Word-Level Optical Font Recognition Using Typographical Features

Kim, Soo-Hyung; Kwag, H.K.; Suen, Ching Y.

doi:10.1142/s0218001404003307

Cited by 5 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By applying Bayes' formula and assuming equal occurrence probabilities for F i , rule (4) can be converted to assign x to F i if for all j i (5) where…”

Section: Font Recognitionmentioning

confidence: 99%

“…To recognize the font of the input text image, the extracted stroke templates are compared with the font database and classified according to rule (5). A set of variables named VoteCount i , i = 1, 2, …, n, is used to count the templates that each candidate font wins.…”

Section: Font Recognitionmentioning

confidence: 99%

“…serif vs. sans-serif and upright vs. slanted), which is based on analysis of the global page properties and recognition results of short words such as 'a', 'it', and 'of'. The systems of Zramdini et al [4] and Kim et al [5] accomplished font recognition via character-level typographical features. Chaudhuri et al [6] devised several algorithms to detect italic, bold, and all-capital words within English-document images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Linguistic Optical Font Recognition Using Stroke Templates

Sun

2006

18th International Conference on Pattern Recognition (ICPR'06)

View full text Add to dashboard Cite

One of the essential distinctions between different fonts is their stroke shape. A method is presented to automatically extract representative stroke templates from a text image, which contains characters of the same typeface. The collected stroke templates are classified and saved to a font database. To recognize an unknown font for an input text image, a Bayes decision rule is used to determine which font entrant in the database provides the best matching to the unknown font. The experiment demonstrates that this approach can distinguish between Chinese and English fonts without the prior information of their script. Another advantage is that it can learn a new font very quickly. Forty fonts (twenty English and twenty Chinese) are used in our experiment. An average recognition accuracy of 97 percent can be achieved in the present system.

show abstract

“…By applying Bayes' formula and assuming equal occurrence probabilities for F i , rule (4) can be converted to assign x to F i if for all j i (5) where…”

Section: Font Recognitionmentioning

confidence: 99%

Section: Font Recognitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Linguistic Optical Font Recognition Using Stroke Templates

Sun

2006

18th International Conference on Pattern Recognition (ICPR'06)

View full text Add to dashboard Cite

show abstract

“…Applying an OCR to a machine-printed text with known font causes more accurate result than when the font of the input text is unknown [1]. Several works have been done in optical font recognition in various languages such as Latin [2][3][4][5][6][7][8][9][10], Chinese [6,[11][12][13], Arabic [14][15][16], and Farsi [17][18][19][20]. In all of these works, the font of the whole text in a document image was assumed to be uniform.…”

Section: Introductionmentioning

confidence: 99%

“…Typographical feature-based algorithms [3][4][5]7] extract some features, like character skews, betweencharacters and between-words space widths, and projections in upper, center and lower zones of the line from the printed texts. The main drawback of these approaches is that they require noise-free and highquality text images [18].…”

Section: Introductionmentioning

confidence: 99%

Farsi Font Recognition Based On The Fonts Of Text Samples Extracted By Som

Ziaratban¹,

Bagheri²

2015

J. Math. Computer Sci.

View full text Add to dashboard Cite

A Farsi font recognition algorithm based on the fonts of some frequent text samples is proposed. Some features are extracted from the connected components of a text image. The feature vectors are clustered by using a Self-Organizing Map (SOM) clustering method. The clusters with more members determine the most frequent connected components (MFCCs). A number of members of these big clusters are extracted from the input image. This procedure is applied to both training and test images. Since the frequent samples in different Farsi texts are very similar, it can be guaranteed that a large number of samples of the detected MFCCs for a test image surely are in the extracted training samples set. The font type and font style of the extracted test samples are recognized by matching between them and the training samples. The most frequent recognized font of the extracted samples is considered as the font of the input text. To achieve a more accurate algorithm with lower complexity, the font size is determined in the second phase after the phase of the font type and style recognition. Using a lexicon reduction procedure reduces the complexities and processing time. The font size estimation is carried out based on the size of a particular MFCC in a text image. Experiments show that the proposed method outperforms other font recognition methods.

show abstract