High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

A Survey on Correlation Filters for Object Detection

Author(s):

Disha Davis , IES College of Engineering,Chittilappilly,Thrissur Dt.,Kerala; Nicy Johnson, IES College of Engineering,Chittilappilly,Thrissur Dt.,Kerala

Keywords:

Object Detection, Correlation Filters, Feature Extraction, Classifiers

Abstract

Object detection is a sequence of segments comprises the objects of interest, which are taken as preprocessing and expansively applied in various vision tasks like face detection, face recognition, video object co-segmentation. Out of these, Correlation filters are the special classifiers which are designed for accurate object detection. Normal correlation filters require scalar valued image features and only perform on objects with consistent appearance but newer filters work with feature spaces that establish some invariance to small deformations. However, most of existing approaches only utilizes the proposals to compute the location; the aim is to propose a fastest algorithm for making the object detection as an efficient task. This paper accentuates correlation techniques and feature extraction methods used by researchers for object detection.

Other Details

Paper ID: IJSRDV7I10026
Published in: Volume : 7, Issue : 1
Publication Date: 01/04/2019
Page(s): 102-104

Article Preview

Download Article