Multilayer Neural Networks and Nearest Neighbor Classifier Performances for Image Annotation

Abstract

The explosive growth of image data leads to the research and development of image content searching and indexing systems. Image annotation systems aim at annotating automatically animage with some controlled keywords that can be used for indexing and retrieval of images. This paper presents a comparative evaluation of the image content annotation system by using the multilayer neural networks and the nearest neighbour classifier. The region growing segmentation is used to separate objects, the Hu moments, Legendre moments and Zernike moments which are used in as feature descriptors for the image content characterization and annotation.The ETH-80 database image is used in the experiments here. The best annotation rate is achieved by using Legendre moments as feature extraction method and the multilayer neural network as a classifier.

Authors and Affiliations

Mustapha OUJAOURA , Brahim MINAOUI , Mohammed FAKIR

Keywords

Related Articles

Object Conveyance Algorithm for Multiple Mobile Robots based on Object Shape and Size

This paper describes a determination method of a number of a team for multiple mobile robot object conveyance. The number of robot on multiple mobile robot systems is the factor of complexity on robots formation and moti...

Fitness Proportionate Random Vector Selection based DE Algorithm (FPRVDE)

Differential Evolution (DE) is a simple, powerful and easy to use global optimization algorithm. DE has been studied in detail by many researchers in the past years. In DE algorithm trial vector generation strategies hav...

Piezoelectric based Biosignal Transmission using Xbee

This paper is showcasing the development of an innovative healthcare solution that will allow patient to be monitored remotely. The system utilizes a piezoelectric sheet sensor and XBee wireless communication protocol to...

Performance Comparison of QEC Network based JAVA Application and Web based PHP Application

Every organization wants to automate the manual system for moving and storing their data in particular format. A QEC department takes feedback of teacher evaluation manually from the students in the university that is so...

Proposal for a Feature Automation Solution for an IMS-KMS-IoT Platform based on SDN

The concept of the Internet of Things is a paradigm that is gaining more and more ground and soon the number of connected objects will be counted in billions. This will transform our lives and pose new challenges. To mee...

Download PDF file
  • EP ID EP87082
  • DOI 10.14569/IJACSA.2012.031126
  • Views 154
  • Downloads 0

How To Cite

Mustapha OUJAOURA, Brahim MINAOUI, Mohammed FAKIR (2012). Multilayer Neural Networks and Nearest Neighbor Classifier Performances for Image Annotation. International Journal of Advanced Computer Science & Applications, 3(11), 165-171. https://europub.co.uk/articles/-A-87082