Vol.:(0123456789) Multimedia Tools and Applications https://doi.org/10.1007/s11042-023-17120-z 1 3 Towards exploiting believe function theory for object based scene classifcation problem Anfel Amirat 1  · Lamine Benrais 2  · Nadia Baha 1 Received: 31 December 2021 / Revised: 31 August 2023 / Accepted: 15 September 2023 © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023 Abstract Scene classifcation is one of the active research domains of artifcial intelligence (AI) with many real-world applications. This paper presents a new scene classifcation approach based on the Belief Function Theory, which provides a more efective way of handling uncertainty information compared to traditional probability-based methods. Unlike previ- ous methods that rely on probabilities, which have proved their limitations, the main con- tribution of our approach is the use of belief degrees to classify unknown scenes based on object labels. We conduct experiments on three well-known datasets (SUN397, MIT Indoor, and LabelMe) and compare our results with state-of-the-art methods. Our approach achieves competitive results with a simple and robust framework that outperforms previous methods in some cases. We also provide insights into the strengths and limitations of our approach and discuss potential future directions for research. Overall, our work demon- strates the efectiveness of the Belief Function theory in scene classifcation and opens up new avenues for further research and innovation in this area. Keywords Scene Classifcation · Belief Function Theory · Object-based approach · Uncertainty classifcation 1 Introduction Scene Scene classifcation is a fundamental problem in computer vision with wide-ranging real-world applications, including surveillance [1, 49], autonomous driving [2, 3], robot- ics [4], and more [5–7]. It aims to assign a scene to a predefned category based on its * Anfel Amirat aamirat@usthb.dz Lamine Benrais lamine.benrais@kuleuven.be Nadia Baha Nbahatouzene@usthb.dz 1 Computer Science Faculty, University of Science and Technology Houari Boumediene, Algiers, Algeria 2 KU Leuven, Faculty of Arts, B-3000, Leuven, Belgium