*Corresponding author. Email: ahmed.a.n@uoanbar.edu.iq Review Article A Short Review on Supervised Machine Learning and Deep Learning Techniques in Computer Vision Ahmed Adil Nafea 1 *, , Saeed Amer Alameri 2, , Russel R Majeed 3 , Meaad Ali Khalaf 4, , Mohammed M AL-Ani 5, , 1 Department of Artificial Intelligence, College of Computer Science and IT, University of Anbar, Ramadi , Iraq. 2 Department of Information Technology, Seiyun University, Hadhramout, Yemen. 3 College of Education for Pure Sciences, University of Thi-Qar, Thi-Qar, Iraq. 4 Department of Computer Science, AUL University, Beirut, Lebanon. 5 Center for Artificial Intelligence Technology (CAIT), Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia (UKM), Bangi, Selangor, Malaysia A R T I C L E I N F O Article History Received 28 Nov 2023 Accepted 15 Jan 2024 Published 11 Feb 2024 Keywords Computer Vision 1 Deep Learning 2 Machine Learning 3 Supervised Learning 4 Techniques 5 A B S T R A C T In last years, computer vision has shown important advances, mainly using the application of supervised machine learning (ML) and deep learning (DL) techniques. The objective of this review is to show a brief review of the current state of the field of supervised ML and DL techniques, especially on computer vision tasks. This study focuses on the main ideas, advantages, and applications of DL in computer vision and highlights their main concepts and advantages. This study showed the strengths, limitations, and effects of computer vision supervised ML and DL techniques. 1. BACKGROUND Computer vision plays a pivotal role by employing image and pattern analysis methodologies to address complex challenges, treating an image as an intricate array of pixels. This field within artificial intelligence (AI) automates monitoring and inspection tasks, showcasing its capability to extract meaningful information from a diverse range of visual inputs, including digital images and videos. In essence, computer vision emerges as an indispensable component, facilitating systems in deriving valuable insights within the context of AI [1]. Computer vision goals to allow computers and machines to understand visual information, similar to humans it means the development of algorithms and techniques to analyze, process, and extract meaning from visual data [2]. Supervised ML and DL are two prominent techniques in computer vision that have developed the method visual data is analyzed and interpreted [3]. Supervised ML works in training a model developing labeled examples, utilizing algorithms such as support vector machines (SVMs), decision trees (DT), random forests (RF), and naive Bayes (NB) classifiers [4]. DL aims onartificial neural networks learned via the human brain's structure and operation. These networks, combined with many layers of connected nodes, extract representations from raw input data [5]. Fig. 1. shows the classification of common ML and DL techniques. In this review of supervised ML and DL techniques in computer vision, studying their required models, architectures, strengths, and limitations. Babylonian Journal of Machine Learning Vol.2024, pp. 48–55 DOI: https://doi.org/10.58496/BJML/2024/004; ISSN: 3006–5429 https://mesopotamian.press/journals/index.php/BJML