仿视皮层V1结构的纹理特征提取

doi:10.3969/j.issn.1001-2400.2017.03.017

西安电子科技大学学报

仿视皮层V1结构的纹理特征提取

邹洪中;许悦雷;马时平;李帅;张文达

(空军工程大学航空航天工程学院，陕西西安 710038)

收稿日期:2016-06-29 出版日期:2017-06-20 发布日期:2017-07-17
作者简介:邹洪中(1992-)，男，空军工程大学硕士研究生，E-mail: hongzhongz@126.com
基金资助:
国家自然科学基金资助项目(61372167, 61379104)

Texture feature extraction simulating the structure of V1 in the cortex

ZOU Hongzhong;XU Yuelei;MA Shiping;LI Shuai;ZHANG Wenda

(Institute of Aeronautics and Astronautics Engineering, Air Force Engineering Univ., Xi'an 710038, China)

Received:2016-06-29 Online:2017-06-20 Published:2017-07-17

摘要/Abstract

摘要：

针对传统模型在提取图像纹理特征时的局限性，借鉴初级视皮层细胞对边缘及形状的敏感性，提出了基于初级视皮层模型的图像纹理特征提取模型．采用二维Gabor滤波器和指数延迟函数来模拟初级视皮层简单细胞的感受野，并引用绝对值求和与归一化进一步得到初级视皮层细胞模型，分析其对自然图像的响应输出特性，解码得到图像的纹理特征．仿真结果表明，建立的初级视皮层细胞模型能够基本拟合生物实验数据，实现对栅格及随机点刺激的运动特征提取; 所提纹理特征提取模型在对比选取最佳模型参数时能较好地实现对简单人造图像及自然图像的纹理特征提取，有效地搭建了生物视觉与计算机视觉的联系平台．

关键词: 纹理, 视觉特征, 初级视皮层模型, 自然图像, 运动特征

Abstract:

Focusing on the limitation of the traditional model in extracting image texture features, and referring to the sensitivity of V1 to the edge and shape, the texture feature extraction model based on the V1 model is creatively put forward. 2D Gabor filters and exponential delay function are adopted to simulate the receptive fields of the V1 simple cell, and further a V1 model is obtained by citing the sum of absolute values and normalization, and by analyzing the response characteristics of natural images, image texture features can be obtained by decoding. Simulation results show that the V1 model can tally basically with the experimental data of biology and extract motion features from the grid and random-dot stimuli, and by choosing the best model parameters by comparison, the proposed texture feature extraction model can extract texture features from simple synthetic images and natural images, which effectively sets up the correlation platform of biological vision and computer vision.

Key words: texture, visual feature, primary visual cortex model, natural image, motion feature

邹洪中;许悦雷;马时平;李帅;张文达. 仿视皮层V1结构的纹理特征提取[J]. 西安电子科技大学学报, 2017, 44(3): 96-100+107.

ZOU Hongzhong;XU Yuelei;MA Shiping;LI Shuai;ZHANG Wenda. Texture feature extraction simulating the structure of V1 in the cortex[J]. Journal of Xidian University, 2017, 44(3): 96-100+107.

参考文献

［1］刘丽, 匡纲要. 图像纹理特征提取方法综述［J］. 中国图象图形学报, 2009,14(4): 622-635.
LIU Li, KUANG Gangyao. Overview of Image Textural Feature Extraction Methods［J］. Journal of Image and Graphics, 2009, 14(4): 622-635.
［2］ NAMBOODIRI V M K, HUERTAS M A, MONK K, et al. Visually Cued Action Timing in the Primary Visual Cortex ［J］. Neuron, 2015, 86(1): 319-330.
［3］ ZOU Z, YANG J, MEGALOOIKONOMOU V, et al. Trabecular Bone Texture Classification Using Wavelet Leaders［C］//Proceedings of SPIE: 9788. Bellingham: SPIE, 2016: 97880E.
［4］ AHMADVAND A, KABIRI P. Multispectral MRI Image Segmentation Using Markov Random Field Model ［J］. Signal, Image and Video Processing, 2016, 10(2): 251-258.
［5］ ERGEN B. Scale Invariant and Fixed-length Feature Extraction by Integrating Discrete Cosine Transform and Autoregressive Signal Modeling for Palmprint Identification ［J］. Turkish Journal of Electrical Engineering and Computer Sciences, 2016, 24(3): 1768-1781.
［6］王卫卫, 席灯炎, 杨塨鹏, 等. 利用结构纹理分解的海洋舰船目标检测［J］. 西安电子科技大学学报, 2012, 39(4): 131-137.
WANG Weiwei, XI Dengyan, YANG Gongpeng, et al. Warship Target Detection Algorithm Based on Cartoon-texture Decomposition［J］. Journal of Xidian University, 2012, 39(4): 131-137.
［7］ PURVES D, MONSON B B, SUNDARARAJAN J, et al. How Biological Vision Succeeds in the Physical World ［J］. Proceedings of National Academy of Sciences, 2014, 111(13): 4750-4755.
［8］ CHEONG S K, TAILBY C, SOLOMON S G, et al. Cortical-like Receptive FIelds in the Lateral Geniculate Nucleus of Marmoset Monkeys ［J］. The Journal of Neuroscience: The Official Journal of the Society for Neuroscience, 2013, 33(16): 6864-6876.
［9］ ODAIBO S G. The Gabor-Einstein Wavelet: a Model for the Receptive Fields of V1 to MT Neurons ［J］. arXiv, 2014, 1:1-39.
［10］ SOLARI F, CHESSA M, MEDATHATI N V K, et al. What Can We Expect from a V1-MT Feedforward Architecture for Optical Flow Estimation? ［J］. Signal Processing: Image Communication, 2015, 39: 342-354.
［11］ BHATEJA V, SRIVASTAVA A, SINGH G, et al. A Modified Speckle Suppression Algorithm for Breast Ultrasound Images Using Directional FIlters［C］//Advances in Intelligent Systems and Computing: 249 VOLUME II. Berlin: Springer Verlag, 2014: 219-226.
［12］ GAO S, PENG Y H, GUO H Z, et al. Texture Analysis and Classification of Ultrasound Liver Images ［J］. Bio-Medical Materials and Engineering, 2014, 24(1): 1209-1216.
［13］ SIMONCELLI E P, HEEGER D J. A Model of Neuronal Responses in Visual Area MT ［J］. Vision Research, 1998, 38(5): 743-761.
［14］ AN X, GONG H, MCLOUGHLIN N, et al. The Mechanism for Processing Random-dot Motion at Various Speed in Early Cortices［J］. PLOS ONE, 2014, 9(3): e93115.

[1]	武鑫婷, 黄樱, 牛保宁, 关虎, 兰方鹏, 刘杰. 图像纹理引导的迭代水印模型[J]. 西安电子科技大学学报, 2024, 51(5): 110-121.
[2]	夏译蓝, 王秀美, 程培涛. 基于多注意力机制的纹理感知视频修复方法[J]. 西安电子科技大学学报, 2024, 51(3): 136-146.
[3]	段亭宇, 水鹏朗, 封天. 对数正态纹理海杂波背景非相干CFAR检测方法[J]. 西安电子科技大学学报, 2022, 49(5): 1-8.
[4]	戎如意,薛珮芸,白静,贾海蓉,谢娅利. 双通道决策信息融合下的微表情识别[J]. 西安电子科技大学学报, 2022, 49(4): 127-133.
[5]	邓燕子;卢朝阳;李静. 交通场景的多视觉特征图像分割方法[J]. J4, 2015, 42(6): 11-16.
[6]	张国鹏;廖琪梅;焦纯;李宝娟;刘洋;卢虹冰 . 虚拟结肠镜的计算机辅助诊断技术 [J]. J4, 2015, 42(2): 157-161.
[7]	闫允一;姜帅;郭宝龙. 结合稳定兴趣点和Gabor小波的图像检索[J]. J4, 2014, 41(5): 118-123.
[8]	吴玉莲;冯象初. 利用平衡方法的非凸图像修复[J]. J4, 2014, 41(5): 141-147.
[9]	王卫卫;席灯炎;杨塨鹏;周丽娟. 利用结构纹理分解的海洋舰船目标检测[J]. J4, 2012, 39(4): 131-137.
[10]	刘伟;郭立新;王安琪. 具有纹理特征的二维高斯粗糙面单双站极化散射[J]. J4, 2011, 38(6): 75-81+102.
[11]	郝岩;冯象初;许建楼. 一种非局部扩散的图像修复模型[J]. J4, 2010, 37(5): 825-828.
[12]	李世忠;胡莘;顾学迈;吕源;王昱. 新型遥感立体图像编码质量评价方法[J]. J4, 2009, 36(5): 927-932.
[13]	汪凯斌1;俞卞章1;王琦2;奚玮1. 无须反复初始化的活动围道纹理分割方法 [J]. J4, 2008, 35(3): 542-545.
[14]	邵晓鹏;郑宏斌;徐军;张建奇. 光裸地表红外辐射统计模型及纹理特征分析 [J]. J4, 2007, 34(6): 944-946.
[15]	马文萍;尚荣华;焦李成. 免疫克隆优化聚类技术 [J]. J4, 2007, 34(6): 911-915.

仿视皮层V1结构的纹理特征提取

Texture feature extraction simulating the structure of V1 in the cortex

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0