Persian Writer Identification Using Extended Gabor Filter

Helli, Behzad; Moghadam, Mohsen Ebrahimi

doi:10.1007/978-3-540-69812-8_57

Cited by 18 publications

(21 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A Persian handwritten identification system that was based on a new generation of Gabor filter that was called XGabor filter is proposed in 2008 [52]. Feature extraction was done using Gabor and XGabor filters; in the classification phase, weighted Euclidian distance (WED) classifier was used.…”

Section: Persianmentioning

confidence: 99%

A Survey on Writer Identification Schemes

Sreeraj¹,

Idicula²

2011

IJCA

View full text Add to dashboard Cite

This paper presents a survey of the literature on writer identification schemes and techniques up till date. The paper outlines an overview of the writer identification schemes mainly in Chinese, English, Arabic and Persian languages. Taxonomy of different features adopted for online and offline writer identification schemes is also drawn at. The feature extraction methods adopted for the schemes are discussed in length outlining the merits and demerits of the same. In automated writer identification, text independent and text dependent methods are available which is also discussed in this paper. An evaluation of writer identification schemes under multiple languages is also analyzed by comparing the recognition rate.

show abstract

Section: Persianmentioning

confidence: 99%

A Survey on Writer Identification Schemes

Sreeraj¹,

Idicula²

2011

IJCA

View full text Add to dashboard Cite

show abstract

“…A 2D XGabor filter is obtained by modulating a 2D circular sinusoid with 2D Gaussian [1]. Let xg(x, y, φ, r x , r y ) be the function defining a 2D XGabor filter centered at the origin with Φ as the spatial frequency and r x , r y as the horizontal and vertical ratios.…”

Section: Xgabor Filtermentioning

confidence: 99%

“…Generating the response for an image is done in the same manner with equation (2). XGabor filter models the curves in the image; therefore, by using it, most frequent curves in input image are detected [1]. In feature extraction phase, XGabor filter was used in 5 different ratios and each one of them were applied in 32*32, 64*64, 128*128 and 256*256 block sizes.…”

Section: Xgabor Filtermentioning

confidence: 99%

“…In recent systems, in order to avoid this problem, the input data has been normalized, so that the system may be more independent to the words of the text [1,2,7].…”

Section: Classification Criteriamentioning

confidence: 99%

“…English); for example, the proposed methods for English handwritten are not usable in Persian, because of special characteristics of Persian handwriting such as different styles in writing that has been explained in Ref. [1], There are different methods in writer identification in different languages. For example, a Gabor filter based method which uses the weighted Euclidian distance (WED) classifier after extracting the features have been proposed for Persian writer identification [7].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A writer identification method based on XGabor and LCS

Helli

Moghaddam

2009

IEICE Electron. Express

Self Cite

View full text Add to dashboard Cite

Writer identification is a popular research field in many languages such as English, Persian, Chinese, etc. The approaches of writer identification methods are dependent on the language because different languages letters have different pattern. In this paper, we have presented XGabor filter and proposed a language independent writer identification system. In the feature extraction phase of proposed method, Gabor and XGabor filters are used while in the classification phase, a new classification method is defined that is not based on any kind of distances among feature vectors. The proposed classifier uses the sequence similarity of the Sorted Order of Features (SOF). To measure this similarity, the Longest Common Subsequence (LCS) algorithm is employed. In simulation phase, two databases in different languages have been used. First one consisted of 100 people's Persian handwritings and second one had 30 people's English handwritings. The accuracy of the system was satisfactory in both of them.

show abstract