Neural network technology for pattern recognition, stock prediction and market forecasting

OCR Optical Character Recognition System

Download now Matlab source code
Requirements: Matlab, Matlab Image Processing Toolbox, Matlab Neural Network Toolbox.

Optical character recognition (OCR) is the translation of optically scanned bitmaps of printed or written text characters into character codes, such as ASCII. This is an efficient way to turn hard-copy materials into data files that can be edited and otherwise manipulated on a computer. This is the technology long used by libraries and government agencies to make lengthy documents quickly available electronically. Advances in OCR technology have spurred its increasing use by enterprises. For many document-input tasks, OCR 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. Before OCR can be used, the source material must be scanned using an optical scanner (and sometimes a specialized circuit board in the PC) to read in the page as a bitmap (a pattern of dots). Software to recognize the images is also required.

The OCR software then processes these scans to differentiate between images and text and determine what letters are represented in the light and dark areas. Older OCR systems match these images against stored bitmaps based on specific fonts. The hit-or-miss results of such pattern-recognition systems helped establish OCR's reputation for inaccuracy. Today's OCR engines add the multiple algorithms of neural network technology to analyze the stroke edge, the line of discontinuity between the text characters, and the background. 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.

Our software package proposes to solve the classification of isolated handwritten characters and digits of the UJI Pen Characters Data Set using Neural Networks. The data consists of samples of 26 characters and 10 digits written by 11 writers on a tablet PC. The characters (in standard UNIPEN format) are written both in upper and lower case and there is a whole two set of characters per writer. So the output should be in one of the 35 classes. The ultimate objective is building a writer independent model for each character.

The selection of valuable features is crucial in character recognition, therefore a new and meaningful set of features, the Uniform Differential Normalized Coordinates (UDNC), introduced by C. Agell, is adopted. These features are shown to improve the recognition rate using simple classification algorithms so they are used to train a Neural Network and test its performance on UJI Pen Characters Data Set.

Index Terms: Matlab, source, code, ocr, optical character recognition, scanned text, written text, ascii, isolated character.

Release 1.0 Date 2010.01.25
Major features:

• Handwriting recognition for isolated characters
• UNIPEN file format supported
• Uniform differential normalized coordinates
• Fast and optimized implementation
• Easy and intuitive GUI
• Demo code (protected P-files) available for performance evaluation