Title Extraction from Book Cover Images Using Histogram of Oriented Gradients and Color Information
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this paper, we present a technique to extract the title areas from book cover images. A typical book cover image may contain text, pictures, diagrams as well as complex and irregular background. In addition, the high variability of character features such as thickness, font, position, background and tilt of the text also makes the text extraction task more complicated. Therefore, we propose a two steps efficient method that uses Histogram of Oriented Gradients and color information to find the title areas. Firstly, text localization is carried out to find the title candidates. Finally, refinement process is performed to find the sufficient components of title areas. To obtain the best result, we also use other constraints about the size, ratio between the length and width of the title. We achieve encouraging results of extracted title regions from book cover images which prove the advantages and efficiency of the proposed method.
Abstract
In this paper, we present a technique to extract the title areas from book cover images. A typical book cover image may contain text, pictures, diagrams as well as complex and irregular background. In addition, the high variability of character features such as thickness, font, position, background and tilt of the text also makes the text extraction task more complicated. Therefore, we propose a two steps efficient method that uses Histogram of Oriented Gradients and color information to find the title areas. Firstly, text localization is carried out to find the title candidates. Finally, refinement process is performed to find the sufficient components of title areas. To obtain the best result, we also use other constraints about the size, ratio between the length and width of the title. We achieve encouraging results of extracted title regions from book cover images which prove the advantages and efficiency of the proposed method.
참고문헌 (13)
- Do Yen, "Generation of Training Database Using a Noise Model for OCR Systems", The 6th International Conference on Ubiquitous Information Management and Communication (2012), CD-Pub.
- 김수형, "Automatic Generation of Database to Train New Fonts for OCR Systems", THE 2012 INTERNATIONAL WORKSHOP ON ADVANCED IMAGE TECHNOLOGY, pp.178~182 (2012), IWAIT 2012
- Kee chul Jung, "Text Information Extraction in Images and Video: A Survey", Pattern Recognition, 37(5), pp.977~997 (2004)
- C. J. Park, "An efficient extraction of character string positions using morphological operator", Proc. IEEE Int. Conf. Systems, Man, Cybernetics, 3, pp.1616~1620 (2000)
- Z. Yu, "Locating text in complex color images", Proc. 3rd Int. Conf. Document Analysis and Recognition, pp.146~149 (1995)
- D. Chen, "Text identification in complex background using SVM", Proc. IEEE Computer Soc.Conf. Computer Vision and Pattern Recognition, pp.621~626 (2001)
- Yassin M. Y. Hasan, "Morphological Text Extraction from Images", IEEE Transaction on Image Processing, 9(11), pp.1978~1983 (2000)
- M. Chen, "Analysis, understanding and representation of Chinese newspaper with complex layout", Proc. 7th IEEE Int. Conf. Image Processing, 2, pp.590~593 (2000)
- A. Antonacopoulos, "ICDAR 2005 page segmentation competition", Proc. ICDAR, 2005, pp.75~80 (2005)
- A. K. Jain, "Document representation and its application to page decomposition", IEEE Trans. Pattern Anal. Mach. Intell., 20(3), pp.294~308 (1998)
- Navneet Dalal, "Histograms of Oriented Gradients for Human Detection", Computer Vision and Pattern Recognition, pp.886~893 (2005)
- B. Epshtein, "Detecting Text in Natural Scenes with Stroke Width Transform", Proc. CVPR, 2010, pp.2963~2970 (2010)
- Nguyen Noi Bai, "체인 정합과 확장된 그룹핑 방법을 사용한 곡선형 텍스트 라인 추출", 정보처리학회논문지. 소프트웨어 및 데이터 공학, 14(6), pp.453~460 (2007), 한국정보처리학회