Title

Poster Session A: Classification of Compressed Human Face Images by using Principle Components

Abstract/Description

This paper describes the novel approach of classifying the humans on the basis of their compressed face images. The compression of the face images is performed using Discrete Wavelet Transform (DWT). While the classification encompass the use of Principal Components Analysis (PCA). Classification technique utilizes PCA in some different way. Only first principal component is used as feature vector out of 92 components (since image size is 112×92), causing a better results of 87.39%. The Euclidean distance is used as distance metric. In the end our results are compared to our previous research of classifying the uncompressed images.

Location

Crystal Ball Room A, Hotel Pearl Continental, Karachi, Pakistan

Session Theme

Poster Session A: Artificial Intelligence [AI-1]

Session Type

Poster Session

Session Chair

Dr. Arshad B. Siddiqui

Start Date

28-8-2005 12:30 PM

End Date

28-8-2005 12:50 PM

Share

COinS
 
Aug 28th, 12:30 PM Aug 28th, 12:50 PM

Poster Session A: Classification of Compressed Human Face Images by using Principle Components

Crystal Ball Room A, Hotel Pearl Continental, Karachi, Pakistan

This paper describes the novel approach of classifying the humans on the basis of their compressed face images. The compression of the face images is performed using Discrete Wavelet Transform (DWT). While the classification encompass the use of Principal Components Analysis (PCA). Classification technique utilizes PCA in some different way. Only first principal component is used as feature vector out of 92 components (since image size is 112×92), causing a better results of 87.39%. The Euclidean distance is used as distance metric. In the end our results are compared to our previous research of classifying the uncompressed images.