Optimal Local Area Separation to Binarize Low-contrast Character Image Using Genetic Algorithm
スポンサーリンク
概要
- 論文の詳細を見る
The method to binarize a gray-scaled image by local thresholds in separated image areas is useful when the image has uneven brightness. However, many binary noises often occur in local image areas with even brightness. This paper proposes a method to separate a gray-scaled image dynamically for local thresholding to generate a binary image using a genetic algorithm. The experimental results show that the binarized images by the proposed method included less noise and blur than the binalized images by the conventional method that separates a gray-scaled image equally. Also, the method that the number of separated local areas is variable depending on the objective gray-scaled images generated the binary images with fewer noises than the method that the number of local areas is constant.
- 社団法人映像情報メディア学会の論文
- 2000-01-14
著者
関連論文
- Optimal Local Area Separation to Binarize Low-contrast Character Image Using Genetic Algorithm
- IMAGE MATCHING METHOD FOR PRINTED CIRCUIT BOARD USING EDGE DIRECTION HISTOGRAM BASED ON EDGE STRENGTH
- Image Matching Based on Relation between Pixels Located on the Maximum and Minimum Gray-levels in Local Area
- A Case of Mediastinal Pancreatic Pseudocyst Successfully Treated with Somatostatin Analogue