Diagonal Based Feature Extraction for Handwritten Alphabets Recognition System Using Neural Network

Pradeep, J.; Srinivasan, E.; Himavathi, S.

doi:10.5121/ijcsit.2011.3103

Cited by 81 publications

(30 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The weights are updated as follows [9], [10], [11]. Initially the weights of the hidden to output layer are updated.…”

Section: Weight Updatementioning

confidence: 99%

An Approach to Handwriting Recognition using Back-Propagation Neural Network

Chakraborty¹,

Sarkar²

2013

IJCA

View full text Add to dashboard Cite

Handwriting Recognition is an important topic in Computer Science. In this paper a procedure is presented to identify characters that are drawn using stylus with the help of BackPropagation Neural Network. The paper describes the entire procedure from feature extraction to the training of the network. Feature extraction includes pixel grabbing, finding character bounds and down-sampling of the image to 7*5 pixel size. The neural network is trained by supervised learning which includes error calculation using backpropagation approach. After the training is completed the network is ready to identify characters that are drawn in the computer. This same approach given in this paper can be extended to recognize handwritten documents and also for recognizing multilingual characters.

show abstract

“…The weights are updated as follows [9], [10], [11]. Initially the weights of the hidden to output layer are updated.…”

Section: Weight Updatementioning

confidence: 99%

An Approach to Handwriting Recognition using Back-Propagation Neural Network

Chakraborty¹,

Sarkar²

2013

IJCA

View full text Add to dashboard Cite

show abstract

“…These 14 diagonal features are averaged to form a single feature value which is to be placed in the corresponding zone. Finally, for each character image 24 features were extracted [27]. Figure 3 gives the idea of this approach.…”

Section: Diagonal Distance Approachmentioning

confidence: 99%

Off-Line Handwritten Character Recognition System Using Support Vector Machine

Katiyar¹

2017

AJNNA

View full text Add to dashboard Cite

Selection of classifiers and feature extraction methods has a prime role in achieving best possible classification accuracy in character recognition system. Issues of character recognition system related to choice of classifiers and feature extraction methods can be resolved through these objectives. In this proposed work an efficient Support Vector Machine based off-line handwritten character recognition system has been developed. The experiments have been performed using well known standard database acquired from CEDAR, also seven different approaches of feature extraction techniques have been proposed to construct the final feature vector. It is evident from the experimental results that the performance of Support Vector Machine outperforms other state of art techniques reported in literature.

show abstract

“…The binary image fitted in a matrix is divided into nine square sub-matrices of size 6x6 as shown in Figure ( For made the feature extraction simple method for implementation, we can converted the one feature value of each sub-matrix in matrix form into a real number by the equation (5), such that the Feature value of sub-matrix, is computed by this equation. The total number of 1s cells in a sub-matrix is divided by the total number of cells in that submatrix [10]. The normalized feature value of sub-matrix is computed by dividing the sum distances of 1s cells from the sum distances of all cells in that sub-matrix.…”

Section: ) Feature Extractionmentioning

confidence: 99%

High Accuracy Arabic Handwritten Characters Recognition Using Error Back Propagation Artificial Neural Networks

Abed¹,

Alasad²

2015

ijacsa

View full text Add to dashboard Cite

Abstract-This manuscript considers a new architecture to handwritten characters recognition based on simulation of the behavior of one type of artificial neural network, called the Error Back Propagation Artificial Neural Network (EBPANN). We present an overview of our neural network to be optimized and tested on 12 offline isolated Arabic handwritten characters ‫،ش،ط،غ،ف،ك،م،و،ي(‬ ‫)ا,ت,ج،ذ‬ because the similarity of some Arabic characters and the location of the points in the character. Accuracy of 93.61% is achieved using EBPANN which is the highest accuracy achieved during Offline Handwritten Arabic Character Recognition. It is noted that the EBPANN in general generates an optimized comparison between the input samples and database samples which improves the final recognition rate. Experimental results show that the EBPANN is convergent and more accurate in solutions that minimize the error recognition rate.

show abstract

Diagonal Based Feature Extraction for Handwritten Alphabets Recognition System Using Neural Network

Abstract: ABSTRACT

Cited by 81 publications

References 13 publications

An Approach to Handwriting Recognition using Back-Propagation Neural Network

An Approach to Handwriting Recognition using Back-Propagation Neural Network

Off-Line Handwritten Character Recognition System Using Support Vector Machine

High Accuracy Arabic Handwritten Characters Recognition Using Error Back Propagation Artificial Neural Networks

Contact Info

Product

Resources

About