Author:
Tayyaba Azim
Affiliation:
University of Southampton, United Kingdom
Keyword(s):
Object Detection, Feature Learning, Deep Models, Support Vector Machines, Fisher Kernel.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Camera Networks and Vision
;
Computer Vision, Visualization and Computer Graphics
;
Early and Biologically-Inspired Vision
;
Features Extraction
;
Image and Video Analysis
;
Image Formation and Preprocessing
;
Image Formation, Acquisition Devices and Sensors
;
Motion, Tracking and Stereo Vision
;
Tracking and Visual Navigation
Abstract:
This paper surveys the learning algorithms of visual features representation and the computational modelling approaches proposed with the aim of developing better artificial object recognition systems. It turns out that most of the learning theories and schemas have been developed either in the spirit of understanding biological facts of vision or designing machines that provide better or competitive perception power than humans. In this study, we discuss and analyse the impact of notable statistical approaches that map the cognitive neural activity at macro level formally, as well as those that work independently without any biological inspiration towards the goal of developing better classifiers. With the ultimate objective of classification in hand, the dimensions of research in computer vision and AI in general, have expanded so much so that it has become important to understand if our goals and diagnostics of the visual input learning are correct or not. We first highlight the m
ainstream approaches that have been proposed to solve the classification task ever since the advent of the field, and then suggest some criterion of success that can guide the direction of the future research.
(More)