The Bidirectional Long-Short-Term Memory Neural Network based Word Retrieval for Arabic Documents
Journal Title: Transactions on Machine Learning and Artificial Intelligence - Year 2015, Vol 3, Issue 1
Abstract
The reflow from Arabic document image collections is a challenging task. This is partly due to the insolubility of the Arabic script. Because of the peculiarity of the whole body of the Arabic words, namely connectivity between the characters, thereby the segmentation of An Arabic word is very arduous and also the variability of the handwritten styles and shapes as well as deceleratation in the print therefore Arabic document repositories are not liable to indexation and reflow. In this paper, we are proposing an idea for reflow coherent Arabic document in response to an appropriate Arabic query word. We present a novel approach at reflow on an Arabic document image, using a Bidirectional Long-Short-Term Memory Neural Network. The designed to take relating to information into account, these networks can maintain Arabic word images that cannot be durable segmented into individual Arabic characters. The partitioning Arabic word, we easier the problem and receive elevated reflow rates. The proposed capable reflow scheme avoids unambiguous recognition of Arabic characters. An experimental evaluation on a dataset of Arabic word images conjunct from handwritten notebook show good precision even in the impendence of printing transformation and deceleratation. The reflow Arabic word performance is comparison with baseline methods. These results encourage the development of real world systems for word reflow for Arabic documents
Authors and Affiliations
Dr. Yusuf Perwej
Keywords
Related Articles
- EP ID EP278943
- DOI 10.14738/tmlai.31.863
- Views 70
- Downloads 0
Novel Compact CPW LowPass Filter Integrating Periodic Triangle DGS Cells
In this paper, we introduce a new periodic structure for CPW of a low pass filter based on the DGS technique with triangle slot cell forme. The proposed structure is a minuature low pass filter that exhibits low insertio...
Migration of the Temporal RDB into Temporal ORDB including Bitemporal Data : Phases
This paper proposes an approach for migrating existing relational database (TRDB) according to SQL: 2011 standard into temporal object relational database (TORDB) including Bitemporal data. This is done with methods that...
Semantic Web Service Discovery Framework using Multi-Agents System and NLP Techniques
As a consequently increase amount of web services available on the web, automatic discovery presents a great challenge, in order to satisfy this requirement, semantic discovery approaches based on ontologies have been de...
Learning Style Classification Based on Student's Behavior in Moodle Learning Management System
In learning field, each student has his own learning style that affects his way of get, process, understand and percept information. Determining the learning style of students enhances the performance of learning process...
On Modified Self Organizing Feature Maps
This paper presents optimization of self-organizing feature maps by adjusting tunable parameters and in the iterative process by utilizing linear algebra concepts. A gradient rule is applied on the weights matrix singula...