西安交通大学理学院,西安,710049
网络首发:2010-10-10,
纸质出版:2010
移动端阅览
刘京鑫, 孙剑, 孟德宇. 基于视觉原理的分类算法[J]. 西安交通大学学报, 2010,44(10):116-119+124.
New Classification Algorithm Based on Visual Principles[J]. 2010, 44(10): 116-119+124.
从一种新的基于生物视觉原理的观点
提出了一种新的数据分类算法.将数据集看作图像
利用高斯导函数进行特征提取
并用提取出来的特征计算数据的局部结构
在此基础上设计各向异性感受野函数
最后根据各向异性的核函数构造出分类决策函数.在标准测试集上的实验表明:所提出的算法与支持向量机算法分类正确率相当
同时具有更高的训练速度; 与Parzen窗分类算法相比
尽管训练速度相对较慢
但分类精度明显提高
很好地综合了分类算法对训练速度和分类精度的要求.
A novel data classification algorithm based on the biological visual principles is proposed. Viewing the data set as an image
the local structures of data image are extracted as the basis of an anisotropic receptive field function
and the decision function is designed. The experiments on standard datasets show that this algorithm is comparable to SVM in accuracy but with significantly higher training rate. Compared with the Parzen window classification algorithm
though with relatively slower in training rate
it achieves much higher accuracy. Thus
the proposed algorithm meets the requirements of both training rate and classification accuracy.
RAJAN J, RAYNER P. Time series classification using the Volterra connection model and Bayes decision theory[C]∥IEEE International Conference on Acoustics, Speech, and Signal Processing. Piscataway, NJ, USA: IEEE, 1993:27-30.
FUKUNAGA K. Introduction to statistical pattern recognition[M]. San Diego, USA: Academic Press, 1990:30-33.
RATSCH G,MIKA S, MULLER S B. Constructing boosting algorithms from SVMs: an application to one-class classification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(9):1184-1199.
EGMONT PETERSEN M, DE RIDDER D, HANDELS H. Image processing with neural networks: a review[J]. Pattern Recognition, 2002, 35(10):2279-2301.
CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 3(3):273-297.
HUBEL D H, WIESEL T N. Receptive fields, binocular interaction and functional architecture in the cat's visual cortex[J]. Journal of Physiology, 1962, 160(1):106-154.
HOWELL A J, HOWELL A J, BUXTON H, et al. Receptive field functions for face recognition[C]∥Proc 2nd Int Workshop Parallel Modelling of Neural Operators for Pattern Recognition. Faro, Portugal: University of Algarve, 1995:83-92.
DAUGMAN J G. Two-dimensional spectral analysis of cortical receptive field profiles[J]. Vision Research, 1980, 20(10):847-856.
LINDEBERG T. Scale-space for discrete signals [J]. PAMI, 1990, 12(3):234-254.
SCENIAK M P, RINGACH D L, HAWKEN M J, et al. Contrast's effect on spatial summation by macaque V1 neurons[J]. Nature Neuroscience, 1999, 2(8):733-739.
SHEPP L A. Radon-Nikodym derivatives of Gaussian measures [J]. The Annals of Mathematical Statistics, 1966, 37(2):321-354.
JAIN A K, FARROKHNIA F. Unsupervised texture segmentation using Gabor filter [J]. Pattern Recognition, 1991, 24(12):1167-1186.
XU Zongben, DAI Mingwei, MENG Deyu. A fast heuristic strategy for model selection of support vector machines [J]. IEEE Transactions on Systems, Man and Cybernetics: part B, 2009, 39(5):1292-1307.
0
浏览量
4
下载量
1
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621