A Figure Image Processing System
Patent document images maintained by the U.S. patent database have a specific format, in which figures and descriptions are separated into different pages. This makes it difficult for users to refer to a figure while reading the description or vice versa. The system introduced in this paper is to prepare these patent documents for a friendly browsing interface. The system is able to segment an imaged page with several figures into individual figures and extract caption and label information from the figure. After obtaining captions and labels, figures and the relevant description are linked together, and thus users could easily refer from a description to the figure or vice versa.
KeywordsGraphics Recognition Graphics Segmentation User Interface
Unable to display preview. Download preview PDF.
- 1.The U.S. Patent Database, http://www.uspto.gov/patft/help/contents.htm
- 5.Wong, K.Y., Casey, R.G., Wahl, F.M.: Document analysis system. IBM Journal of Research and Development, 647–656 (1982)Google Scholar
- 6.Gonzalez, R., Woods, R.: Digital Image Processing, ch. 2. Addison-Wesley Publishing Company, Reading (1992)Google Scholar
- 7.Yuan, B., Kwoh, L.K., Tan, C.L.: Finding the best-fit bounding-boxes. In: 7th IAPR Workshop on Document Analysis Systems, New Zealand (February 13-15, 2006)Google Scholar