ridm@nrct.go.th   ระบบคลังข้อมูลงานวิจัยไทย   รายการโปรดที่คุณเลือกไว้

Over-segmentation and neural binary validation for cursive handwriting recognition

หน่วยงาน Central Queensland University, Australia

รายละเอียด

ชื่อเรื่อง : Over-segmentation and neural binary validation for cursive handwriting recognition
นักวิจัย : Lee, Hong. , Verma, Brijesh.
คำค้น : Optical character recognition. , Applied research. , 890202 Application Tools and System Utilities. , 080109 Pattern Recognition and Data Mining. , 080108 Neural, Evolutionary and Fuzzy Computation. , Image processing , Text processing (Computer science) , Segmentation algorithm -- Neural learning -- Handwriting recognition
หน่วยงาน : Central Queensland University, Australia
ผู้ร่วมงาน : -
ปีพิมพ์ : 2553
อ้างอิง : http://hdl.cqu.edu.au/10018/56292
ที่มา : Lee, H & Verma, B 2010, 'Over-segmentation and neural binary validation for cursive handwriting recognition' in IEEE editors (eds.) 2010 IEEE World Congress on Computational Intelligence (IEEEWCCI 2010): International Joint Conference on Neural Networks (IJCNN), 18-23 July 2010, Barcelona, Spain, IEEE, USA, pp. 3233-3237. http://dx.doi.org/10.1109/IJCNN.2010.5596579
ความเชี่ยวชาญ : -
ความสัมพันธ์ : 2010 IEEE World Congress on Computational Intelligence (IEEE WCCI 2010). International Joint Conference on Neural Networks (IJCNN), 18-23 July 2010, Barcelona, Spain. USA. : IEEE, 2010. p. 3233-3237 5 pages Refereed 9781424469178 (online) 9781424481262 , ACQUIRE [electronic resource] : Central Queensland University Institutional Repository.
ขอบเขตของเนื้อหา : -
บทคัดย่อ/คำอธิบาย :

A novel Over-Segmentation and Neural Binary Validation (OSNBV) is presented in this paper. OSNBV is a character segmentation strategy for off-line cursive handwriting recognition. Unlike the approaches in the literature, OSNBV is a prioritized segmentation approach. Initially, OSNBV over-segments a handwritten word into primitives. Neural binary validation is iteratively applied to the primitives. The outcome of each iteration is to join two neighboring primitives when the joined one improves the global neural competency. OSNBV introduces Transition Count (TC) and TC for English (EngTC) to prevent under-segmentation error during neural binary validation. OSNBV also incorporates Transition Count Matrix (TCM) into neural global competency. The proposed approach has been evaluated on CEDAR benchmark database. The results showed a significant improvement in segmentation errors. The analysis of results showed that the inclusion of TCM into the validation function has played a major role in improving over-segmentation and bad-segmentation errors.

บรรณานุกรม :
Lee, Hong. , Verma, Brijesh. . (2553). Over-segmentation and neural binary validation for cursive handwriting recognition.
    กรุงเทพมหานคร : Central Queensland University, Australia.
Lee, Hong. , Verma, Brijesh. . 2553. "Over-segmentation and neural binary validation for cursive handwriting recognition".
    กรุงเทพมหานคร : Central Queensland University, Australia.
Lee, Hong. , Verma, Brijesh. . "Over-segmentation and neural binary validation for cursive handwriting recognition."
    กรุงเทพมหานคร : Central Queensland University, Australia, 2553. Print.
Lee, Hong. , Verma, Brijesh. . Over-segmentation and neural binary validation for cursive handwriting recognition. กรุงเทพมหานคร : Central Queensland University, Australia; 2553.