Study of Various Types of ML Algorithms

Study of Various Types of ML Algorithms

Prof.SayaliS. Kuchekar,DhanashriL.Pawar,ShreejeetV.Adsul

Department of E&TC, Sinhgad College of Engineering

Department of E&TC ,Sinhgad College of Engineering

Department of E&TC ,Sinhgad College of Engineering

---------------------------------------------------------------------***---------------------------------------------------------------------

Abstract - This paper introduces about various algorithms used in image processing, The field of image detection has advanced significantly with the development of several powerful algorithms designed to identify and localize objects in images. This study investigates three prominent algorithms in image detection: You Only Look Once (YOLO), Region-based Convolutional Neural Networks (RCNN), and Single ShotMultibox Detector(SSD).Eachofthesealgorithms employs distinct methodologies for achieving object detection, and their performance varies depending on factors such as speed, accuracy, and computational complexity. YOLO is renowned for its real-time detectioncapabilities,making itsuitablefor applications where speed is crucial. RCNN, on the other hand, offers high accuracy by employing region proposals and deep learning for classification, though it is computationally intensive. SSD strikes a balance between speed and accuracy by utilizing a single network to predict object locationsandclassscoresdirectly.Thisstudyprovidesan in-depth comparison of these algorithms based on key performance metrics, such as precision, recall, and inference time.

Key Words :computer vision, image processing, object detection, CNN, Accuracy.