Recognizing objects in complex scenes: A Recent Systematic Review

Authors

  • Hashim Rosli Faculty of Computer Science and Mathematics, Universiti Malaysia Terengganu (UMT), Kuala Nerus, 21030 Terengganu, Malaysia
  • Rozniza Ali Faculty of Computer Science and Mathematics, Universiti Malaysia Terengganu (UMT), Kuala Nerus, 21030 Terengganu, Malaysia
  • Muhammad Suzuri Hitam Faculty of Computer Science and Mathematics, Universiti Malaysia Terengganu (UMT), Kuala Nerus, 21030 Terengganu, Malaysia
  • Ashanira Mat Deris Faculty of Computer Science and Mathematics, Universiti Malaysia Terengganu (UMT), Kuala Nerus, 21030 Terengganu, Malaysia
  • Noor Hafhizah Abd Rahim Faculty of Computer Science and Mathematics, Universiti Malaysia Terengganu (UMT), Kuala Nerus, 21030 Terengganu, Malaysia
  • Usman Haruna Department of Computer Science Yusuf Maitama Sule University, Kano, Nigeria

DOI:

https://doi.org/10.37934/araset.61.2.208226

Keywords:

object, recognition, image processing, machine learning, complex scene

Abstract

This systematic review provides a comprehensive examination of recent advancements in object recognition within complex scenes, focusing on addressing challenges such as clutter, occlusion, and diverse environmental conditions. Leveraging the PRISMA framework, the study meticulously analysed a diverse range of literature from esteemed sources, employing advanced search methods on Scopus and WoS databases to identify and analyse primary research studies (n = 25). The review encompasses three key themes: Theme 1 concentrates on Image Noise Identification and Removal Techniques, while Theme 2 delves into Image Classification and Recognition under Noise. Additionally, Theme 3 explores Innovative Models and Approaches for Noise-Robust Image Analysis. Despite the progress achieved, contemporary recognition systems struggle with real-world complexities such as varied scales, lighting variations, and different viewpoints. The synthesis of findings emphasizes the necessity for innovative strategies that capitalize on contextual cues and harness the potential of deep learning to enhance precision in object recognition within intricate visual environments. The insights gleaned from this synthesis are poised to guide future research directions, informing the development of more resilient algorithms capable of navigating challenges and catalysing advancements in the field of object recognition.

Downloads

Download data is not yet available.

Author Biographies

Hashim Rosli, Faculty of Computer Science and Mathematics, Universiti Malaysia Terengganu (UMT), Kuala Nerus, 21030 Terengganu, Malaysia

p5812@pps.umt.edu.my

Rozniza Ali, Faculty of Computer Science and Mathematics, Universiti Malaysia Terengganu (UMT), Kuala Nerus, 21030 Terengganu, Malaysia

rozniza@umt.edu.my

Muhammad Suzuri Hitam, Faculty of Computer Science and Mathematics, Universiti Malaysia Terengganu (UMT), Kuala Nerus, 21030 Terengganu, Malaysia

suzuri@umt.edu.my

Ashanira Mat Deris, Faculty of Computer Science and Mathematics, Universiti Malaysia Terengganu (UMT), Kuala Nerus, 21030 Terengganu, Malaysia

ashanira@umt.edu.my

Noor Hafhizah Abd Rahim, Faculty of Computer Science and Mathematics, Universiti Malaysia Terengganu (UMT), Kuala Nerus, 21030 Terengganu, Malaysia

noorhafhizah@umt.edu.my

Usman Haruna, Department of Computer Science Yusuf Maitama Sule University, Kano, Nigeria

uharuna@yumsuk.edu.ng

Downloads

Published

2024-10-28

Issue

Section

Articles