CASIA OpenIR  > 类脑智能研究中心
A Fast Contour Detection Model Inspired by Biological Mechanisms in Primary Vision System
Kang, Xiaomei1,2; Kong, Qingqun1,2; Zeng, Yi1,2,3,4; Xu, Bo1,2,3; Ceng Y(曾毅)
2018-04-30
发表期刊FRONTIERS IN COMPUTATIONAL NEUROSCIENCE
卷号12期号:12页码:28
文章类型Article
摘要Compared to computer vision systems, the human visual system is more fast and accurate. It is well accepted that V1 neurons can well encode contour information. There are plenty of computational models about contour detection based on the mechanism of the V1 neurons. Multiple-cue inhibition operator is one well-known model, which is based on the mechanism of V1 neurons' non-classical receptive fields. However, this model is time-consuming and noisy. To solve these two problems, we propose an improved model which integrates some additional other mechanisms of the primary vision system. Firstly, based on the knowledge that the salient contours only occupy a small portion of the whole image, the prior filtering is introduced to decrease the running time. Secondly, based on the physiological finding that nearby neurons often have highly correlated responses and thus include redundant information, we adopt the uniform samplings to speed up the algorithm. Thirdly, sparse coding is introduced to suppress the unwanted noises. Finally, to validate the performance, we test it on Berkeley Segmentation Data Set. The results show that the improved model can decrease running time as well as keep the accuracy of the contour detection.
其他摘要相比于计算机视觉系统,人的视觉系统更加快速和准确。神经科学的研究表明,在人的视觉系统中,V1区神经元能够很好地编码轮廓信息。基于V1区的编码机制,文献中出现了很多计算模型,其中比较公认的模型是MCI模型,它是基于V1区神经元的非经典感受野特性而提出的,但是它存在耗时长、提取的轮廓噪声多等不足。针对这些问题,本文融合初级视觉系统其他生物学机理,提出了一种快速的轮廓提取计算模型。首先,基于目标轮廓在图像中所占比例较小这一观察,我们引入了先验过滤来减少运行时间。然后,基于相邻神经元响应具有很强相关性,因此响应包含有很多冗余信息的这一生理依据,我们在模型中引入了均匀采样,以此来加速算法;其次,根据V1区神经元的响应具有稀疏性这一特点,在模型中引入了稀疏编码,抑制场景中非真实轮廓的噪声;最后,为了验证模型效果,我们将该计算模型在公开的数据集BSDS500上进行测试。实验结果表明,我们的模型一方面能够降低算法的运行时间,另一方面能够保证提取轮廓准确性。

关键词Primary Visual System Biological Mechanism Contour Detection Prior Filtering Uniform Sampling Sparse Coding
WOS标题词Science & Technology ; Life Sciences & Biomedicine
DOI10.3389/fncom.2018.00028
关键词[WOS]PRIMARY VISUAL-CORTEX ; RECEPTIVE-FIELD INHIBITION ; EDGE-DETECTION ; SUPPRESSION ; EXTRACTION ; NEURONS ; MACAQUE ; COLOR ; CUES ; V1
收录类别SCI
语种英语
项目资助者National Natural Science Foundation of China(61403375) ; CETC Joint Fund(6141B08010103)
WOS研究方向Mathematical & Computational Biology ; Neurosciences & Neurology
WOS类目Mathematical & Computational Biology ; Neurosciences
WOS记录号WOS:000431133100001
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/20915
专题类脑智能研究中心
通讯作者Ceng Y(曾毅)
作者单位1.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Beijing, Peoples R China
3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai, Peoples R China
4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
推荐引用方式
GB/T 7714
Kang, Xiaomei,Kong, Qingqun,Zeng, Yi,et al. A Fast Contour Detection Model Inspired by Biological Mechanisms in Primary Vision System[J]. FRONTIERS IN COMPUTATIONAL NEUROSCIENCE,2018,12(12):28.
APA Kang, Xiaomei,Kong, Qingqun,Zeng, Yi,Xu, Bo,&曾毅.(2018).A Fast Contour Detection Model Inspired by Biological Mechanisms in Primary Vision System.FRONTIERS IN COMPUTATIONAL NEUROSCIENCE,12(12),28.
MLA Kang, Xiaomei,et al."A Fast Contour Detection Model Inspired by Biological Mechanisms in Primary Vision System".FRONTIERS IN COMPUTATIONAL NEUROSCIENCE 12.12(2018):28.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
A Fast Contour Detec(2315KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Kang, Xiaomei]的文章
[Kong, Qingqun]的文章
[Zeng, Yi]的文章
百度学术
百度学术中相似的文章
[Kang, Xiaomei]的文章
[Kong, Qingqun]的文章
[Zeng, Yi]的文章
必应学术
必应学术中相似的文章
[Kang, Xiaomei]的文章
[Kong, Qingqun]的文章
[Zeng, Yi]的文章
相关权益政策
暂无数据
收藏/分享
文件名: A Fast Contour Detection Model Inspired by Biological Mechanisms in Primary Vision System.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。