College of Computer Science and Mathematics

Discussion of a high diplom in the College of Computer Science and Mathematics – Department of Statistics and Informatics entitled:

“Using Swarm Intelligence to Enhance Contrast of The Color Images”

 

In continuation of the scientific research movement and with the follow-up and presence of the Dean of the College of Computer Science and Mathematics

Respected Professor Dr. Duha Bashir Abdullah

It was discussed in the discussion hall of the College of Computer Science and Mathematics at the University of Mosul on Wednesday 21/2/2024

Higher diploma thesis by

Amani Ahmed Yahya Hussein

supervised by Assist. Prof. Hanan Hamid Ali

The study looked at improving image contrast, which aims to enhance image quality and make details clearer. The focus of this study was on improving image contrast using three main algorithms: Histogram Equalizer, ACE Mean, and Hybrid ACE-FireFly. Histogram Equalizer is a classic method that distributes color frequency evenly, enhancing contrast and enhancing details, while ACE Mean relies on mathematical integration and optimization techniques to enhance image quality and make contrast more pronounced. Hybrid ACE-FireFly represents a cross between ACE, a traditional method, and FireFly. It is an intelligent algorithm to improve contrast using the advantages of each.

Common metrics such as PSNR, MSE, and RMSE were used to evaluate the image quality. PSNR reflects the effectiveness of algorithms in providing image quality, as the values increase when the quality is better. Also, MSE is measured by the difference between the actual values of the pixels in the image, and low values indicate high quality. RMSE is used to determine the extent of deviation between the two images. The results show noticeable improvements in image quality using the adopted algorithms, and the metrics used reflect an improvement in contrast and quality of details in the processed images.

Ten images of different contrast were tested to verify the performance efficiency of the proposed algorithm. The results indicate that the proposed hybrid method was the best among similar methods used.

The discussion committee consists of

Assis. Dr . Shahbaa Ibrahim Khalil– Chairman

Assis. Prof. Dr. Naktal Moaid Edan – Member

Assis. Prof. Hanan Hamid Ali– Member and supervisor