Multi-font Numeral Recognition without Thinning based on Directional Density of Pixels

Dhandra, B.V.; Malemath, V. S.; Mallikarjun, H M; Hegadi, Ravindra S.

doi:10.1109/icdim.2007.369346

Cited by 13 publications

(14 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dhandra et. al [9] proposed a method based on directional density feature which is thinning free, independent of size, and font styles of the numeral for printed English numerals. However, all these recognition schemes are script dependent, and their performance good for a languages it is considered.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

"Kannada, Telugu and Devanagari Handwritten Numeral Recognition with Probabilistic Neural Network: A Script Independent Approach"

Dhandra¹,

Benne²,

Hangarge³

2011

IJCA

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

“…We have extracted 13 potential feature set includes Directional density estimation [9], Water Reservoir principle based features [10], Maximum profile distances and fill hole density. The proposed method address the extension of Dhandra et.al [19] for Script Independent Numeral Recognition based on Structural features.…”

Section: Introductionmentioning

confidence: 99%

"Kannada, Telugu and Devanagari Handwritten Numeral Recognition with Probabilistic Neural Network: A Script Independent Approach"

Dhandra¹,

Benne²,

Hangarge³

2011

IJCA

View full text Add to dashboard Cite

“…This measure is a useful tool for assessing the similarity of time series with the same length but with various amplitudes. Formula for comparison between two vectors of the same size P and Q based on Jensen similarity measure is expressed by (1). The output of this formula is between 0 and 1.…”

Section: Similarity Measurementioning

confidence: 99%

“…Although recognition of printed/handwritten numerals is studied topic and many techniques of recognition of both machine and hand printed character are available in the literature but not much work has been reported on the recognition of multi-font numerals, in recent times [1]. Digits recognition has been a focus of many studies depending on the type of features extracted and the different ways of extracting them among different languages.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recognition of Multi-font English Numerals using SOM Neural Network

Hassanpour¹,

Samadiani²

2014

IJCA

View full text Add to dashboard Cite

In this paper a new scheme is proposed for off-line recognition of multi-font numeral, using neural networks. Recognition of numerals has been a research area for many years because of its various applications. But there wasn't much research done for recognition of multi-font numerals. The approaches proposed so far, suffer from larger computation time and training because they must have a set of training samples per each font. They can be extended to recognize many more fonts but the accuracy decreases rapidly. So as to eliminate these drawbacks, in this paper, a method is presented which recognizes 30 different fonts of different sizes varying from size 10 to 28, with an accuracy of 99.55% on a database of 2000 numeral images. The purpose of this study is to provide a new method to recognize digits based on neural network that can identify the same symbols after training without limitation on the type of the font. In the proposed method, a high accuracy rate is achieved in recognizing digits by extracting the appropriate features without the need for complex neural network architecture. This method uses a self-organizing map (SOM) neural network to measure similarity between the features of digits and the features of the indicators associated with the digits from 0 to 9 obtained in the training stage. In this method, one sample is used for each digit to train the network. So, the proposed method can be used to recognize typed letters without limitation on fonts.

show abstract

Online time numeral recognition from monochrome video sequence

Sahani

Das

2013

2013 Ieee Conference on Information and Communication Technologies

View full text Add to dashboard Cite

Multi-font Numeral Recognition without Thinning based on Directional Density of Pixels

Cited by 13 publications

References 8 publications

"Kannada, Telugu and Devanagari Handwritten Numeral Recognition with Probabilistic Neural Network: A Script Independent Approach"

"Kannada, Telugu and Devanagari Handwritten Numeral Recognition with Probabilistic Neural Network: A Script Independent Approach"

Recognition of Multi-font English Numerals using SOM Neural Network

Online time numeral recognition from monochrome video sequence

Contact Info

Product

Resources

About