A Model of On-line Handwritten Japanese Text Recognition Free from Line Direction and Writing Format Constraints

Zhou

Liu

et al. 2010

IJDAR

This paper describes a robust model for on-line handwritten Japanese text recognition. The method evaluates the likelihood of candidate segmentation paths by combining scores of character pattern size, inner gap, character recognition, single-character position, pair-character position, likelihood of candidate segmentation point and linguistic context. The path score is insensitive to the number of candidate patterns and the optimal path can be found by the Viterbi search. In experiments of handwritten Japanese sentence recognition, the proposed method yielded superior performance.

Section: P(c)mentioning

confidence: 99%

“…(4) by setting h1 =1, h2 =0 (h=1~7) and =0 for [1], and by setting 41 = 42 , h2 =0(h=1~3, 5~7), and =0 for [4], respectively.…”

Section: P(c)mentioning

confidence: 99%

A robust model for on-line handwritten japanese text recognition

Zhou

Liu

et al. 2010

IJDAR

“…Nakagawa et al [4] shows the effect of integrating linguistic context, character structure context along with recognition score to improve on-line handwritten Japanese text recognition. Graves et al [3] shows the state-of-the-art on-line English handwriting recognition with the bi-directional recurrent neural networks which integrate context from both forward and backward directions.…”

Section: Introductionmentioning

confidence: 99%

Semi-Incremental Recognition of On-Line Handwritten Japanese Text

Nguyen

IEICE Trans. Inf. & Syst.

Nakagawa

2016

SUMMARY This paper presents a semi-incremental recognition method for on-line handwritten Japanese text and its evaluation. As text becomes longer, recognition time and waiting time become large if it is recognized after it is written (batch recognition). Thus, incremental methods have been proposed with recognition triggered by every stroke but the recognition rates are damaged and more CPU time is incurred. We propose semi-incremental recognition and employ a local processing strategy by focusing on a recent sequence of strokes defined as "scope" rather than every new stroke. For the latest scope, we build and update a segmentation and recognition candidate lattice and advance the best-path search incrementally. We utilize the result of the best-path search in the previous scope to exclude unnecessary segmentation candidates. This reduces the number of candidate character recognition with the result of reduced processing time. We also reuse the segmentation and recognition candidate lattice in the previous scope for the latest scope. Moreover, triggering recognition processes every several strokes saves CPU time. Experiments made on TUAT-Kondate database show the effectiveness of the proposed semi-incremental recognition method not only in reduced processing time and waiting time, but also in recognition accuracy.

“…On the other hand, the off-line method recognizes an off-line pattern, which is a character pattern image, and although it is insensitive to stroke order variation or duplicated strokes, it is not very robust to stroke connection and deformation. To overcome the disadvantage of the on-line method, the off-line recognition method is combined with the on-line method to form a combined recognizer since the off-line method is made applicable to an on-line pattern by discard- [3]. Moreover, Japanese is a large character set language that uses thousands of ideographic characters of Chinese origin, two sets of phonetic characters, alpha, numerics and symbols, so designing a compact yet robust text recognition system running on handheld devices is challenging.…”

Section: Introductonmentioning

confidence: 99%

Development of a Robust and Compact On-Line Handwritten Japanese Text Recognizer for Hand-Held Devices

Gao

IEICE Trans. Inf. & Syst.

Nakagawa

2013

SUMMARYThe 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 elasticmatching 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 15 MB 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 64.1 MB to 14.9 MB while the accuracy loss is only 0.5% from 93.6% to 93.11%. The method is scalable so even systems of less than 11 MB or less than 6 MB still remain 92.80% or 90.02% accuracy, respectively. key words: on-line recognition, handwritten text recognition, elastic matching, MQDF, vector quantization IntroductonWith the development of pen-based or touch-based handheld devices, handwritten text recognition system running on such hand-held devices needs to be developed. The relatively small RAM of a hand-held device requires a handwritten text recognition system as small as possible that maintains high accuracy. This paper focuses on constructing a compact on-line handwritten Japanese text recognition system, running on such devices.Handwritten character recognition mainly includes two types of methods: on-line and off-line recognition. The online method works on an input on-line handwritten character pattern, which is a time-sequence of pen-tip coordinates, and although it is easily made robust to stroke connection and deformation, it is sensitive to stroke order variation. On the other hand, the off-line method recognizes an off-line pattern, which is a character pattern image, and although it is insensitive to stroke order variation or duplicated strokes, it is not very robust to stroke connection and deformation. To overcome the disadvantage of the on-line method, the off-line recognition method is combined with the on-line method to form a combined recognizer since the off-line method is made applicable to an on-line pattern by discard- [3]. Moreover, Japanese is a large character set language that uses thousands of ideographic characters of Chinese origin, two sets of phonetic characters, alpha, numerics and symbols, so designing a compact yet robust text recognition system running on handheld devices is challenging. We need to compress each component in the text recognizer while keeping high accuracy.For Japanese and Chinese off-line handwritten character recognition, MQDF2 [4] has been widely used, but its performance depends on two parameters: the size of feature vector dimensions and the number of p...