A new ring radius transform-based thinning method for multi-oriented video characters
Thinning that preserves visual topology of characters in video is challenging in the field of document analysis and video text analysis due to low resolution and complex background. This paper proposes to explore ring radius transform (RRT) to generate a radius map from Canny edges of each input ima...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Published: |
Springer Verlag (Germany)
2015
|
| Subjects: |
| _version_ | 1796960678870777856 |
|---|---|
| author | Wu, Y. Shivakumara, P. Wei, W. Lu, T. Pal, U. |
| author_facet | Wu, Y. Shivakumara, P. Wei, W. Lu, T. Pal, U. |
| author_sort | Wu, Y. |
| collection | UM |
| description | Thinning that preserves visual topology of characters in video is challenging in the field of document analysis and video text analysis due to low resolution and complex background. This paper proposes to explore ring radius transform (RRT) to generate a radius map from Canny edges of each input image to obtain its medial axis. A radius value contained in the radius map here is the nearest distance to the edge pixels on contours. For the radius map, the method proposes a novel idea for identifying medial axis (middle pixels between two strokes) for arbitrary orientations of the character. Iterative-maximal-growing is then proposed to connect missing medial axis pixels at junctions and intersections. Next, we perform histogram on color information of medial axes with clustering to eliminate false medial axis segments. The method finally restores the shape of the character through radius values of medial axis pixels for the purpose of recognition with the Google Open source OCR (Tesseract). The method has been tested on video, natural scene and handwritten characters from ICDAR 2013, SVT, arbitrary-oriented data from MSRA-TD500, multi-script character data and MPEG7 object data to evaluate its performances at thinning level as well as recognition level. Experimental results comparing with the state-of-the-art methods show that the proposed method is generic and outperforms the existing methods in terms of obtaining skeleton, preserving visual topology and recognition rate. The method is also robust to handle characters of arbitrary orientations. |
| first_indexed | 2024-03-06T05:48:15Z |
| format | Article |
| id | um.eprints-19427 |
| institution | Universiti Malaya |
| last_indexed | 2024-03-06T05:48:15Z |
| publishDate | 2015 |
| publisher | Springer Verlag (Germany) |
| record_format | dspace |
| spelling | um.eprints-194272018-09-26T04:44:36Z http://eprints.um.edu.my/19427/ A new ring radius transform-based thinning method for multi-oriented video characters Wu, Y. Shivakumara, P. Wei, W. Lu, T. Pal, U. QA75 Electronic computers. Computer science Thinning that preserves visual topology of characters in video is challenging in the field of document analysis and video text analysis due to low resolution and complex background. This paper proposes to explore ring radius transform (RRT) to generate a radius map from Canny edges of each input image to obtain its medial axis. A radius value contained in the radius map here is the nearest distance to the edge pixels on contours. For the radius map, the method proposes a novel idea for identifying medial axis (middle pixels between two strokes) for arbitrary orientations of the character. Iterative-maximal-growing is then proposed to connect missing medial axis pixels at junctions and intersections. Next, we perform histogram on color information of medial axes with clustering to eliminate false medial axis segments. The method finally restores the shape of the character through radius values of medial axis pixels for the purpose of recognition with the Google Open source OCR (Tesseract). The method has been tested on video, natural scene and handwritten characters from ICDAR 2013, SVT, arbitrary-oriented data from MSRA-TD500, multi-script character data and MPEG7 object data to evaluate its performances at thinning level as well as recognition level. Experimental results comparing with the state-of-the-art methods show that the proposed method is generic and outperforms the existing methods in terms of obtaining skeleton, preserving visual topology and recognition rate. The method is also robust to handle characters of arbitrary orientations. Springer Verlag (Germany) 2015 Article PeerReviewed Wu, Y. and Shivakumara, P. and Wei, W. and Lu, T. and Pal, U. (2015) A new ring radius transform-based thinning method for multi-oriented video characters. International Journal on Document Analysis and Recognition (IJDAR), 18 (2). pp. 137-151. ISSN 1433-2833, DOI https://doi.org/10.1007/s10032-015-0238-y <https://doi.org/10.1007/s10032-015-0238-y>. http://dx.doi.org/10.1007/s10032-015-0238-y doi:10.1007/s10032-015-0238-y |
| spellingShingle | QA75 Electronic computers. Computer science Wu, Y. Shivakumara, P. Wei, W. Lu, T. Pal, U. A new ring radius transform-based thinning method for multi-oriented video characters |
| title | A new ring radius transform-based thinning method for multi-oriented video characters |
| title_full | A new ring radius transform-based thinning method for multi-oriented video characters |
| title_fullStr | A new ring radius transform-based thinning method for multi-oriented video characters |
| title_full_unstemmed | A new ring radius transform-based thinning method for multi-oriented video characters |
| title_short | A new ring radius transform-based thinning method for multi-oriented video characters |
| title_sort | new ring radius transform based thinning method for multi oriented video characters |
| topic | QA75 Electronic computers. Computer science |
| work_keys_str_mv | AT wuy anewringradiustransformbasedthinningmethodformultiorientedvideocharacters AT shivakumarap anewringradiustransformbasedthinningmethodformultiorientedvideocharacters AT weiw anewringradiustransformbasedthinningmethodformultiorientedvideocharacters AT lut anewringradiustransformbasedthinningmethodformultiorientedvideocharacters AT palu anewringradiustransformbasedthinningmethodformultiorientedvideocharacters AT wuy newringradiustransformbasedthinningmethodformultiorientedvideocharacters AT shivakumarap newringradiustransformbasedthinningmethodformultiorientedvideocharacters AT weiw newringradiustransformbasedthinningmethodformultiorientedvideocharacters AT lut newringradiustransformbasedthinningmethodformultiorientedvideocharacters AT palu newringradiustransformbasedthinningmethodformultiorientedvideocharacters |