Development of a Robust and Compact On-Line Handwritten Japanese Text Recognizer for Hand-Held Devices
スポンサーリンク
概要
- 論文の詳細を見る
The paper describes how a robust and compact on-line handwritten Japanese text recognizer was developed by compressing each component of an integrated text recognition system including a SVM classifier to evaluate segmentation points, an on-line and off-line combined character recognizer, a linguistic context processor, and a geometric context evaluation module to deploy it on hand-held devices. Selecting an elastic-matching based on-line recognizer and compressing MQDF2 via a combination of LDA, vector quantization and data type transformation, have contributed to building a remarkably small yet robust recognizer. The compact text recognizer covering 7,097 character classes just requires about 15MB memory to keep 93.11% accuracy on horizontal text lines extracted from the TUAT Kondate database. Compared with the original full-scale Japanese text recognizer, the memory size is reduced from 64.1MB to 14.9MB while the accuracy loss is only 0.5% from 93.6% to 93.11%. The method is scalable so even systems of less than 11MB or less than 6MB still remain 92.80% or 90.02% accuracy, respectively.
著者
-
Zhu Bilan
Graduate School Of Engineering Tokyo University Of Agriculture And Technology
-
Nakagawa Masaki
Graduate School Of Engineering Tokyo University Of Agriculture And Technology
-
NAKAGAWA Masaki
Graduate School of Engineering, Tokyo University of Agriculture and Technology
-
GAO Jinfeng
Graduate School of Engineering, Tokyo University of Agriculture and Technology
関連論文
- Evaluation of radioiodinated 5-iodo-3- (2(S) -azetidinylmethoxy) pyridine as a ligand for SPECT investigations of brain nicotinic acetylcholine receptors
- A Model of On-line Handwritten Japanese Text Recognition Free from Line Direction and Writing Format Constraints(On-line Text, Document Image Understanding and Digital Documents)
- An On-line Handwritten Japanese Text Recognition System Free from Line Direction and Character Orientation Constraints(On-line Text, Document Image Understanding and Digital Documents)
- Structuring Search Space for Accelerating Large Set Character Recognition(Search Space for Character Recognition, Document Image Understanding and Digital Documents)
- Development of a Robust and Compact On-Line Handwritten Japanese Text Recognizer for Hand-Held Devices