ridm@nrct.go.th   ระบบคลังข้อมูลงานวิจัยไทย   รายการโปรดที่คุณเลือกไว้

A novel multiple experts and fusion based segmentation algorithm for cursive handwriting recognition

หน่วยงาน Central Queensland University, Australia

รายละเอียด

ชื่อเรื่อง : A novel multiple experts and fusion based segmentation algorithm for cursive handwriting recognition
นักวิจัย : Lee, Hong. , Verma, Brijesh.
คำค้น : Applied research. , 890202 Application Tools and System Utilities. , 890201 Application Software Packages (excl. Computer Games) , 080109 Pattern Recognition and Data Mining. , 080108 Neural, Evolutionary and Fuzzy Computation. , 080106 Image Processing. , Pattern perception. , Algorithms. , Neural networks (Computer science) , Segmentation algorithm -- Handwriting recognition -- Neural networks
หน่วยงาน : Central Queensland University, Australia
ผู้ร่วมงาน : -
ปีพิมพ์ : 2551
อ้างอิง : http://hdl.cqu.edu.au/10018/27960 , http://dx.doi.org/10.1109/IJCNN.2008.4634219 , cqu:4286
ที่มา : Hong, L & Verma, B 2008, 'A novel multiple experts and fusion based segmentation algorithm for cursive handwriting recognition', paper presented at the 2008 IEEE World Congress on Computational Intelligence (WCCI 2008). Hong Kong.http:/dx.doi.org/10.1109/IJCNN.2008.4634219
ความเชี่ยวชาญ : -
ความสัมพันธ์ : Proceedings : International Joint Conference on Neural Networks (IJCNN 2008) : (part of the 2008 IEEE World Congress on Computational Intelligence (WCCI 2008)), June 1-6, 2008. USA. : IEEE, 2008. p. 2993-2998 6 pages Refereed 9781424418213 (online) , ACQUIRE [electronic resource] : Central Queensland University Institutional Repository.
ขอบเขตของเนื้อหา : -
บทคัดย่อ/คำอธิบาย :

This paper presents a novel segmentation algorithm for offline cursive handwriting recognition. An over-segmentation algorithm is introduced to dissect the words from handwritten text based on the pixel density between upper and lower baselines. Each segment from the over-segmentation is passed to a multiple expert-based validation process. First expert compares the total foreground pixel of the segmentation point to a threshold value. The threshold is set and calculated before the segmentation by scanning the stroke components in the word. Second expert checks for closed areas such as holes. Third expert validates segmentation points using a neural voting approach which is trained on segmented characters before validation process starts. Final expert is based on oversized segment analysis to detect possible missed segmentation points. The proposed algorithm has been implemented and the experiments on cursive handwritten text have been conducted. The results of the experiments are very promising and the overall performance of the algorithm is more effective than the other existing segmentation algorithms.

บรรณานุกรม :
Lee, Hong. , Verma, Brijesh. . (2551). A novel multiple experts and fusion based segmentation algorithm for cursive handwriting recognition.
    กรุงเทพมหานคร : Central Queensland University, Australia.
Lee, Hong. , Verma, Brijesh. . 2551. "A novel multiple experts and fusion based segmentation algorithm for cursive handwriting recognition".
    กรุงเทพมหานคร : Central Queensland University, Australia.
Lee, Hong. , Verma, Brijesh. . "A novel multiple experts and fusion based segmentation algorithm for cursive handwriting recognition."
    กรุงเทพมหานคร : Central Queensland University, Australia, 2551. Print.
Lee, Hong. , Verma, Brijesh. . A novel multiple experts and fusion based segmentation algorithm for cursive handwriting recognition. กรุงเทพมหานคร : Central Queensland University, Australia; 2551.