Feature-based neural wavelet optical character recognition system

Iftekharuddin, Khan M.; Schechinger, Terry D.; Jemili, Kanaan; Karim, Mohammad A.

doi:10.1117/12.213654

Cited by 8 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature, there are techniques to analyze textures (in general texture not text [25], [26], [27] and [28]): Gabor filters [9], [11], co-occurrence matrices [12], [13], [29], [31], principal component analysis [14], [10], low-order statistical moments (mean value, standard deviation, correlation, etc.) [4], [14], [15], [24], [30], high-order statistical moments [16], [17], [15] and analysis with wavelet transforms [18], [19]. A method is given in reference [19] for the recognition of characters, but the recognition of the type of fonts is disregarded.…”

Section: Feature Extractionmentioning

confidence: 99%

“…[4], [14], [15], [24], [30], high-order statistical moments [16], [17], [15] and analysis with wavelet transforms [18], [19]. A method is given in reference [19] for the recognition of characters, but the recognition of the type of fonts is disregarded. In this project, statistical moments were used since it has been found that they have a very good performance with non-structured random textures [16], [17], [1], [15].…”

Section: Feature Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Font Clustering Using Stochastic Versio of the EM Algorithm and Global Texture Analysis

Avilés‐Cruz

Villegas

Arechiga-Martínez

et al. 2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. An Unsupervised Font clustering technique is proposed in this work. The new approach is based on global texture analysis, using high order statistic features, Gaussian classifier and a stochastic version of the EM algorithm. The font recognition is performed by taking the document as a simple image, where one or several types of fonts are present. The identification is not performed letter by letter as with conventional approaches. In the proposed method a window analysis is employed to obtain the features of the document, using fourth and third order moments. The new technique does not involve a study of local typography; therefore, it is content independent. A detailed study was performed with 8 types of fonts commonly used in the Spanish language. Each type of font can have four styles that lead, to 32 font combinations. The font recognition with clean images is 100% accurate.

show abstract