Improvement of Multimodal Images Classification Based on DSMT Using Visual Saliency Model Fusion With SVM

Journal Title: INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY - Year 2018, Vol 18, Issue 0

Abstract

Multimodal images carry available information that can be complementary, redundant information, and overcomes the various problems attached to the unimodal classification task, by modeling and combining these information together. Although, this classification gives acceptable classification results, it still does not reach the level of the visual perception model that has a great ability to classify easily observed scene thanks to the powerful mechanism of the human brain.  In order to improve the classification task in multimodal image area, we propose a methodology based on Dezert-Smarandache formalism (DSmT), allowing fusing the combined spectral and dense SURF features extracted from each modality and pre-classified by the SVM classifier. Then we integrate the visual perception model in the fusion process. To prove the efficiency of the use of salient features in a fusion process with DSmT, the proposed methodology is tested and validated on a large datasets extracted from acquisitions on cultural heritage wall paintings. Each set implements four imaging modalities covering UV, IR, Visible and fluorescence, and the results are promising.

Authors and Affiliations

Hanan Anzid, Gaetan le Goic, Aissam bekkari, Alamin Mansouri, Driss Mammass

Keywords

Related Articles

ANALYZING AND IMPROVING WEB APPLICATION QUALITY USING DESIGN PATTERNS

With the mounting demand of web applications, a number of issues allied to its quality have came in existence. In the meadow of web applications, it is very thorny to develop high quality web applications. A design patte...

Particle Swarm Optimization and Shuffle Complex Evolution for Calibrating Xinanjiang Model Parameters

Xinanjiang model, a conceptual hydrological model, is well known and widely used in China since 1970s. Xinanjiang model consists of large number of parameters that cannot be directly obtained from measurable quantities o...

AFDroid: Anti-Forensics Device To Protect Android System

Mobile devices are among the most common new technologies of the year, gaining even more spread over and success in the day-to-day life of wide range of people. Unfortunately, while the number of mobile devices are used...

Factors Affecting Information and Communication Technology (ICT) Use by Southern Colleges Teachers in Balqa Applied University

This research was conducted to study the factors affecting the use of Information and Communication Technologies (ICTs) by Southern Colleges Teachers in Balqa applied university teachers. The results of this study indica...

THE PROSPECT OF SOLAR POWER GENERATION TECHNOLOGY

Over the years, several means of electrical power generation have been in place ranging from wood, coal, to fuel. All these means have at its point served purpose at the needed time. This work presents the historical res...

Download PDF file
  • EP ID EP649747
  • DOI 10.24297/ijct.v18i0.7956
  • Views 170
  • Downloads 0

How To Cite

Hanan Anzid, Gaetan le Goic, Aissam bekkari, Alamin Mansouri, Driss Mammass (2018). Improvement of Multimodal Images Classification Based on DSMT Using Visual Saliency Model Fusion With SVM. INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY, 18(0), 7418-7430. https://europub.co.uk/articles/-A-649747