作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2012, Vol. 38 ›› Issue (16): 23-26. doi: 10.3969/j.issn.1000-3428.2012.16.006

• 专栏 • 上一篇    下一篇

基于纹理图像分析的生物视觉模型不变性评价

储宇潼 1,2,霍 宏 1,2,钱 康 1,2,朱辰阳 1,2,方 涛 1,2   

  1. ( 1. 上海交通大学自动化系,上海 200240;2. 系统控制与信息处理教育部重点实验室,上海 200240)
  • 收稿日期:2011-09-21 修回日期:2011-12-09 出版日期:2012-08-20 发布日期:2012-08-17
  • 作者简介:储宇潼(1987-),女,硕士研究生,主研方向:计算机视觉,数字图像处理;霍 宏,讲师、博士研究生;钱 康、朱辰阳,硕士研究生;方 涛,教授、博士生导师
  • 基金资助:

    国家自然科学基金资助项目(41071256);国家“973”计划基金资助项目(2012CB719903);国家教育部高等学校博士学科点专项科研基金资助项目(20090073110018)

Invariance Evaluation for Biological Visual Model Based on Analysis of Textured Images

CHU Yu-tong 1,2, HUO Hong 1,2, QIAN Kang 1,2, ZHU Chen-yang 1,2, FANG Tao 1,2   

  1. (1. Department of Automation, Shanghai Jiaotong University, Shanghai 200240, China; 2. Key Laboratory of System Control and Information Processing, Ministry of Education, Shanghai 200240, China)
  • Received:2011-09-21 Revised:2011-12-09 Online:2012-08-20 Published:2012-08-17

摘要:

基于纹理图像,从计算机视觉角度对生物视觉模型——视皮层目标识别的标准模型进行定量分析与评价。对原始图像分别进行尺度、旋转及仿射等变化,利用标准模型提取变化后图像的生物视觉特征,再根据提取的生物视觉特征对纹理图像进行分类,采用图像分类结果的曲线下面积来定量分析和评价生物视觉模型是否具有不变性。大量与局部二元模式特征的对比实验表明,该模型提取的生物视觉特征对于纹理图像具备优良的尺度、旋转与仿射不变性。

关键词: 生物视觉特征, 局部二元模式特征, 尺度不变性, 旋转不变性, 仿射不变性, 纹理图像

Abstract:

From the view of computer vision, the particular quantitative analyses and evaluations about rotational, scale and affine invariance of standard model of object recognition in cortex are made based on textured images. The original textured images are scaled, rotated and affinely transformed respectively. Biological visual features of these transformed images, also called Standard Model Features(SMFs), are extracted by the standard model. The SMFs are used to classify the images. After classification, the area under curve is utilized to quantitatively analyze and evaluate whether the standard model has invariance or not. Compared with the Local Binary Pattern(LBP) feature, a great deal of experiments show that the biological visual features extracted by the standard model have superior scale, rotational and affine invariance to textured images.

Key words: biological visual feature, Local Binary Pattern(LBP) feature, scale invariance, rotational invariance, affine invariance, textured image

中图分类号: