Profile Image
Assist. Lecturer

Taha Yassin Abdulqader

Research Interests

|

Gender MALE
Place of Work Mosul Technical Institute
Position مقرر القسم
Qualification Master
Speciality Computer Science
Email taha.yassin@ntu.edu.iq
Phone 07737502494
Address حي المأمون, Mosul, Mosul, Iraq

Skills

Image Processing (80%)
Watermarking (85%)
Data Hiding (80%)
Machine Learning (70%)

Publications

Enhancing Image Recognition with Quaternion Neural Networks: A Novel Approach to Color Layer Integration
Apr 25, 2025

Journal Journal of Image and Graphics

publisher Scopus

DOI 10.18178/joig.13.2.190-197

Issue 2301-3699 (Print); 2972-3973 (Online)

Volume 13, No. 2, 2025

Neural networks have been widely used in image recognition tasks, and this study explores a novel method— Quaternion Neural Networks (QNNs)—for enhancing performance. Using quaternion algebra, QNNs minimize the number of trainable parameters, leading to more compact models and quicker training times than Convolutional Neural Network CNNs. Therefore, color layers might potentially improve network performance by learning common parameters through input as linked values. Experiments assess learning processes by taking into account the roles of color and structure as well as stability in the presence of noisy visuals. According to the experimental results, QNNs retain an accuracy of 85% in the absence of noise, but at a noise level of σ = 0.30, accuracy dropped to 70%. Notwithstanding this, the network proved to be effective in learning structural information, exhibiting robustness against noise and disturbances in texture and color, hence confirming its suitability for wider image recognition uses. The paper establishes a proof of concept for the effectiveness of quaternion networks that will open up new avenues for research and possible uses that could outperform or supplement traditional networks.

Read Publication

Robust Image Watermarking for Tamper Detection and Self-Recovery Using SVD and RSA Methods
Jul 25, 2024

Journal CENTRAL ASIAN JOURNAL OF MATHEMATICAL THEORY AND COMPUTER SCIENCES

Issue 03

Volume 05

To The paper proposes an Image watermarking technique for identifying and self￾recovering tampered images. The system identifies tampered images by comparing the SVD values of 4X4 blocks and average pixel intensities of 2×2 blocks. In the process of SVD computation, the RGB channel images are divided into 4X4 blocks, after which a further 2X2 blocks division is executed for determination of average pixel intensity. Within the same block, tamper-detection data is entered, whereas the self-recovery data is scattered all over the image utilising inverse and RSA techniques for neighborhood block-based recovery. This method assures easy long-term self￾healing. The outputs produced from testing with 15 multiple host images in varied attacks were constantly performing better with a PSNR ratio upto an average of 45 dB.

Read Publication