The revised Fundamental Theorem of Moment Invariants
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern recognition and image analysis
Pattern recognition and image analysis
The Document Spectrum for Page Layout Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Goal-Directed Evaluation of Binarization Methods
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
Object recognition is an important task in many image processing and pattern recognition applications. Character recognition is one of the most successful applications of automatic pattern recognition techniques and essentially involves identification and classification of two dimensional (2D) signal structures. The ability to identify machine printed characters in an automated or a semi-automated manner has practical significance and different techniques are applied to get the desired recognition results. The process of character recognition involves several steps including pre-processing, feature extraction and classification. Preprocessing includes the removal of noise from the image, convert into binary image and then segment into individual character. After segmentation, each character is resized according to its aspect ratio and then boundary of the character is extracted. Feature extraction is done by applying central moment invariant technique to extract the relevant features. Classification is performed by minimum distance classifier in a 9-dimension Euclidian feature space.