Scribd Logo
Upload

Welcome to Scribd!

  • 41 views

    Optical Character Recognition Using Artificial Neural Network

    Uploaded by

    Farhad Ahmed Chirley
    This document summarizes an article about using artificial neural networks for optical character recognition. It discusses preprocessing steps like segmentation, feature extraction, and classification. Neural networks can be trained on extracted features from images to classify characters. The document outlines the training and testing methodology, including preprocessing, feature extraction, and classification steps. It also discusses implementing an automatic character recognition system in MATLAB using a neural network approach.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Optical Character Recognition Using Artificial Neural Network

    Uploaded by

    Farhad Ahmed Chirley
    41 views4 pages
    This document summarizes an article about using artificial neural networks for optical character recognition. It discusses preprocessing steps like segmentation, feature extraction, and classification. Neural networks can be trained on extracted features from images to classify characters. The document outlines the training and testing methodology, including preprocessing, feature extraction, and classification steps. It also discusses implementing an automatic character recognition system in MATLAB using a neural network approach.

    Original Description:

    dbdrbnrnnernewnwnnrnrnwrewergwfwqrfqwreqw

    Original Title

    786-1424671582_2

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document summarizes an article about using artificial neural networks for optical character recognition. It discusses preprocessing steps like segmentation, feature extraction, and classification. Neural networks can be trained on extracted features from images to classify characters. The document outlines the training and testing methodology, including preprocessing, feature extraction, and classification steps. It also discusses implementing an automatic character recognition system in MATLAB using a neural network approach.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    41 views4 pages

    Optical Character Recognition Using Artificial Neural Network

    Uploaded by

    Farhad Ahmed Chirley
    This document summarizes an article about using artificial neural networks for optical character recognition. It discusses preprocessing steps like segmentation, feature extraction, and classification. Neural networks can be trained on extracted features from images to classify characters. The document outlines the training and testing methodology, including preprocessing, feature extraction, and classification steps. It also discusses implementing an automatic character recognition system in MATLAB using a neural network approach.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 4

    International Journal of Engineering Research and General Science Volume 3, Issue 1, January-February, 2015

    ISSN 2091-2730

    Optical Character Recognition Using Artificial Neural Network


    Dr.Mrs.V.V.Patil 1, Rajharsh Vishnu Sanap 2 , Rohini Babanrao Kharate 3 .
    1, 2

    Dept Of Electronics Engg , Dr J.J.Magdum College Of Engg , Jaysingpur , India.

    3 Dept

    Of Electronics & Telecom. Engg ,TPCTs College Of Engg , Osmanabad , India.

    vvpatil2429@gmail.com , rvssanap@gmail.com , kharaterohini@gmail.com


    Abstract -This paper examines the use of neural networks to accomplish optical character recognition.Recognition of Handwritten
    text has been one of the active and challenging areas of research in the field of image processing and pattern recognition [4].The
    whole process of recognition includes two phases segmentation of characters intoline, word and characters and then recognition
    through feedforward neural network. Basically an offline handwritten alphabetical character recognition system using multilayer feed
    forward neural network has been described in our work. a method of feature extraction is introduced for extracting the features of the
    handwritten alphabets and then we use the data to train the artificial neural network.It contributes immensely to the advancement of an
    automation process and can improve the interface between man and machine in numerous applications [7].

    Keywords - Character Recognition, Training, Feature Extraction, Image Processing, ANN,OCR, classification.
    INTRODUCTION
    Character recognition, usually abbreviated to optical character recognition or shortened OCR, is the mechanical or electronic
    translation of images of handwritten, typewritten or printed text (usually captured by a scanner) into machine editable text [1]. It is a
    field of research in pattern recognition, artificial intelligence and machine vision. Though academic research in the field continues, the
    focus on character recognition has shifted to implementation of proven techniques. For many document-input tasks, character
    recognition is the most cost-effective and speedy method available. And each year, the technology frees acres of storage space once
    given over to file cabinets and boxes full of paper documents [10].
    The goal of Optical Character Recognition (OCR) is to classify optical patterns (often contained
    in a digital image) corresponding to alphanumeric or other characters. The process of OCR involves several steps including
    segmentation, feature extraction, and classification [12].Theneural network technology can be usedto analyze the stroke edge, the line
    of discontinuity between the text characters, and the background [3]. Allowing for irregularities of printed ink on paper, each
    algorithm averages the light and dark along the side of a stroke, matches it to known characters and makes a best guess as to which
    character it is. The OCR software then averages or polls the results from all the algorithms to obtain a single reading [2]. Neural
    networks can be used, if we have a suitable dataset for training and learning purposes. Datasets are one of the most important things
    when constructing new neural network.

    METHODOLOGY
    To solve the defined handwritten character recognition problem of classification we used MATLAB computation software with
    Neural Network Toolbox and Image Processing Toolbox add-on.In Classification Processthere are two steps in building a
    classifiertraining and testing. These steps can be broken down further into substeps.

    TRAINING
    a. Pre-processing Processes the data so it is in a suitable form .
    b. Feature extraction Reduce the amount of data by extracting relevant
    informationUsually results in a vector of scalar values. (We also need to
    normalize the features for distance measurements)
    c. Model Estimation from the finite set of feature vectors, need to estimate a model
    (usually statistical) for each class of the training data.

    TESTING
    a. Pre-processing
    73

    www.ijergs.org

    International Journal of Engineering Research and General Science Volume 3, Issue 1, January-February, 2015
    ISSN 2091-2730

    b. Feature extraction (both same as above)


    c. Classification Compare feature vectors to the various models and find the
    closest match. One can use a distance measure.

    Fig 1. Training And Testing Of Data

    AUTOMATIC IMAGE PREPROCESSING


    The image is first being converted to grayscale image follow by the threshing technique, which make the image become binary image.
    The binary image is then sent through connectivity test in order to check for the maximum connected component, which is, the box of
    the form [6]. After locating the box, the individual characters are then cropped into different sub images that are the raw data for the
    following feature extraction routine. Binarization is Usually presented with a grayscale image, binarization is then simply amatter of
    choosing a threshold value.Morphological OperatorsRemove isolated specks and holes in characters, can use
    theMajorityoperator.Segmentation is by far the most important aspect of the pre-processing stage. It allows the recognizer to extract
    features from each individual character [12]. In the more complicated case of handwritten text, the segmentation problem becomes
    much more difficult as letters tend to be connected to each other.It Checks the connectivity of shapes, label, and isolate.

    FEATURE EXTRACTION
    The sub-images have to be cropped sharp to the border of the character in order to standardize the sub-images. The image
    standardization is done by finding the maximum row and column with 1s and with the peak point, increase and decrease the counter
    until meeting the white space, or the line with all 0s. This technique is shown in figure below where a character S is being cropped
    and resized.

    Fig 2. Cropped and resized picture


    The image pre-processing is then followed by the image resize again to meet the network input requirement, 5 by 7 matrices, where
    the value of 1 will be assign to all pixel where all 10 by 10 box are filled with 1s, as shown below:
    74

    www.ijergs.org

    International Journal of Engineering Research and General Science Volume 3, Issue 1, January-February, 2015
    ISSN 2091-2730

    Fig 3. Image resize again to meet the network input requirement


    Finally, the 5 by 7 matrices is concatenated into a stream so that it can be feed into network 35 input neurons. The input of the network
    is actually the negative image of the figure, where the input range is 0 to 1, with 0 equal to black and 1 indicate white, while the value
    in between show the intensity of the relevant pixel [15]. By this, we are able to extract the character and pass to another stage for
    future "classification" or "training" purpose of the neural network character.

    DESIGN AND IMPLEMENTATION


    Initially we are making the Algorithm of Character Extraction. We are using MATLAB as tool for implementing the
    algorithm. Then we design neural network, we need to have a Neural Network that would give the optimum results . There is no
    specific way of finding the correct model of Neural Network. It could only be found by trial and error method [11]. Take different
    models of Neural Network, train it and note the output accuracy. There are basically two main phases in our Paper: Pre-processing and
    Character Recognition. In first phase we have are preprocessing the given scanned document for separating the Characters from it and
    normalizing each characters. Initially we specify an input image file, which is opened for reading and preprocessing. The image would
    be in RGB format (usually) so we convert it into binary format [8]. To do this, it converts the input image to grayscale format (if it is
    not already an intensity image), and then uses threshold to convert this grayscale image to binary i.e.all the pixels above certain
    threshold as 1 and below it as 0. we needed a method to extract a given character from the document.
    The character recognition application can be used in two different ways. First way is to type every command inside the
    MATLAB console and workspace on hand. The second way is to use already pre-prepared Graphical User Interface [10]. The GUI
    consists of two files. First file include all necessary programming code, and the second file include visible interface shapes and forms.
    The interface works like the workflow of recognition process. First we load the image, than we select the character and after that we
    click crop, pre-process, feature extraction and finally recognize [7]. On every stage, GUI shows us a new image, which is unique for
    the each step. The images can be viewed in the Main window, RGB, Binary, Crop to Edges and Features window.

    CONCLUSION
    This paper carries out a study handwritten character recognition using Artificial Neural Network.Artificial neural networks are
    commonly used to perform character recognition due to their high noise tolerance. The systems have the ability to yield excellent
    results. The feature extraction step of optical character recognition is the most important. A poorly chosen set of features will yield
    poor classification rates by any neural network. At the current stage of development, the software does perform well either in terms of
    speed or accuracy but not better. It is unlikely to replace existing OCR methods, especially for English text. A simplistic approach for
    recognition of Optical characters using artificial neural networks has been described.

    REFERENCES:
    [1] S. Mori, C. Y. Suen and K. Kamamoto, Historical review of OCR research and development, Proc. Of IEEE, vol. 80, (1992)
    July, pp. 1029-1058.
    [2] N. Arica and F. Yarman-Vural, An Overview of Character Recognition Focused on Off-line Handwriting, IEEE Transactions on
    Systems, Man, and Cybernetics, Part C: Applications and Reviews, vol. 31, no. 2, (2001), pp. 216 - 233.
    [3] A. Rajavelu, M. T. Musavi and M. V. Shirvaikar, A Neural Network Approach to Character Recognition, Neural Networks, vol.
    2, (1989), pp. 387-393.
    [4] R. Plamondon and S. N. Srihari, On-line and off- line handwritten character recognition: A comprehensive survey, IEEE
    Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 1, (2000), pp. 63-84.

    75

    www.ijergs.org

    International Journal of Engineering Research and General Science Volume 3, Issue 1, January-February, 2015
    ISSN 2091-2730

    [5] U. Bhattacharya and B. B. Chaudhuri, Handwritten numeral databases of Indian scripts and multistage recognition of mixed
    numerals, IEEE Transaction on Pattern analysis and machine intelligence, vol. 31, no. 3, (2009), pp. 444-457.
    [6] M. Hanmandlu, K. R. M. Mohan and H. Kumar, Neural-based Handwritten character recognition, in Proceedings of Fifth IEEE
    International Conference on Document Analysis and Recognition, ICDAR99, Bangalore, India, (1999), pp. 241-244.
    [7] T. V. Ashwin and P. S. Sastry, A font and size-independent OCR system for printed Kannada documents using support vector
    machines, in Sadhana, vol. 27, Part 1, (2002) February, pp. 3558.
    [8] S. V. Rajashekararadhya and P. Vanajaranjan, Efficient zone based feature extraction algorithm for handwritten numeral
    recognition of four popular south-Indian scripts, Journal of Theoretical and Applied Information Technology, JATIT, vol. 4, no. 12,
    (2008), pp. 1171-1181.
    [9] R. G. Casey and E. Lecolinet, A Survey of Methods and Strategies in Character Segmentation, IEEE Transactions on Pattern
    Analysis and Machine Intelligence, vol. 18, no. 7, (1996) July, pp. 690-706.
    [10] R. C. Gonzalez, R. E. woods and S. L. Eddins, Digital Image Processing using MATLAB, Pearson Education, Dorling
    Kindersley, South Asia, (2004).
    [11] T. V. Ashwin and P. S. Sastry, A font and size-independent OCR system for printed Kannada documents using support
    vectormachines, in Sadhana, vol. 27, Part 1, (2002) February, pp. 3558.
    [12] M. Blumenstein and B. Verma, Neural-based solutions for the segmentation and recognition of difficult handwritten words
    from a benchmark database, in Proceedings of the Fifth International Conference on Document Analysis and Recognition, ICDAR
    99, (1999) September, pp. 281 284.
    [13] Y. Tay, M. Khalid, R. Yusof and C. Viard-Gaudin, Offline cursive handwriting recognition system based on hybrid markov
    model and neural networks, in Proceedings of the IEEE International Symposium on Computational Intelligence in Robotics and
    Automation 2003, vol. 3, (2003) July, pp. 1190 1195.
    [14] G. Kim, V. Govindaraju and S. Srihari, A segmentation and recognition strategy for handwritten phrases, in Proceedings of the
    13th International Conference on Pattern Recognition 1996, vol. 4, (1996) August, pp. 510514.
    [15] Y. Y. Chung and M. T. Wong, Handwritten character recognition by fourier descriptors and neural network, in Proceedings of
    IEEE Region 10 Annual Conference on Speech and Image Technologies for Computing and Telecommunications, TENCON 97, vol.
    1, (1997) December, pp. 391 394

    76

    www.ijergs.org

    You might also like