Segmentation-based recognition of handwritten touching pairs of digits using structural features

Kim, Kye Kyung; Kim, Jin Ho; Suen, Ching Y.

doi:10.1016/s0167-8655(01)00114-3

Cited by 39 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Level set methods are proposed to separate the printed, or handwritten text regions from the background using partial derivatives and an external vector field in an iterative process in [135], [136]. Segmentation-based (Explicit) solutions have solved the touched characters problems [137], [138] and Recognitionbased (implicit) techniques [139], [140].…”

Section: Game Theorymentioning

confidence: 99%

“…Segmentation-based (Explicit) [137], [138] Touched characters Recognition-based (implicit) [139], [140] Script-specific: Hist [154], CJK [155]- [157], Arabic: [150], [151], Brahmi [147], [154] that can be processed by machine learning or deep learning algorithms for solving classification problems. It preserves the information in the original input dataset and maps those features on a lower dimension.…”

Section: Touched Charactersmentioning

confidence: 99%

See 1 more Smart Citation

Document Analysis and Recognition: A survey

NIGAM¹,

Verma²,

Nagabhushan³

2023

Preprint

View full text Add to dashboard Cite

<p>The journey of research for Document Analysis and Recognition (DAR) started with the problem of automatic character recognition. Today, it has covered a vast span of recognition tasks such as text recognition, script identification, writer identification, word spotting, signature verification etc., in scripts like Roman, Arabic, Chinese, Japanese, Brahmi etc. Extensive advancements in deep learning techniques have achieved state-of-the-art results for various DAR tasks. This work explores the challenges from different perspectives and reviews the techniques for online/offline and printed/handwritten DAR tasks. We examine the research works with the view of script-related challenges. Various datasets for DAR are categorized into historic, printed and handwritten datasets. We present a comprehensive survey of challenges, techniques, datasets, evaluation metrics, script-related perspectives and potential future directions for DAR.</p>

show abstract

Section: Game Theorymentioning

confidence: 99%

Section: Touched Charactersmentioning

confidence: 99%

Document Analysis and Recognition: A survey

NIGAM¹,

Verma²,

Nagabhushan³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The segmentation-recognition with veri¯cation is usually named segmentation-veri¯cation. 10,11 Generally, algorithms based on the segmentation-recognition approach are faster than segmentation-veri¯cation since a number of separation attempts are smaller.…”

Section: Introductionmentioning

confidence: 99%

“…Kyung et al 11 proposed using structural features of contours to generate multiple hypotheses. These hypotheses are based on an analysis of the ligature and the characteristics of candidate break points, which are veri¯ed using a MultiLayer Perceptron numeral classi¯er.…”

Section: Introductionmentioning

confidence: 99%

SVM-Based Segmentation-Verification of Handwritten Connected Digits Using the Oriented Sliding Window

Gattal

Chibani

2015

Int. J. Comp. Intel. Appl.

View full text Add to dashboard Cite

We propose in this paper a system to recognize handwritten digit strings, which constitutes a di±cult task because of overlapping and/or joining of adjacent digits. To resolve this problem, we use a segmentation-veri¯cation of handwritten connected digits based conjointly on the oriented sliding window and support vector machine (SVM) classi¯ers. The proposed approach allows separating adjacent digits according the connection con¯guration by¯nding at the same time the interconnection points between adjacent digits and the cutting path. SVM-based segmentation-veri¯cation using the global decision module allows the rejection or acceptance of the processed image. Experimental results conducted on a large synthetic database of handwritten digits show the e®ective use of the oriented sliding window for segmentationveri¯cation.

show abstract