A double-threshold image binarization method based on edge detector

This paper presents a new double-threshold image binarization method based on the edge and intensity information. We first find seeds near the image edges and present an edge connection method to close the image edges. Then, we use closed image edges to partition the binarized image that is generated using a high threshold, and obtain a primary binarization result by filling the partitioned high-threshold binary image with the seeds. Finally, the final binarization result is obtained by remedying the primary binarization result with the low-threshold binary image. Compared with the classical binarization methods and the similar binarization methods, our method is effective on the binarization of images with low contrast, noise and non-uniform illumination. (c) 2007 Elsevier Ltd. All rights reserved.