Handwritten Numeral Databases of Indian Scripts and Multistage Recognition of Mixed Numerals
Citations
175 citations
Cites background or methods from "Handwritten Numeral Databases of In..."
...The state of the art classifiers include statistical classifier such as modified quadratic discriminant function (MQDF), neural classifiers such as multi layer perceptron (MLP), radial basis function (RBF) classifier, polynomial classifier (PC), learning vector quantization (LVQ) and support vector machine (SVM) [5]....
[...]
...In [5], the wavelet filter is applied three times, and the chain code histogram feature is extracted from each of the detailed image components DL/L (k) , k = 1, 2, 3....
[...]
...Ujjwal and Chaudhuri [5] presented a multistage cascaded recognition scheme using wavelet based multi resolution representations and MLP classifiers for the recognition of mixed handwritten numerals Bengla, Devanagari and English....
[...]
159 citations
Cites background or methods from "Handwritten Numeral Databases of In..."
...Pal and Chaudhuri [12] and [99] also proposed a suffix- and prefix-based error correction technique, which can take care of different inflectional languages....
[...]
...To get an idea about the occurrence frequency of different Devanagari characters, Chaudhuri and Pal [5] provided the occurrence statistics of 20 frequent characters in Devanagari script, as shown in Table I, based on a study of three million words....
[...]
...An approach based on the detection of “shirorekha” is proposed by Chaudhuri and Pal [13] with the assumption that the skew of such header lines show the skew of the whole document....
[...]
...Bhattacharya and Chaudhuri [2] use a distinct MLP classifier at each stage of their recognition scheme for handwritten numerals....
[...]
...Bhattacharya and Chaudhuri [2] use a distinct MLP classifier at each stage of their recognition...
[...]
139 citations
Cites background or methods from "Handwritten Numeral Databases of In..."
...multilayer perceptron classifier gave better accuracy on Devanagri, and Bangla numerals [25], 140] but gave...
[...]
...Another research carried out on Hindi numerals [25] used a relatively large dataset of 22,556 isolated numeral samples of Devanagari and 23,392 samples of Bangla scripts....
[...]
135 citations
Cites methods from "Handwritten Numeral Databases of In..."
...KEYWORDS Handwritten character recognition, Image processing, Feature extraction, feed forward neural networks....
[...]
130 citations
References
14 citations
Additional excerpts
...Ç...
[...]
13 citations
Additional excerpts
...Ç...
[...]
11 citations
9 citations
"Handwritten Numeral Databases of In..." refers background in this paper
...Handwritten numeral samples from the two databases (10 samples per class are shown)....
[...]