Contextual Arabic Handwriting Recognition System Using Embedded Training Based Hybrid HMM/MLP Models
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 anArtificial 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 EP308421
- DOI 10.14738/tmlai.54.2983
- Views 108
- Downloads 0
SAAS Cloud security : Attacks and Proposed Solutions
Nowadays the Cloud has started to gain ground even in SMEs, in spite of that the Cloud is still unknown for several ... for others few reliable. SaaS represents a promising technology, which grows each year rapidly. Only...
Study of Test Anxiety of Freshmen Engineering Boys and Girls Students and their Academic Performance in Science & Humanities Subjects
The main aim of this learning was the effect of teaching of self-regulation on test anxiety; college achievement and met cognition in boy students, The Society under study include all boy and girl students of MLRIT. From...
Uni ed Acoustic Modeling using Deep Conditional Random Fields
Acoustic models based on Deep Neural Networks (DNNs) lead to sig- ni cant improvement in the recognition accuracy. In these methods, Hid- den Markov Models (HMMs) state scores are computed using exible dis- criminant DN...
Random Key Cuckoo Search for the Quadratic Assignment Problem
This paper proposes an adaptation of the RandomKey Cuckoo Search (RKCS) algorithm for solving the famous Quadratic Assignment Problem (QAP). We used a simplified and efficient randomkey encoding scheme to convert a conti...
Opinion Mining Using Sequence Labelling
Opinion mining aims to determine the attitude of a person by identifying and extracting subjective information. The attitude is the judgement, evaluation or emotional state of the person towards a product, or service or...