A system for machine-written and hand-written character distinction

Kuhnke, K.; Simoncini, L.; Kovács-V, Zs.M.

doi:10.1109/icdar.1995.602025

Cited by 48 publications

(21 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The methods working at character level analyze the regularity of the writing. [43] analyzes the straightness and the symmetry of Latin printed characters whereas [44] bases its approach on the fluctuations caused by the handwriting, transforming Chinese characters into the frequency domain. Both approaches use neural networks to take the decision.…”

Section: Script Identificationmentioning

confidence: 99%

“…The second approach obtains an average classification accuracy of 91.1% and 94.07% (depending on the system configuration) for the writing type identification on Arabic and Latin documents of the MAURDOR dataset. Regarding the approaches working at the character level, [43] achieves an accuracy of 78.5% on the NIST dataset for handwritten characters and on a private dataset for printed characters.…”

Section: Script Identificationmentioning

confidence: 99%

See 1 more Smart Citation

Language Identification in Document Images

Barlas¹,

Hebert²,

Chatelain³

et al. 2016

View full text Add to dashboard Cite

This paper presents a system dedicated to automatic language identification of text regions in heterogeneous and complex documents. This system is able to process documents with mixed printed and handwritten text and various layouts. To handle such a problem, we propose a system that performs the following sub-tasks: writing type identification (printed/handwritten), script identification and language identification. The methods for the writing type recognition and the script discrimination are based on the analysis of the connected components while the language identification approach relies on a statistical text analysis, which requires a recognition engine. We evaluate the system on a new public dataset and present detailed results on the three tasks. Our system outperforms the Google plug-in evaluated on the ground-truth transcriptions of the same dataset.

show abstract

Section: Script Identificationmentioning

confidence: 99%

Section: Script Identificationmentioning

confidence: 99%

Language Identification in Document Images

Barlas¹,

Hebert²,

Chatelain³

et al. 2016

View full text Add to dashboard Cite

show abstract

“…The classification is typically performed at the text line [19,20,21,22], word [23], or character level [24,71]. At the line level, machine printed text lines are typically arranged regularly with a straight baseline, while handwritten text lines are irregular with a varying baseline.…”

Section: Related Workmentioning

confidence: 99%

“…There are two tasks in known form processing: form identification and form registration. These two tasks can be solved in one unified frame- Handwriting/machine printed text discrimination can be performed at different levels, such as the text line [19,20,21,22], word [23], or character level [24,25].…”

Section: Summary and Future Workmentioning

confidence: 99%

“…Although less information is available at the character level, humans can still identify the handwritten and machine printed characters easily, inspiring researchers to pursue classification at the character level. Kuhnke [24] proposed a neural network-based approach with straightness and symmetry as features. Zheng et al [71] used run-length histogram features to identify handwritten and printed Chinese characters and achieved promising results.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Handwriting Identification, Matching, and Indexing in Noisy Document Images

Zheng¹

2006

View full text Add to dashboard Cite

Throughout history, handwriting has been the primary means of recording information that is persevered across both time and space. With the coming of the electronic document era, we are challenged with making an enormous amount of handwritten documents available for electronic access. Though many handwritten documents contain only handwriting, now, more are mixed with printed text, noise, and background patterns. The mixture of handwriting with other components presents a great challenge for making an original document electronically accessible.Many handwritten documents come together with a special background pattern, rule lines, which are printed on the paper to guide writing. After digitization, rule lines will touch text and cause problems for further document image analysis if they are not detected and removed. In this dissertation, we present a rule line detection algorithm based on hidden Markov model (HMM) decoding, achieving both high detection accuracy and a low false alarm rate. After detection, line removal is performed by line width thresholding.Handwriting often mixes with printed text, such as signatures and annotations on a business letter. Handwriting in a printed document often indicates corrections, additions, or other supplemental information that should be treated differently from the main content. The data set we are processing is noisy, which makes the problem more challenging. In this dissertation, we first segment the document at a suitable level, and then classify each segmented block as machine printed text, handwriting, or noise. Markov random field (MRF) based post-processing is exploited to refine the classification results.The identified handwriting may be further analyzed. In this dissertation, we propose a novel point-pattern based handwriting matching technique and apply it for handwriting synthesis and retrieval. We formulate point matching as an optimization problem trying to preserve the local neighborhood structures. After establishing the correspondence between two handwriting samples, we warp one sample toward the other using the thin plate spline (TPS) deformation model to synthesize new handwriting samples. We also apply our matching algorithm for handwriting retrieval since it is much easier to define robust features based on the matching

show abstract

Optical Font Recognition of Chinese Characters Based on Texture Features

Tian

2006

Advances in Machine Learning and Cybernetics

View full text Add to dashboard Cite

A system for machine-written and hand-written character distinction

Cited by 48 publications

References 4 publications

Language Identification in Document Images

Language Identification in Document Images

Handwriting Identification, Matching, and Indexing in Noisy Document Images

Optical Font Recognition of Chinese Characters Based on Texture Features

Contact Info

Product

Resources

About