论文:2012,Vol:30,Issue(2):201-205
引用本文:
余瑞星, 孟立勋. 一种新的ICM模型参数设置方法[J]. 西北工业大学
Yu Ruixing, Meng Lixun. A New and Effective Method for Setting Parameters of ICM (Intersecting Cortical Model)[J]. Northwestern polytechnical university

一种新的ICM模型参数设置方法
余瑞星, 孟立勋
西北工业大学 航天学院,陕西 西安 710072
摘要:
针对ICM模型用于目标识别参数需要人工设置的问题,提出一种新的ICM模型参数设置方法。该方法从提高目标识别率出发,提出利用相关系数确定ICM模型参数学习准则,使用梯度下降法对这一准则进行求解,达到根据输入图像的不同自适应确定ICM模型参数的目的。实验结果表明该方法可以很好解决传统ICM网络参数需要人工选取的劣势。
关键词:    交叉皮层模型    图标    误差函数    梯度下降    目标识别   
A New and Effective Method for Setting Parameters of ICM (Intersecting Cortical Model)
Yu Ruixing, Meng Lixun
College of Astronautics,Northwestern Polytechnical University,Xi'an 710072,China
Abstract:
In identifiying targets, the parameters of the ICM model need to be set manually. So we propose what webelieve to be a new and effective method for setting the parameters, which is explained in sections 1 and 2 of thefull paper. Section 1 briefs the ICM. Subsections 2. 1 deals with the error function, which is based on correlationcoefficients, and the ICM parameteer setting procedures based on gradient descent; subsection 2. 2 gives a 3-stepcalculation procedure for adaptively setting the ICM parameters in accordance with different input images. Section 3uses three numerical examples to verify the effectiveness of our method; the simulation results, given in Figs. 1through 3 and Tables 1 and 2, and their analysis show preliminarily that our new method has slightly higher targetrecognition rate than the method mentioned in Ref. 11 and can indeed effectively set the ICM parameters and en-hance the reliability and efficiency of the ICM.
Key words:    algorithms    analysis    calculations    correlation methods    effects    efficiency    feature extraction    func-tions    image processing    models    numerical methods    optimization    parameter estimation    reliability    simulation    standards    targets;error function    gradient descent    intersecting cortical model(ICM)    target recognitionicon   
收稿日期: 2011-05-12     修回日期:
DOI:
基金项目: 国家自然科学基金(61101191);陕西省自然科学基金(2011JQ8016);西北工业大学基础研究基金;航空科学基金(20100153001)资助
通讯作者:     Email:
作者简介: 余瑞星(1978-),女,西北工业大学副教授,主要从事图像处理、计算机视觉与成像制导技术研究。
相关功能
PDF(505KB) Free
打印本文
把本文推荐给朋友
作者相关文章
余瑞星  在本刊中的所有文章
孟立勋  在本刊中的所有文章

参考文献:
[1] 孙即祥. 模式识别中的特征提取与计算机视觉不变量. 北京:国防工业出版社, 2001Sun Jixiang. Feature Extraction in Pattern and Computer Vision Invariants. Beijing: National Defence Industry Press, 2001 (inChinese)
[2] Kauppien H, Sepanen T. An Experiment Comparison of Autoregressive and Fourier Based Descriptors in 2D Shape Classifica-tion. IEEE Trans on Pattern Analysis and Machine Intelligence, 1995, 17(2): 201-207
[3] Kadyrov A, Petrou M. The Trace Transform and Its Application. PAMI, 2001, 23:811-828
[4] 王凤国. 小波变换及其在仿射不变目标识别中的应用: [硕士学位论文]. 西安电子科技大学, 2007Wang Fenguo. Wavelet Transform and Its Application in Affine Invariant Object Recognition. Master Degree Dissertation. Xi'anUniversity of Electronic Science and Technology, 2007 (in Chinese)
[5] Eckhorn R, Reitboeck H J, Arndt Metal. Feature Linking Via Synchronization among Distributed Assemblies: Simulation of Re-sults from Cat Cortex. Neural Comput, 1990, 2(3): 293-307
[6] Johnson J L, Ritter D. Observation of Periodic Waves in a Pulse-Coupled Neural Network. Opt Lett, 1993, 18(15): 1253-1255
[7] Kinser J M. Image Signatures: Classification and Ontology. Proc IASTED Int Conf on Computer Graphics and Imaging, 2001
[8] Yu Ruixing, Zhu Bing, Zhang Ke, et al. An Image Matching Recognition Approach Based on ICM Icon/ FSKD 2008, 4: 20-23
[9] Ulf Ekblad, Jason M Kinser. Theoretical Foundation of the Intersecting Cortical Model and Its Use for Change Detection of Air-craft Cars and Nuclear Explosion Tests. Signal Processing, 2004, 84(7): 1131-1146
[10] 徐 昕, 贺汉根. 神经网络增强学习的梯度算法研究. 计算机学报, 2003, 26(2): 227-232Xu Xin, He Hangen. A Gradient Algorithm for Neural-Network-Based Reinforcement Learning. Chinese Journal of Computers, 2003, 26(2): 227-232 (in Chinese)
[11] 罗 敏, 朱晓岷, 李小红. 基于径向小波变换的图像特征提取算法. 武汉大学学报(信息科学版), 2008, 33(1):29-31Luo Min, Zhu Xiaomin, Li Xiaohong. Wavelet-Radial Descriptor Based Algorithm for Image Feature Extraction. Geomatics andInformation Science of Wuhan University, 2008, 33(1):29-31 (in Chinese)