Contour detection based on a non-classical receptive field model with butterfly-shaped inhibition subregions

Physiological studies show that the response of classical receptive field (CRF) to visual stimulus could be suppressed by non-classical receptive field (NCRF) inhibition of the neurons in primary visual cortex (V1) and most of CRFs and NCRFs in V1 are orientation-selective. In addition, surround inhibition is normally spatially asymmetric. Inspired by these visual mechanisms, we proposed a feasible contour detection method based on an improved orientation-selective inhibition model in this paper. A butterfly-formed surrounding area is employed for the computation of inhibition term, and only one side subregion that produces less inhibition contributes to cell's response, which could provide a flexible inhibitory effect for the NCRF modulation on CRF. Comparisons with other visual contour detection models show that the proposed model can suppress texture effectively while retaining contours as much as possible.     

空间统一调制模型的轮廓检测

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。     

轮廓编组综述

轮廓编组是中层视觉处理的一项重要内容。轮廓编组的目的是从前阶段视觉处理中提取的低层边缘特征中找出符合人类视觉感知的显著性轮廓,这些显著性轮廓往往对应着场景中的目标轮廓。在轮廓编组中,格式塔规则对编组模型的建立有重要的指导作用。讨论了从20世纪90年代到现在的轮廓编组研究中的主要算法,将这些算法进行了分类,阐述了各个算法的提出动机及基本原理;最后,对轮廓编组研究的发展方向进行了展望。     

引入视通路视觉响应与融合模型的轮廓检测

目的 为了提高轮廓检测的综合性能,特别是增强弱轮廓边缘的提取能力,在结合视觉机制的基础上提出了本文方法。方法 模拟视觉信息在视通路中的传递和处理过程,首先根据神经节细胞的中心周边拮抗机制,实现初级轮廓信息的快速提取;接着利用高斯函数与高斯差函数之间的差异性来模拟外膝体非经典感受野的调制作用,实现纹理背景的抑制;然后构建了一种V1区多朝向简单细胞感受野模型,提出了一种基于负值效应的DOG（difference of Gaussians）响应改进评价模式;最后考虑V1区复杂细胞在表征视觉高级特征的能力,给出了一种基于并行处理的视通路视觉响应融合模型,实现目标轮廓的检测与增强。结果 为了验证本文方法对自然场景图像的轮廓检测具备有效性,本文选取RuG轮廓检测数据库中的40幅自然场景图进行轮廓检测实验,并与二维高斯导函数模型（DG）、组合感受野模型（CORF）和空间稀疏约束纹理抑制模型（SSC）等3种典型的自然图像轮廓检测方法进行了分析比较。结果表明,本文方法检测提取到的主体轮廓更加完整,具有较高的图像纯净度,整体上反映了本文所提轮廓检测方法所具备的生物智能性。本文方法的平均P指标为0.45,相较于对比方法具有更好的轮廓检测性能。结论 本文方法具有较好的自然轮廓检测提取能力,尤其对于图像包含部分弱轮廓边缘的检测。本文构建的新模型将有助于对视通路中各层级功能和内在机制的理解,也将为基于视觉机制的图像分析和理解提供一种新的思路。     

基于主视通路结构分级响应模型的轮廓检测方法EI北大核心CSCD

基于视通路结构分级响应与动态传递的方式,本文提出了一种图像轮廓检测的新方法.针对视网膜感光细胞的暗视觉特性,建立亮度自适应的暗视野调节模型,利用多尺度经典感受野的方位选择性,构建高级轮廓与全局轮廓的检测路径;模拟外侧膝状体(Lateral geniculate nucleus,LGN)细胞特性对信息进行纹理稀疏编码,并结合非经典感受野的侧抑制作用抑制背景强纹理;另外在LGN区提出微动整合机制,减少纹理冗余信息,再经适应性突触实现信息关联传递;最后将初级轮廓响应跨视区前馈至V1区并经全局轮廓修正后,与高级轮廓响应实现快速融合.分别以RuG40、BSDS500图像库中的自然图像作为实验数据,检测结果与基准轮廓图的平均最优P指标分别为0.50、0.32,结果表明本方法能更有效地区分轮廓与纹理边缘,凸显主体轮廓.本文利用视神经细胞的内在机制以及神经信息的动态传递过程实现图像轮廓信息的编码与检测,也为研究后续高级视皮层的视觉感知提供了新思路.     

基于时空脉冲编码的图像主体轮廓提取方法

图像主体轮廓包含图像非常重要的信息, 精准有效地提取图像主体轮廓不仅能减少信息冗余, 而且能降低后续图像分析和处理的时间复杂度. 本文基于视觉神经元信息处理机理, 提出了一种基于时空脉冲编码的图像主体轮廓提取方法. 首先, 利用Gabor函数模拟神经节细胞感受野对图像进行多尺度多方向的信息提取; 其次, 模拟视网膜非经...     

引入低对比度环境下视觉感知机制的轮廓检测模型

传统的基于视觉感知机制的轮廓检测模型在遇到边缘局部对比度低时会出现部分目标轮廓丢失现象,并且在去抑制区共线增强时会使得噪声增强或高曲率轮廓拐角处断裂。针对这些问题,提出一种引入低对比度环境下视觉感知机制的轮廓检测模型。在传统轮廓检测模型的基础上一方面引入刺激物对比度对感受野大小及侧抑制强度的调节机制;另一方面根据Gestalt知觉组织原则将去抑制区划分为邻接去抑制区和外周去抑制区,分别给予不同的增强机制。并结合数学形态学滤波方法对得到的轮廓进行噪声滤波处理。针对自然图像进行实验,结果表明本模型在解决上述问题上有显著效果,提高自然背景中轮廓提取的性能。     

基于周边抑制机理的遥感图像背景纹理抑制方法

针对遥感图像中主要目标周围的纹理信息对目标识别造成的干扰,提出了基于周边抑制机理的背景纹理抑制方法。通过在边缘提取的基础上增加周边抑制模块,实现了对纹理边缘和轮廓边缘的分别处理,有效地抑制了纹理、保留了轮廓。以周边抑制机理为基础,结合多尺度处理技术,进一步提高了背景纹理抑制的效果。实验结果表明,本方法可以有效抑制背景纹理,为识别有较多背景纹理的遥感图像地物目标创造良好条件。     

Visual segmentation by contextual influences via intra-cortical interactions in the primary visual cortex.

Stimuli outside classical receptive fields have been shown to exert a significant influence over the activities of neurons in the primary visual cortex. We propose that contextual influences are used for pre-attentive visual segmentation. The difference between contextual influences near and far from region boundaries makes neural activities near region boundaries higher than elsewhere, making boundaries more salient for perceptual pop-out. The cortex thus computes global region boundaries by detecting the breakdown of homogeneity or translation invariance in the input, using local intra-cortical interactions mediated by the horizontal connections. This proposal is implemented in a biologically based model of V1, and demonstrated using examples of texture segmentation and figure-ground segregation. The model is also the first that performs texture or region segmentation in exactly the same neural circuit that solves the dual problem of the enhancement of contours, as is suggested by experimental observations. The computational framework in this model is simpler than previous approaches, making it implementable by V1 mechanisms, though higher-level visual mechanisms are needed to refine its output. However, it easily handles a class of segmentation problems that are known to be tricky. Its behaviour is compared with psycho-physical and physiological data on segmentation, contour enhancement, contextual influences and other phenomena such as asymmetry in visual search.     

多水平外区抑制的轮廓检测

提取自然图像中的物体轮廓是机器视觉研究的重要问题,主要困难在于自然图像中的纹理性边缘严重干扰了物体轮廓的提取。研究表明视皮层方位选择性神经元的非经典感受野机制使得人类视觉系统在处理自然图像时不仅能够抑制纹理性边缘,而且能够增强物体的轮廓。基于此人们提出多种仿生轮廓检测算法,但算法中被称为抑制水平的参量在取值较高时会漏检部分轮廓,而在其取值较低时又会引入过多的纹理性边缘。针对这一问题,提出多水平外区抑制轮廓检测算法,通过整合各级单水平外区抑制的检测信息,有效抑制了纹理性边缘和降低了漏检轮廓的可能性。实验结果表明,相对于传统算法,新算法在轮廓检测性能上提高了10%左右,并具有更好的稳健性。     

Feedback and Surround Modulated Boundary Detection

Edges are key components of any visual scene to the extent that we can recognise objects merely by their silhouettes. The human visual system captures edge information through neurons in the visual cortex that are sensitive to both intensity discontinuities and particular orientations. The “classical approach” assumes that these cells are only responsive to the stimulus present within their receptive fields, however, recent studies demonstrate that surrounding regions and inter-areal feedback connections influence their responses significantly. In this work we propose a biologically-inspired edge detection model in which orientation selective neurons are represented through the first derivative of a Gaussian function resembling double-opponent cells in the primary visual cortex (V1). In our model we account for four kinds of receptive field surround, i.e. full, far, iso- and orthogonal-orientation, whose contributions are contrast-dependant. The output signal from V1 is pooled in its perpendicular direction by larger V2 neurons employing a contrast-variant centre-surround kernel. We further introduce a feedback connection from higher-level visual areas to the lower ones. The results of our model on three benchmark datasets show a big improvement compared to the current non-learning and biologically-inspired state-of-the-art algorithms while being competitive to the learning-based methods.     

A model of the response of visual area V2 to combinations of orientations

The role of the V2 area in visual processing is still almost entirely unexplored. Recently, several studies revealed the tuning of V2 neurons in the macaque to stimuli consisting of two segments with different orientations. By measuring orientation tuning inside subunits of the overall receptive field, units with non uniform orientation selectivity have been found. In this work, the emergence of a computational organization supporting similar responses is explored, using an artificial model of cortical maps. This model, called LISSOM (Laterally Interconnected Synergetically Self-Organizing Map) includes excitatory and inhibitory lateral connections. In this simulation two LISSOM maps are arranged as V1 and V2 areas. In the first area, the classical domains of orientation selectivity develop, while in V2 most neurons become sensitive to pairs of orientations. The overall activation of these units depend on the presence of oriented segments at a finer grain than the whole receptive fields, with complex nonlinear interactions.     

引入初级视通路计算模型的轮廓检测

目的 轮廓是对图像目标的一种稀疏表达方式，从图像中提取出有效物体轮廓可以更好地完成后续的视觉认知任务，所以轮廓检测在计算机视觉领域具有较好的应用。本文考虑到初级视通路中视觉信息传递和处理流程中的特点，提出了一种基于初级视通路计算模型的轮廓检测方法。方法 在视网膜神经节环节，提出一种体现方向选择特性的经典感受野（CRF）改进模型，利用多尺度特征融合策略来模拟视网膜神经节细胞对图像目标的初级轮廓响应；在视网膜神经节到神经节-外膝体（LGN）的视通路中，提出一种反映视觉信息时空尺度特征的时空编码机制，模拟神经节-外膝体通路对初级轮廓响应的去冗余处理；利用非下采样轮廓波变换和Gabor变换协同作用，模拟非经典感受野（NCRF）的侧向抑制特性。最后利用初级视皮层对整体轮廓的前馈机制，实现对轮廓局部细节信息的完整性融合。结果 选择将RuG40图库的所有图像作为测试集合进行模型性能测试，对检测结果进行非极大值抑制和阈值处理，最终将得到的二值轮廓图与基准图比较，整个数据集和单张图的最优平均P指标分别为0.49和0.56。对于单个图像最优参数条件下的检测结果均值，将本文方法与非经典感受野抑制模型（ISO）和多特征外周抑制模型（MCI）比较，较两者分别提高了19.1%和7.7%。结果表明本文方法能有效突出主体轮廓并抑制纹理背景。结论 面向图像处理应用的初级视通路计算模型，将为后续图像理解和分析提供一种新的思路。     

近距大偏角圆形目标的检测

圆形目标距离图像采集设备较近且存在较大偏转角时成像会产生严重的形变,给目标图像的自动检测带来了困难。提出了一种近距大偏角圆形目标的检测算法,利用闭运算处理,去除图像背景中的噪声,并采用嵌套双层轮廓提取方法实现目标轮廓提取,通过轮廓特征提取算法获得目标轮廓的初选轮廓,利用初选轮廓的细节特征信息确认目标轮廓。为了实现目标的高效检测,采用模板匹配算法进一步提高了算法运行效率以及稳定性。实验结果表明,所提出的检测算法可以有效地适应不同的背景环境,具有较强的鲁棒性和实时性。     

基于生物视觉特征的目标轮廓提取算法

自然场景中的目标轮廓提取是计算机视觉中的一个重要研究问题。其难点在于场景中大量的纹理边缘严重地干扰了轮廓提取的完整性。近年来,一些研究工作将生物视觉特征引入图像边缘轮廓提取,取得了一定的效果。其中通过引入视觉外区抑制特征可以在提取物体轮廓边缘的同时抑制一定量的纹理边缘,从而得到轮廓边缘集合。然而在整合轮廓边缘时,传统模型仅仅采用求交并集的简单合并方法,使得强响应的细小纹理残留。基于此,提出了一种改进的基于生物视觉特征的自然场景目标轮廓提取算法。首先采用多水平抑制方法得到候选轮廓边缘集合。接着将一种基于生物视觉特征的边缘组合方法用于将候选边缘整合成为一个完整的目标轮廓。与传统的外区抑制算法相比,基于视觉特征的轮廓提取算法提高了自然场景中目标轮廓提取的准确性和完整性。     

自然图像中目标轮廓上显著边缘检测的计算模型

如何模拟人类视觉感知系统的感知过程,建立一个鲁棒性较好、无监督的自然图像中目标轮廓上显著边缘检测的计算模型是文中要讨论的问题。首先确定自然图像中目标所在的子区域。然后通过分析纹理以及颜色等低级视觉特征得到一组潜在的轮廓边缘,对这些潜在的轮廓边缘进行闭合性分析,建立各条潜在边缘之间闭合关系的图模型。最后通过最短路径找出最优的轮廓上的显著边缘。将该模型用于多幅自然图像,实验效果较好。该模型在生物学上的合理性也得到验证。     

一种仿生物视觉感知的视频轮廓检测方法

消除背景的局部边缘干扰同时保证目标的完整轮廓是视频轮廓检测的一个难点, 基于运动感知的生物视觉证据, 提出一种运动能量抑制模型, 有效抑制背景边缘, 激励目标的强边缘. 通过归一化整理视频运动切片的四方向运动能量抑制响应, 反映V1 层视觉神经元的周围抑制感知特性, 进而采用"双半圆盘"算子提取边缘梯度响应, 同时, 结合运动和外观线索, 用随机森林对边缘梯度响应的 局部结构进行树划分, 得到最终的检测结果. 实验表明, 本文提出的方法较已有的视频轮廓检测方法有更 优的量化查全-查准率曲线、F-measure值和AP值以及更好的视觉轮廓感官效果.     

Extracting eyebrow contour and chin contour for face recognition

This paper proposes a novel method for extraction of eyebrow contour and chin contour. We first segment rough eyebrow regions using spatial constrained sub-area K-means clustering. Then eyebrow contours are extracted by Snake method with effective image force. For chin contour extraction, we first estimate several possible chin locations which are used to build a number of curves as chin contour candidates. Based on the chin like edges extracted by proposed chin edge detector, the curve with the largest likeliness to be the actual chin contour is selected. Finally, the credible extracted eyebrow contour and the estimated chin contours are used as geometric features for face recognition. Experimental results show that the proposed algorithms can extract eyebrow contours and chin contours with good accuracy and the extracted features are effective for improving face recognition rates.     

A Holistic Approach for Efficient Contour Detection

Object contours contain important visual information which can be applied to numerous vision tasks. As recent algorithms focus on the accuracy of contour detection, the entailed time complexity is significantly high. In this paper, we propose an efficient and effective contour extraction method based on both local cues from pixels and global cues from saliency. Experimental results demonstrate that a good trade-off between accuracy and speed can be achieved by the proposed approach for contour detection.