A Method for Document Zone Content Classification.

Y Wang,IT Phillips,RM Haralick

16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL III, PROCEEDINGS（2002）

Univ Washington

被引用3|浏览3

摘要

This paper describes an algorithm to classify each given document zone into one of nine classes and provides a protocol for its performance evaluation. The classification scheme uses an optimized binary decision tree and Viterbi algorithm for HMM to find the optimal solution. Our algorithm was trained and tested on a total of 24,177 zones within the 1600 images from UWCDROM III database. Its accuracy rate is 98.45% with a mean false alarm rate of 0.50%.

更多

查看译文

关键词

binary decision diagrams,decision trees,document image processing,hidden Markov models,image classification,image segmentation,performance evaluation,visual databases,HMM,UWCDROM III database,Viterbi algorithm,document zone content classification,false alarm rate,hidden Markov model,optimized binary decision tree,performance evaluation,visual database