Handwritten Arabic Numeral Recognition using a Multi Layer Perceptron
Citations
93 citations
Cites background or methods from "Handwritten Arabic Numeral Recognit..."
...First, they introduced two changes to the MLP-based model [14]: the use of rectified linear unit (ReLU) as the activation of each neuron in input layer and hidden layer and the softmax function in the outer classifying layer....
[...]
...[14] developed a set of 88 features representing samples of handwritten Arabic numerals....
[...]
...This is better than the performance of models presented in [8] and [14], where they achieved accuracy values of 93....
[...]
82 citations
Cites background or methods from "Handwritten Arabic Numeral Recognit..."
...that has affected the method in [1], by applying dropout regularization....
[...]
...[1] used a pre selected 88 features to feed into the MLP network, however we did not pre-select any features or reduce them....
[...]
...[1] have devised a novel method for Arabic handwritten digit recognition with help of a multi layer perceptron (MLP) which can bring significant accuracy to the...
[...]
...TABLE I PERFORMANCE COMPARISON OF PROPOSED METHODS AND METHOD DESCRIBED IN [1]...
[...]
...We also propose a modification of the method described in [1], where our method scores identical accuracy as that of [1], with the value of 93....
[...]
75 citations
48 citations
29 citations
Cites result from "Handwritten Arabic Numeral Recognit..."
...The drawback of their paper was that they compared their work with a single paper [48] published in 2010, which may seem an old paper....
[...]
References
29,130 citations
2,653 citations
"Handwritten Arabic Numeral Recognit..." refers background in this paper
...The past work on OCR of handwritten alphabets and numerals has mostly found to concentrate on Roman script[3] related to English and some other European languages, and scripts related to Asian languages like Chinese [2], Korean, Japanese....
[...]
319 citations
76 citations
51 citations
"Handwritten Arabic Numeral Recognit..." refers background in this paper
...The past work on OCR of handwritten alphabets and numerals has mostly found to concentrate on Roman script[3] related to English and some other European languages, and scripts related to Asian languages like Chinese [2], Korean, Japanese....
[...]