- rating the regions of excitatory and inhibitory lateral connections. Conclusion The proposed method was tested on synthetic and natural images; encouraging results were obtained. The proposed model is expected to improve contour detection per- formance when images contain objects of interest on a cluttered background.