Creating Color Image Features Using Local Contrast Method

Ayman Al-Rawashdeh,Ziad Al-Qadi

doi:10.11591/eei.v7i3.1216

Ayman Al-Rawashdeh, Ziad Al-Qadi

Open Access

https://doi.org/10.11591/eei.v7i3.1216

Copy DOI

Abstract

Digital color images are now one of the most popular data types used in the digital processing environment. Color image recognition plays an important role in many vital applications, which makes the enhancement of image recognition or retrieval system an important issue. Using color image pixels to recognize or retrieve the image, but the issue of the huge color image size that requires accordingly more time and memory space to perform color image recognition and/or retrieval. In the current study, image local contrast was used to create local contrast victor, which was then used as a key to recognize or retrieve the image. The proposed local contrast method was properly implemented and tested. The obtained results proved its efficiency as compared with other methods.

Highlights

Color image features play an important role in image manipulation, as they can be used as a finger print for fast image retrieval or image recognition [1], [2]
The feature victor is usually small in size as compared to the original image size, which means that training time of artificial neural network (ANN) will be reduced when image features is used to identify the image [4,5,6,7]
The comparison shows that the extraction time using CSLBP is lower compared to the time when local contrast (LC) extraction method was used

Summary

Color Image Features

Color image features play an important role in image manipulation, as they can be used as a finger print for fast image retrieval or image recognition [1], [2]. Color images usually have big sizes and the identification of image pixel by pixel needs big efforts and might be considered time consuming process This suggests the need for a more efficient method to identify color image depending on the extraction of features with a small size [8,9,10]. LBP method does not reduce the histogram victor size (256 elements), and it might not be suitable to extract color image features [8,9,10,11]. Figure. 10 explains the process of abstaining LC using 4 neighbors [22]

IMPLEMENTATION

RESULTS

CONCLUSION