A Comparative Performance Study of Threshold Methods for Actual Documents Recognition System based on Post-PC Environment

S. Ji, C. Yunkoo, K. Taeyuen, and K. KyeKyung (Korea)


Binarization, Document Recognition, Image Segmentation


Segmentation of gray level images into foreground and background is an important task in several image processing applications such as document processing, industrial inspection and medical image analysis. For example, the correctness of the automatic recognition results in document images is entirely dependent on the quality of the thresholding of the gray level image. This paper represents a survey of a variety thresholding techniques including both global and local thresholding. Several thresholding methods are examined in detail to evaluate their performance based on a given set of test images. We also attempt to evaluate the performance of several thresholding methods for Post-PC Camera documents image recognition system using a broken line structures, broken symbols and text, blurring of lines, symbols and text, noise in homogeneous areas measure as a criterion functions.

Important Links:

Go Back