A segmentation method for touching Japanese handwritten characters based on connecting condition of lines

Yamaguchi, Tomoharu; Yoshikawa, Tomohiro; Shinogi, Tsuyoshi; Tsuruoka, Shuichi; Teramoto, M.

doi:10.1109/icdar.2001.953905

Cited by 15 publications

(11 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Th1 is set to 1.0 so that touching parts between adjacent characters can be cut. Although projection analysis is a very simple segmentation method, the result can still serve as a guidepost [2,3].…”

Section: Character Segmentationmentioning

confidence: 99%

“…(4) Sort the word candidate reliabilities based on new reliabilities obtained by (3). Figure 13 illustrates the combination process.…”

Section: Algorithmmentioning

confidence: 99%

“…Segmentation and recognition of Japanese handwritten words is therefore a very difficult problem. Though several segmentation methods for handwritten Japanese words have been proposed [1]- [3], these methods are not always effective especially when adjacent characters touch at multiple points or overlap heavily. In particular, when a writing box is small, heavy touching appears to occur frequently.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Accuracy improvement for handwritten Japanese word recognition by combination of character and word recognizer

Hotta

Takebe

Suwa

et al. 2005

Eighth International Conference on Document Analysis and Recognition (ICDAR'05)

View full text Add to dashboard Cite

This paper proposes a combination method of character recognizer (CR) and word recognizer (WR) for Japanese handwritten words. CR is composed of character segmentation, isolated character recognition, and postprocessing. On the other hand, WR recognizes word images holistically based on a given word lexicon. These methods have been used as key modules in handwritten address recognition but have not been compared quantitatively up to now. In this paper, CR and WR are first empirically compared with each other using synthesized words generated from character images. Based on the comparison, a combination method is then proposed. Experimental results show that the combination approach can achieve better recognition performance than the other two methods.

show abstract

Section: Character Segmentationmentioning

confidence: 99%

“…(4) Sort the word candidate reliabilities based on new reliabilities obtained by (3). Figure 13 illustrates the combination process.…”

Section: Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Accuracy improvement for handwritten Japanese word recognition by combination of character and word recognizer

Hotta

Takebe

Suwa

et al. 2005

Eighth International Conference on Document Analysis and Recognition (ICDAR'05)

View full text Add to dashboard Cite

show abstract

“…There are two primary approaches to the segmentation of touching characters, recognition-free and recognition-based. Recognitionfree segmentation techniques use contour, skeleton and projection profile analysis [2][3][4][5][6][7][8][9][10] and use only structural information. These empirical methods may efficiently address some touching problems but may not be robust enough to handle a lot of variation or uncertainty.…”

Section: Introductionmentioning

confidence: 99%

Template Based Segmentation of Touching Components in Handwritten Text Lines

Kang

Doermann

2011

2011 International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

In this paper, we present a template based approach to the segmentation of touching components in handwritten text lines. Local patches around touching components are identified and a dictionary is created consisting of template patches together with their correct segmentations. We use two shape context based methods to compute similarity between input patches and dictionary templates to find the best match. The template's known segmentation is then transformed to segment the input patch. Experiments are carried on a dataset of touching text lines.

show abstract

“…They prune the touching-point candidates by projection analysis and select the appropriate ones based on the configurations around each candidate point. Some restrictions on the number of touching points are introduced to decrease the candidates [18]. However, these last two proposals are not combined with recognition.…”

Section: Introductionmentioning

confidence: 99%

A Segmentation Method of Single- and Multiple-Touching Characters in Offline Handwritten Japanese Text Recognition

Nguyen

Nakagawa

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis paper presents a method to segment single-and multiple-touching characters in offline handwritten Japanese text recognition with practical speed. Distortions due to handwriting and a mix of complex Chinese characters with simple phonetic and alphanumeric characters leave optical handwritten text recognition (OHTR) for Japanese still far from perfection. Segmentation of characters, which touch neighbors on multiple points, is a serious unsolved problem. Therefore, we propose a method to segment them which is made in two steps: coarse segmentation and fine segmentation. The coarse segmentation employs vertical projection, stroke-width estimation while the fine segmentation takes a graphbased approach for thinned text images, which employs a new bridge finding process and Voronoi diagrams with two improvements. Unlike previous methods, it locates character centers and seeks segmentation candidates between them. It draws vertical lines explicitly at estimated character centers in order to prevent vertically unconnected components from being left behind in the bridge finding. Multiple candidates of separation are produced by removing touching points combinatorially. SVM is applied to discard improbable segmentation boundaries. Then, ambiguities are finally solved by the text recognition employing linguistic context and geometric context to recognize segmented characters. The results of our experiments show that the proposed method can segment not only single-touching characters but also multiple-touching characters, and each component in our proposed method contributes to the improvement of segmentation and recognition rates.

show abstract

A segmentation method for touching Japanese handwritten characters based on connecting condition of lines

Cited by 15 publications

References 2 publications

Accuracy improvement for handwritten Japanese word recognition by combination of character and word recognizer

Accuracy improvement for handwritten Japanese word recognition by combination of character and word recognizer

Template Based Segmentation of Touching Components in Handwritten Text Lines

A Segmentation Method of Single- and Multiple-Touching Characters in Offline Handwritten Japanese Text Recognition

Contact Info

Product

Resources

About