Title :
A SVM-based Image Classification Method in Document System of Personnel Archives
Author :
Chen, Jianbang ; Han, Lu ; Xiong, Zhan ; Sun, Ning ; Gao, Guangchao ; Li, Quandong
Author_Institution :
Sch. of Comput. & Inf. Sci., Southwest Univ., Chongqing, China
Abstract :
Information technology has deeply penetrated into the personnel archives management to improve its security, privacy and high efficiency. This paper comes up with a method to solve problems about image classification. It combines SVM with Huffman tree to construct a classifier HFM-SVM. Constructing HFM-SVM, it extracts paragraph and local pixel features of archive document images as training samples and test data and can classify all of personnel archive documents into five classes such as ID cards, application forms and labor contracts and so on. Comparing with multiple classifiers, the experimental results show that HFM-SVM does better in automatically fast and accurate classification of personnel archive document images.
Keywords :
Huffman codes; data privacy; document image processing; feature extraction; image classification; information retrieval systems; security of data; support vector machines; HFM-SVM construction; Huffman tree; SVM-based image classification; archive document images; classifier construction; information technology; local pixel feature extraction; paragraph extraction; personnel archive document classification; personnel archive management; privacy improvement; security improvement; support vector machine; test data; training samples; Binary trees; Classification algorithms; Feature extraction; Image classification; Personnel; Support vector machines; Training; Huffman tree; Local pixel feature; Paragraph feature; Personnel Archives; Support vector machine;
Conference_Titel :
Internet Computing for Science and Engineering (ICICSE), 2012 Sixth International Conference on
Conference_Location :
Henan
Print_ISBN :
978-1-4673-1683-5
DOI :
10.1109/ICICSE.2012.35
