Improved HMM for Cursive Arabic Handwriting Recognition System Using MLP Classifier
Journal Title: Transactions on Machine Learning and Artificial Intelligence - Year 2017, Vol 5, Issue 4
Abstract
Recognizing unconstrained cursive Arabic handwritten text is a very challenging task the use of hybrid classification to take advantage of the strong modeling of Hidden Markov Models (HMM) and the large capacity of discrimination related to Multilayer Perceptron (MLP) is a very important component in recognition systems.The proposed work reports an effective method on improvement our previous work that takes into consideration the context of character by applying an embedded training based HMMs this HMM is enhanced by an Artificial neural network that are incorporated into the process of classification to estimate the emission probabilities. The experiments are done on the same benchmark IFN/ENIT database of our previous work to compare the results and show the effectiveness of hybrid classifier for enhancing the recognition rate the results are promising and encouraging.'
Authors and Affiliations
Mouhcine Rabi, Mustapha Amrouch, Zouhir Mahani
Keywords
Related Articles
- EP ID EP308338
- DOI 10.14738/tmlai.54.2969
- Views 80
- Downloads 0
The Role of Cloud Computing in Learning from a Logistic and Strategic Vision Case of Information Systems Management of a Private Moroccan University
This research focuses on the role of cloud computing from a logistic and strategic vision in organizations. Our research question focuses on understanding the difficulties and limitations that bring the support of steeri...
Remote Assessment of Disease and Relapse– Central Nervous System-RADAR-CNS
Remote Assessment of Disease and Relapse in Central Nervous System Disorders (RADARCNS) is a major international research project. It aims to develop new ways of measuring major depressive disorder, epilepsy and multiple...
Detection of Damage in Rail Head by Using SAFE Method
The first cause of train derailment incidents is due to the transverse defect which occurs in the railhead. It is typically an open or internal crack developing in a plane which is generally perpendicular to the directio...
Kannada Named Entity Recognition and Classification using Support Vector Machine
Named Entity Recognition and Classification (NERC) is a process of identification of proper nouns in the text and classification of those nouns into certain predefined categories like person name, location, organization,...
Computational Intelligence for Congestion Control and Quality of Service Improvement in Wireless Sensor Networks
Congestion and quality of service are widely researched topics in Wireless Sensor Networks in recent years. Many researchers proposed and compared the merits and demerits of various algorithms with the existing algorithm...