A new approach to extract and segment characters in natural scenes was proposed in this paper. First, a set of intrinsic features were calculated based on connected components (CCs) extracted by a non-linear Nilblack ...A new approach to extract and segment characters in natural scenes was proposed in this paper. First, a set of intrinsic features were calculated based on connected components (CCs) extracted by a non-linear Nilblack algorithm. Then, feature propagation was conducted for feature enhancement, under the constraint of the layout relations. Next, candidate CCs were fed into classifiers with the enhanced feature vector. At last, a model-based hierarchical merging (MHM) procedure was presented to obtain understandable characters. The proposed merging algorithm utilized the constraint of text lines for specific languages and dynamically merges CCs into characters. The whole algorithm was evaluated at both pixel level and character level, experimental results showed that the proposed method is effective in detecting scene characters with significant geometric variations, uneven illumination, extremely low contrast and cluttered background.展开更多
This paper presents a new method for text detection, location and binarization from natural scenes. Several morphological steps are used to detect the general position of the text, including English, Chinese and Japan...This paper presents a new method for text detection, location and binarization from natural scenes. Several morphological steps are used to detect the general position of the text, including English, Chinese and Japanese characters. Next bounding boxes are processed by a new “Expand, Break and Merge” (EBM) method to get the precise text areas. Finally, text is binarized by a hybrid method based on Otsu and Niblack. This new approach can extract different kinds of text from complicated natural scenes. It is insensitive to noise, distortedness, and text orientation. It also has good performance on extracting texts in various sizes.展开更多
文摘A new approach to extract and segment characters in natural scenes was proposed in this paper. First, a set of intrinsic features were calculated based on connected components (CCs) extracted by a non-linear Nilblack algorithm. Then, feature propagation was conducted for feature enhancement, under the constraint of the layout relations. Next, candidate CCs were fed into classifiers with the enhanced feature vector. At last, a model-based hierarchical merging (MHM) procedure was presented to obtain understandable characters. The proposed merging algorithm utilized the constraint of text lines for specific languages and dynamically merges CCs into characters. The whole algorithm was evaluated at both pixel level and character level, experimental results showed that the proposed method is effective in detecting scene characters with significant geometric variations, uneven illumination, extremely low contrast and cluttered background.
文摘This paper presents a new method for text detection, location and binarization from natural scenes. Several morphological steps are used to detect the general position of the text, including English, Chinese and Japanese characters. Next bounding boxes are processed by a new “Expand, Break and Merge” (EBM) method to get the precise text areas. Finally, text is binarized by a hybrid method based on Otsu and Niblack. This new approach can extract different kinds of text from complicated natural scenes. It is insensitive to noise, distortedness, and text orientation. It also has good performance on extracting texts in various sizes.
