Research on on-line Uyghur character recognition technology based on center distance feature

Simayi, Wujiahemaiti; Ibrayim, Mayire; Tursun, Dilmurat; Hamdulla, Askar

doi:10.1109/isspit.2013.6781896

Cited by 9 publications

(5 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wujiahemaiti (2013) presented the center distance feature (CDF) with its three different implementations (CDF-2, CDF-4 and CDF-8) to extract the features of Uyghur characters [26]. The center distance feature combines the structural and statistical characteristic of characters and used evenly and unevenly grid division method.…”

Section: Structural Featuresmentioning

confidence: 99%

Survey on the Features for Recognition of on-line Handwritten Uyghur Characters

Ibrayim¹,

Hamdulla²,

Tursun³

et al. 2015

IJSIP

Self Cite

View full text Add to dashboard Cite

This survey attempts to provide a detailed overview of the previous work on Uyghur on-line handwritten character recognition technology and mainly focuses on investigating the feature extraction algorithms that have been presented or applied to Uyghur characters. Statistical, structural and combined-hybrid approaches for feature extraction technology for Uyghur characters are going to be explored. Besides the popular feature extraction methods which perhaps are granted to be taken into consideration for all letter kinds, the study on Uyghur handwritten recognition contributed new features and extraction algorithms for pattern recognition. Summarization on observing methods and extracted features from the published work and suggestions for further attempts would be valuable reference for the up-coming research activities on finding more efficient features.

show abstract

Section: Structural Featuresmentioning

confidence: 99%

Survey on the Features for Recognition of on-line Handwritten Uyghur Characters

Ibrayim¹,

Hamdulla²,

Tursun³

et al. 2015

IJSIP

Self Cite

View full text Add to dashboard Cite

show abstract

“…Wujiahemaiti (2013) presented the center distance feature (CDF) with its three different implementations (CDF-2, CDF-4 and CDF-8) to extract the features of Uyghur characters [17]. The center distance feature combines the structural and statistical characteristic of characters and used evenly and unevenly grid division method.…”

Section: Related Workmentioning

confidence: 99%

“…The center distance feature presented in reference [17] analyzes the characters by dividing the rectangular character shape into 32 grids. It describes a character by the distances from the gravitational centers of grid units to the gravitational center of character shape.…”

Section: Center Distance Feature-cdf With Its Three Different Implemementioning

confidence: 99%

“… we have to notice that there is one exceptional group including the characters with much and complex special symbols such as , , , ( 25~28, Table 2). In reference [17], experiments show that eight bins form of CDF is not very much favorable for these characters. Too much bins easily spoil the special symbols of characters and make backwards in recognition rate.…”

Section: Analysis On the Experimental Factsmentioning

confidence: 99%

See 1 more Smart Citation

Research on On-line Uyghur Handwritten Character Recognition Technology Based on Modified Center Distance Feature

Wujiahemaiti

Dilmurat²,

Ibrayim³

et al. 2014

IJSIP

Self Cite

View full text Add to dashboard Cite

Through the analysis on the unique characteristics of Uyghur characters, in order to further improve the recognition rate, this paper developed the Center Distance Feature (CDF) to its modified form which is named as Modified Center Distance Feature (MCDF). By combination with some low dimensional features including stroke number feature, additional part's location feature, shape feature, bottom-up and left-right density feature(BULR) in experiments, MCDF gifted robust recognition accuracy of 98.77% for the 32 isolated forms of Uyghur characters. MCDF increased the recognition accuracy by 4.51 points comparing with the result from the combination of CDF with the same low dimensional features mentioned above, which is 94.16%. This paper used the samples from 400 different volunteers. The recognition system is trained using 70 percent of 12800 samples from 400 different writers and tested on the remained 30 percent.

show abstract

“…After the founding of People's Republic China, the old Dai characters of xishuangbanna was improved and developed into New Tai Lue. Compared with the studies on Chinese characters [1], Uyghur [2,3] languages, the research of the New Tai Lue character recognition is relatively backward, and there are only a few studies on the recognition of New Tai Lue character. For example, Li et al [4] presented a printed New Tai Lue character recognition method based on the Back Propagation (BP) Neural Network.…”

Section: Introductionmentioning

confidence: 99%

Research on Character Recognition Technology of New Tai Lue Based on Gabor Feature and SVM

Zhang¹,

Yu²,

Li³

et al. 2019

dtcse

View full text Add to dashboard Cite

New Tai Lue script which is also known as Simplified Tai Lue, is an alphabet used to write the Tai Lü language used in Xishuangbanna of Yunnan Province in China. In this paper, we present a handwritten character recognition method of New Tai Lue by Support vector machine (SVM) based classifier on Gabor Features. First, some preprocessing approaches such as superfluous points removing, normalization, smoothing, resampling are applied to preprocess the handwritten character images of New Tai Lue. Second, a filter bank consisting of two-dimensional Gabor filters with various scales and orientations is created to extract features from these images. After that, the result images are processed by PCA to do dimension reduction. Finally, SVM is applied as the classifier to perform recognition task. Experimental results conducted on a database of 16200 characters show that the proposed method are effective.

show abstract

Research on on-line Uyghur character recognition technology based on center distance feature

Cited by 9 publications

References 1 publication

Survey on the Features for Recognition of on-line Handwritten Uyghur Characters

Survey on the Features for Recognition of on-line Handwritten Uyghur Characters

Research on On-line Uyghur Handwritten Character Recognition Technology Based on Modified Center Distance Feature

Research on Character Recognition Technology of New Tai Lue Based on Gabor Feature and SVM

Contact Info

Product

Resources

About