On recognition of handwritten devanagari numerals
- Authors: Ghosh, Ranadhir , Bhattacharya, Ujjwal , Chaudhuri, Bidyut , Ghosh, Moumita
- Date: 2005
- Type: Text , Conference paper
- Relation: Paper presented at the Workshop in Learning Algorithms for Pattern Recognition, in conjunction with the 18th Australian Joint Conference on Artificial Intelligence, Sydney, Australia : 5th December, 2005
- Full Text: false
- Reviewed:
- Description: E1
- Description: 2003001371
A feature extraction technique for online handwriting recognition
- Authors: Verma, Brijesh , Lu, Jenny , Ghosh, Moumita , Ghosh, Ranadhir
- Date: 2004
- Type: Text , Conference paper
- Relation: Paper presented at 2004 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary : 25th July, 2004
- Full Text: false
- Reviewed:
- Description: The paper presents a feature extraction technique for online handwriting recognition. The technique incorporates many characteristics of handwritten characters based on structural, directional and zoning information and combines them to create a single global feature vector. The technique is independent to character size and it can extract features from the raw data without resizing. Using the proposed technique and a Neural Network based classifier, many experiments were conducted on UNIPEN benchmark database. The recognition rates are 98.2% for digits, 91.2% for uppercase and 91.4% for lowercase.
- Description: E1
- Description: 2003000868
A hybrid approach for feature and architecture selection in online handwriting recognition
- Authors: Ghosh, Ranadhir , Ghosh, Moumita , Yearwood, John
- Date: 2004
- Type: Text , Conference paper
- Relation: Paper presented at RASC 2004: Fifth International Conference on Recent Advances in Soft Computing, Nottingham, United Kingdom : 16th - 18th December, 2004
- Full Text: false
- Reviewed:
- Description: E1
- Description: 2003000870
An evolutionary neural learning algorithm for offline cursive handwriting words with hamming network lexicon
- Authors: Ghosh, Moumita , Ghosh, Ranadhir , Yearwood, John
- Date: 2004
- Type: Text , Conference paper
- Relation: Paper presented at Seventeenth International Florida Artificial Intelligence Research Symposium Conference, FLAIRS 2004, Miami Beach, USA : 15th May, 2004
- Full Text: false
- Reviewed:
- Description: In this paper we incorporate a hybrid evolutionary method, which uses a combination of genetic algorithm and matrix based solution method such as QR factorization. A heuristic segmentation algorithm is initially used to over segment each word. Then the segmentation points are passed through the rule-based module to discard the incorrect segmentation points and include any missing segmentation points. Following the segmentation the connected contour is extracted between two correct segmentation points. The contour is passed through the feature extraction module that extracts the angular features of the contour, after which the EALS-BT algorithm finds the architecture and the weights for the classifier network. These recognized characters are grouped into words and passed to a variable length lexicon that retrieves words that has highest confidence value. Hamming neural network is used as a lexicon that rectifies the word misrecognized by the classifier. We have used CEDAR benchmark dataset and UCI Machine Learning repository (Upper case) to test the train and test the system
- Description: E1
- Description: 2003000865
Offline handwriting recognition using evolutionary neural learning algorithm based on rule based over segmented data points
- Authors: Ghosh, Moumita , Ghosh, Ranadhir
- Date: 2003
- Type: Text , Conference paper
- Relation: Paper presented at the 11th Conference of the International Graphonomics Society IGS2003 - Connecting Sciences Using Graphonomic Research, Arizona, USA : 2nd May, 2003 p. 73-87
- Full Text: false
- Reviewed:
- Description: In this paper we propose a novel technique of using a hybrid evolutionary method, which uses a combination of genetic algorithm and matrix based solution methods such as QR factorization. The training of the model is based on a layer based hierarchical structure for the architecture and the weights for the Artificial Neural Network classifier. The architecture for the classifier is found using a binary search type procedure. The hierarchical structured algorithm (EALS-BT) is also a hybrid, because it combines the Genetic Algorithm based method with the Matrix based solution method for finding weights. A heuristic segmentation algorithm is initially used to over segment each word. Then the segmentation points are passed through the rule-based module to discard the incorrect segmentation points and include any missing segmentation points. Following the segmentation the contour is extracted between two correct segmentation points. The contour is passed through the feature extraction module that extracts the angular features, after which the EALS-BT algorithm finds the architecture and the weights for the classifier network. These recognized characters are grouped into words and passed to a variable length lexicon that retrieves words that have the highest confidence value. ACM Classification: I.4 (Image Processing and Computer Vision)
- Description: E1
- Description: 2003000420