Abstract A sample vector formation method is presented to decrease the effect of the rotated characters on recognition rate. Firstly, the invariant features are extracted, such as centroid and principal axis. Then, the coordinate transformation is carried out and the image is converted to the polar coordinate system. Finally, the pixels are re-arranged according to the rules. The recognition is carried out directly on the gray-level images by adopting the improved PCA subspace method. Experimental results show that the proposed method can decrease the number of sieving samples with a higher recognition rate, compared with the typical method.
SONG Huai-Bo,LU Chang-Hou,LI Jian-Mei等. Rotate Invariant Vector Extraction of Pressed Protuberant Characters on Metal Label and PCA Based Recognition[J]. , 2008, 21(6): 824-830.
[1] Li Guoping, Lu Changhou, Li Jianmei. The Method of Image Acquisition on Metal Label Pressed Protuberant Characters Based on Moiré Contour // Proc of the 6th World Congress on Control and Automation. Dalian, China, 2006, Ⅱ: 10175-10178 [2] Wang Xuechuan, Paliwal K K. Feature Extraction and Dimensionality Reduction Algorithms and Their Applications in Vowel Recognition. Pattern Recognition, 2003, 36(10): 2429-2439 [3] Cao Jianhai. A Study on Recognition and Checking for the Pressed Protuberant Character on a Metal Label. Ph.D Dissertation. Jinan, China: Shandong University. School of Mechanical Engineering, 2004: 80-82 (in Chinese) (曹建海.金属标牌压印凹凸字符的检测与识别研究.博士学位论文.济南:山东大学.机械工程学院, 2004: 80-82) [4] Wang Junfeng, Shi Tielin, Liu Shiyuan. PCA-Based Signal Whitening Decorrelation. China Mechanical Engineering, 2005, 16(21): 954-1956 (in Chinese) (王峻峰,史铁林,刘世元.基于主分量分析的信号白化解相关处理.中国机械工程, 2005, 16(21): 1954-1956) [5] Jiang Weifeng, Liu Jilin. Recognition of a Limited Chinese Character Set Based on PCA Learning Subspace Algorithm. Journal of Image and Graphics, 2001, 6(2): 186-190 (in Chinese) (蒋伟峰,刘济林.基于PCA学习子空间算法的有限汉字识别.中国图象图形学报, 2001, 6(2): 186- 190) [6] Seghouane A K, Cichocki A. Bayesian Estimation of the Number of Principal Components. Signal Processing, 2007, 87(3): 562-568 [7] Korenius T, Kaurikkale J, Juhola M. On Principal Component Analysis, Cosine and Euclidean Measures in Information Retrieval. Information Science, 2007, 177(22): 4893-4925 [8] Salinelli E, Sgarra C. Shift, Slope and Curvature for a Class of Yields Correlation Matrices. Linear Algebra and Its Applications, 2007, 426(2/3): 650-666 [9] Hu Xuelei, Xu Lei. A Comparative Investigation on Subspace Dimension Determination. Neural Networks, 2004, 17(8/9): 1051-1059 [10] Cordes D, Nandy R R. Estimation of the Intrinsic Dimensionality of fMRI Data. NeuroImage, 2006, 29(1): 145-154 [11] Hu M K. Visual Pattern Recognition by Moment Invariant. IEEE Trans on Information Theory, 1962, 8(2): 179-187 [12] Dudani S A, Breeding K J, McGhee R. Aircraft Identification by Moment Invariants. IEEE Trans on Computers, 1977, 26(1): 39-45 [13] Abu-Mostafa Y S, Psaltis D. Recognitive Aspects of Moment Invariants. IEEE Trans on Pattern Analysis and Machine Intelligence, 1984, 6(6): 698-706 [14] Resis T H. The Revised Fundamental Theorem of Moment Invariants. IEEE Trans on Pattern Analysis and Machine Intelligence, 1991, 13(8): 830-834 [15] Dai M, Baylou P, Najim M. An Efficient Algorithm for Computation of Shape Moments from Run-Length Codes or Chain Codes. Pattern Recognition, 1992, 25(10): 1119-1128 [16] Rui Ting, Wang Jinruo, Shen Chunlin, et al. Invariance-Based Target Recognition Using Linear Discriminate Analysis. Computer Engineering, 2005, 31(15): 4-6,18 (in Chinese) (芮 挺,王金若,沈春林,等.基于线形分析的特征不变性目标识别.计算机工程, 2005, 31(15): 4-6,18) [17] Rui Ting, Shen Chunlin, Qi Tian, et al. Invariance-Based Target Recognition Using Independent Component Analysis. Journal of Chinese Computer Systems, 2005, 26(3): 505-508 (in Chinese) (芮 挺,沈春林,Qi Tian,等.基于ICA的特征不变性目标识别.小型微型计算机系统, 2005, 26(3): 505－508) [18] Wang Qicong. Image Recognition Based on the Wavelet Analysis of Moment Features and the Neural Network. Master Dissertation. Hangzhou, China: Zhejiang University of Technology. College of Information Engineering, 2005: 11-17 (in Chinese) (王其聪.基于小波分析的矩特征和神经网络的图像识别.硕士学位论文.杭州: 浙江工业大学.信息工程学院, 2005: 11-17) [19] Oja E, Kuusela M. The ALSM Algorithm: An Improved Subspace Method of Classification. Pattern Recognition, 1983, 16(4): 421-427
2008, Vol. 21 
