Lexicon-Driven Handwritten Word Recognition Using Optimal Linear Combinations of Order Statistics
IEEE Transactions on Pattern Analysis and Machine Intelligence
Using Contextual Information to Selectively Adjust Preprocessing Parameters
IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Bio-inspired Applications of Connectionism-Part II
| Hi-index | 0.00 |
This paper presents a model for reading cursive script which has an architecture inspired by a reading model and which is based on perceptual concepts. We limit the scope of our study to the off-line recognition of isolated cursive words. First of all, we justify why we choose McClelland & Rumelhart's reading model as the inspiration for our system.Since a thorough description of our recognition method has been already done in a previous paper, a brief resumé of the method's behavior is presented and the main originalities of our model are underlined which are: development of a new technic for baseline extraction, choice of an architecture based on a reading model (hierarchical, parallel, with local representation and interactive activation mecanism), use of significant perceptual features in word recognition such as ascender and descender, creation of a fuzzy position concept dealing with the location uncertainty of features and letters, outside-in labeling process which mimics the human recognition process while reading, adaptability of the model to words of different lengths and from different languages. After this, we focus on the new updates added to the original system: a new baseline extraction module, a new feature extraction module, and a new generation, validation and hypotheses insertion process. After implementation of our method, new results have been obtained on real images and are discussed. We are concentrating now on validating the proposed model using a larger data base.