Loading...
Search
Search in this resource
sort by
کاربرد تجزیه تنک در تشخیص اتوماتیک حروف
729 viewed

کاربرد تجزیه تنک در تشخیص اتوماتیک حروف

حمیدی قلعه جق، سینا Hamidi Ghalehjegh, Sina

Application of Sparse Decomposition to Optical Character Recognition

Hamidi Ghalehjegh, Sina | 2010

876 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 40675 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Babaie-Zadeh, Massoud
  7. Abstract:
  8. Optical Character Recognition is a branch of Image Processing and deals with transforming a scanned document into a text file. The output of a scanning system is in image format and a digital system has no sense about its content. Therefore, this system cannot do any process on its text. For example, words searching, sentences edition and another tasks that are easily done in a word processing software, cannot be directly applied on a scanned document. So, we need a tool to extract the text from a scanned document. A character recognition system consists of different stages: scanning, preprocessing, segmentation, feature extraction, character recognition and post-processing. The purpose of this thesis is studying the possibility of using sparse decomposition (stating an image as a linear combination of a set of training images) in character recognition system. Introductions of this subject have been already studied in our laboratory in an MS thesis done by Ms. Soodeh Ahani. In the current thesis we will enhance the performance of the character recognition system by proposing BSL0 and Weighting methods. In BSL0 method we will use blocking property of the output vector and in Weighting method we will use sparse decomposition idea and minimum distance together to achieve a better quality. Moreover, we will propose an algorithm to overcome the problem of misunderstanding between English uppercase and lowercase letters
  9. Keywords:
  10. Sparse Decomposition ; Pattern Recognition ; Image Processing ; Optical Character Recognition (OCR) ; Character Recognition

 Digital Object List

 Bookmark

No TOC