Welcome to the InfoSci Platform
Object-Based Scene Classification Modeled by Hidden Markov Models Architecture

Object-Based Scene Classification Modeled by Hidden Markov Models Architecture

Benrais Lamine, Baha Nadia
Copyright: © 2021 |Volume: 15 |Issue: 4 |Pages: 30
ISSN: 1557-3958|EISSN: 1557-3966|EISBN13: 9781799859857|DOI: 10.4018/IJCINI.20211001.oa6
Cite Article Cite Article

MLA

Lamine, Benrais, and Baha Nadia. "Object-Based Scene Classification Modeled by Hidden Markov Models Architecture." IJCINI vol.15, no.4 2021: pp.1-30. http://doi.org/10.4018/IJCINI.20211001.oa6

APA

Lamine, B. & Nadia, B. (2021). Object-Based Scene Classification Modeled by Hidden Markov Models Architecture. International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 15(4), 1-30. http://doi.org/10.4018/IJCINI.20211001.oa6

Chicago

Lamine, Benrais, and Baha Nadia. "Object-Based Scene Classification Modeled by Hidden Markov Models Architecture," International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) 15, no.4: 1-30. http://doi.org/10.4018/IJCINI.20211001.oa6

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Multiclass classification problems such as document classification, medical diagnosis or scene classification are very challenging to address due to similarities between mutual classes. The use of reliable tools is necessary to get good classification results. This paper addresses the scene classification problem using objects as attributes. The process of classification is modeled by a famous mathematical tool: The Hidden Markov Models. We introduce suitable relations that scale the parameters of the Hidden Markov Model into variables of scene classification. The construction of Hidden Markov Chains is supported with weight measures and sorting functions. Lastly, inference algorithms extract most suitable scene categories from the Discrete Markov Chain. A parallelism approach constructs several Discrete Markov Chains in order to improve the accuracy of the classification process. We provide numerous tests on different datasets and compare classification accuracies with some state of the art methods. The proposed approach distinguishes itself by outperforming the other.