AN ADVANCED SCALE INVARIANT FEATURE TRANSFORM ALGORITHM FOR FACE RECOGNITION

Journal Title: Indian Journal of Computer Science and Engineering - Year 2016, Vol 7, Issue 3

Abstract

In computer vision, Scale-invariant feature transform (SIFT) algorithm is widely used to describe and detect local features in images due to its excellent performance. But for face recognition, the implementation of SIFT was complicated because of detecting false key-points in the face image due to irrelevant portions like hair style and other background details. This paper proposes an algorithm for face recognition to improve recognition accuracy by selecting relevant SIFT key-points only that by rejecting false key points. In the new proposed Haar-Cascade SIFT algorithm (HC-SIFT), the accuracy in face recognition has been increased from 52.6% to 75.1% from SIFT to HC- SIFT algorithm.

Authors and Affiliations

Mohammad Mohsen Ahmadinejad , Elizabeth Sherly

Keywords

Related Articles

Solving Scheduling problems using Selective Breeding Algorithm and Hybrid Algorithm

The n-job, m-machine scheduling problem is one of the general scheduling problems in a system. Scheduling problems vary widely according to specific production tasks but most are NP-hard problems. Scheduling problems are...

MODELLING PERFORMANCE MONITORING OF IT INFRASTRUCTURE COMPONENTS USING TIMED PETRI NETS

This paper focuses on utilization of Petri Nets as a modelling and simulation tool for analyzing performance monitoring of IT infrastructure. In order to make informed fine tuning decisions, modelling and simulation base...

PERFORMANCE OF CONCURRENCY CONTROL MECHANISMS IN CENTRALISED DATABASE SYSTEMS

The objective of this study is to propose user control system that definitely increases the performance of realtime data service. However the most existing work on this RTDB was based on very critical closed loop control...

A NOVEL APPROACH TO GENERATE FRACTAL IMAGES USING CHAOS THEORY

We propose the fractal generation method to generate the different types of fractals using chaos theory. The fractals are generated by Iterated Function System (IFS) technique. The chaos theory is an unpredictable behavi...

SURVEY OF PACKET DROPPING ATTACK IN MANET

Mobile Ad-hoc NETwork (MANET) is an application of wireless network with self-configuring mobile nodes. MANET does not require any fixed infrastructure. Its development never has any threshold range. Nodes in MANET can c...

Download PDF file
  • EP ID EP118089
  • DOI -
  • Views 110
  • Downloads 0

How To Cite

Mohammad Mohsen Ahmadinejad, Elizabeth Sherly (2016). AN ADVANCED SCALE INVARIANT FEATURE TRANSFORM ALGORITHM FOR FACE RECOGNITION. Indian Journal of Computer Science and Engineering, 7(3), 82-90. https://europub.co.uk/articles/-A-118089