Binarization of Engineering Drawings Using Adaptive Thresholding Techniques
Image binarization is an important issue in image segmentation. In recent years, numerous studies have been focused on this area. Navon et al.  described the segmentation methods including histogram-based methods, boundary-based methods, region-based methods, hybrid-based methods, and graph-based technique. When the threshold method is applied to image binarization, either a global threshold or local threshold method will be used. The former method uses histogram analysis to search for a single threshold in an image and differentiate objects and background according to a comparison of all the pixels within the threshold. The latter method first segments an image into individual blocks and calculates the threshold of each block or even each pixel.
KeywordsImage Binarization Document Image Threshold Method Global Threshold Local Threshold
Unable to display preview. Download preview PDF.
- 2.Gatos B, Pratikakis I, Perantonis SJ (2004) An adaptive binarization technique for low quality historical documents. Marinai S, Dengel A (eds.) D AS, LNCS 3163, 2004, pp. 102–113Google Scholar
- 8.Smith EHB (2002) Uniqueness of bilevel image degradations. SPIE Document Recognition and Retrieval VIII, San Jose, CA, pp. 20–25Google Scholar