基于图像自身复杂视觉信息的特征提取算法与应用

计算机科学 ›› 2014, Vol. 41 ›› Issue (Z6): 234-238.

基于图像自身复杂视觉信息的特征提取算法与应用

赵彦明,季圣杰

河北民族师范学院数学与计算机系模式识别研究室承德067000;昆明理工大学理学院昆明650500

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受河北省高等学校科学研究项目(Z2012127),承德市财政支撑项目(CZ2012009),河北民族师范学院科学技术研究项目(201303)资助

Feature Extraction Algorithms and Applications Based on Complex Visual Information of Image

ZHAO Yan-ming and JI Sheng-jie

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 针对现阶段特征提取方法忽视图像自身的视觉信息的问题,提出了基于图像自身复杂视觉信息的特征提取算法与应用。该算法分析了视觉皮层V1区4B层复杂细胞的视觉功能,揭示了复杂视觉细胞提取区域图像非线性、独立和平移不变性特征的能力,建立了复杂视觉细胞的数学模型,并通过该模型提取了区域图像包含的复杂视觉信息。实验证明:所提算法依据图像自身包含的高级视觉信息,自适应提取区域图像的非线性、独立性和几何不变性特征,克服了常见特征提取算法忽视图像自身视觉特征的缺陷；在基于图像内容的图像检索领域,算法取得了良好的检索效果。

关键词: 视觉感知理论,几何不变性,非线性主成分分析,特征提取中图法分类号TP183,TP391文献标识码A

Abstract: Feature extraction is a key position in the field of image analysis,understanding and recognition.At the present stage,the approach of feature extraction ignores its own visual information of image．Based on that,feature extraction algorithms and applications based on the complex visual information of image itself was proposed.The algorithm analyzes the complex cells function of at the area V1layer 4B of visual cortex,reveals the ability of the complexity of the visual cells,i.e.extracting image region independent,non-linear and translation invariant features,creats the mathematical model of complex visual cells,and extracts complex visual information of region image.It solves the shortcomings of ignoring the visual characteristics of the image itself and achieves good search results in the field of content-based image retrieval.

Key words: Visual perception theory,Geometric invariance,Nonlinear principal component analysis,Feature extraction

赵彦明,季圣杰. 基于图像自身复杂视觉信息的特征提取算法与应用[J]. 计算机科学, 2014, 41(Z6): 234-238. https://doi.org/

ZHAO Yan-ming and JI Sheng-jie. Feature Extraction Algorithms and Applications Based on Complex Visual Information of Image[J]. Computer Science, 2014, 41(Z6): 234-238. https://doi.org/

参考文献

[1] 罗洁思,于德介,彭富强.基于多尺度线性调频基信号稀疏分解的多分量LFM信号检测[J]．电子与信息学报,2009,1(11):2782-2785
[2] 许强,马登武.傅里叶描述子与角点相结合的形状匹配[J]．光电工程,2013,0(6):124-128
[3] 王科俊,邹国锋．基于子模式的Gabor特征融合的单样本人脸识别[J]．模式识别与人工智能,2013,6(1):51-56
[4] 于明月,陈果．双自适应小波局部极大模方法及其在信号特征提取中的应用[J]．振动与冲击,2013,2(1):54-59
[5] 张彦梅,于敬波．基于Zoom-FFT变换域的坦克被动式毫米波探测识别方法[J]．南京理工大学学报:自然科学版,2013(3):86-91
[6] 於东军,吴小俊,Hancock E R．广义SOM及其在人脸性别识别中的应用[J]．计算机学报,2011,4(9):1720-1725
[7] 王尧,余祖俊,朱力强,等．基于脉冲耦合神经网络和Markov随机场的立体匹配研究[J]．仪器仪表学报,2013,34(7):1540-1545
[8] Hyvrinen A,Hoyer P O,Inki M．Topographic IndependentComponent Analysis[J].Neural Computation,2001,3(7):1527-1558
[9] 赵彦明．基于生物视觉信息的PCNN参数自适应设置方法及模型改进[J].计算机科学,2013,40(6):291-294
[10] Olshausen B A,Field D J.How close are we to understanding V1?[J]． Neural C omputation,2005,7:1665-1699
[11] Serre T,Wolf L,Bileschi S,et al.Robust Object Recognition with Cortex-Like Mechanisms[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(3):411-426
[12] Tatani K,Nakamura Y．Dimensionality reduction and reproduction with hierarchical NLPCA neural networks-extracting common space of multiple humanoid motion patterns[C]∥Proc.of IEEE International Conference on Robotics and Automation．2003:1927-1932
[13] Eckhorn R,Reitboeck H J,Arndt M,et al.Feature linking via synchronization among distributed assemblies:Simulations of results from cat visual cortex[J]．Neural Computation,1990(2):293-307
[14] 杨光,王恒,徐鹏,等.基于NSCT和MPCNN的人脸特征提取[J].计算机工程,2012,38(22):152-158

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed