A Triple Approach To Digital Image Processing: Enhancement, Encryption And Compression Using Artificial Intelligence

Dr. Riyad Mubarak Abdullah

doi:10.29284/h4rjg270

Authors

Dr. Riyad Mubarak Abdullah Computer Sciences Department College of Education for Pure Sciences University of Al-Hamdaniya

DOI:

https://doi.org/10.29284/h4rjg270

Keywords:

Artificial Intelligence, Machine Learning, Image Processing, Image Enhancement, Image Encryption, Image Compression, PSNR, SSIM, Compression Ratio, Ensemble Learning.

Abstract

Digital image processing serves a vital function in medical imaging, multimedia and cybersecurity. But common approaches seem too rigid. Though AI-inclined approaches may enhance the encryption and compression processes an all-included prediction model is not yet utilized. This study forms a model that is AI-inclined with the use of Random Forest, Gradient Boosting, Neural Networks and XGBoost. It asserts that Gradient Compression ratio, PSNR, and SSIM can improve precision via stacked ensemble learning, as well as test performance with the use of R² Score, MAE, and MSE. A dataset comprising of 300 images with elements like the Encryption Strength, Noise Level, Resolution, Entropy, and Sharpening Factor was applied. The models were tried and put to training in an 80-2- way, containing hyperparameters tuned for optimization. The feature vitality was analysed via XGBoost and Random Forest to find out the essential predictors. The model used obtained splendid precision ofr PSNR (96.70%) and SSIM (((>(&%). To validate its efficacy in the image quality estimate. Compression proportion was at 14.07% the lowest indicating a dependency and structural complexity of the compression. Entropy and resolution width indicated the major predictors of PNSR and SSIM, while Encryption power was predicted Compression Ratio. This study offers an AI-prediction framework that provide a detailed image processing structure with image processing quality. It attains high precision for PNSR and SSIM as a result it enhances image quality evaluation. The paper finds fundamental qualities which impacts the image processing function, to facilitate practical optimization. It can also highlight the basic challenges in compression proportion prediction to suggest enhancements via deep learning. The projected AI-framework improves the image processing with maximum high precision, consistently to predict PSNR and SSIM. However, the ratio of the prediction needs to be fine-tuned, which emphasizes the execution of deep learning approaches. The utilization of AI models should be added to in the learning procedures as well as deep learning procedures to enhance accuracy and increase its usage in the medical imaging, multimedia and cybersecurity processing.

References

1. A. K. Jain, “Fundamentals of Digital Image Processing,” Prentice Hall, 2020.

2. A. Roy and N. Patel, “Image Super-Resolution Using Deep Learning: A Review,” IEEE Transactions on Computational Imaging, vol. 8, pp. 1184-1199, 2023.

3. A. Singh and P. Das, “AI-Based Image Processing Framework for Secure Encryption,” IEEE Transactions on Information Forensics and Security, vol. 17, pp. 2651-2662, 2022.

4. Al-Abaidy, S. A. F. (2021). Optimal Use of ANN In the Integration Between Digital Image Processing and Encryption Technique. Turk. J. Comput. Math. Educ. (TURCOMAT), 12, 950-958.

5. C. Sun and B. Wang, “Analyzing Image Compression Performance with Reinforcement Learning,” Pattern Recognition Letters, vol. 154, pp. 12-21, 2022.

6. C. Y. Chen, T. S. Lin, and K. C. Chiu, “AI-Based Image Enhancement Techniques for Low-Light Images,” Pattern Recognition Letters, vol. 156, pp. 105-112, 2022.

7. F. Zhang, L. Cheng, and W. Guo, “Neural Networks for Structural Similarity (SSIM) Estimation,” IEEE Transactions on Image Processing, vol. 30, pp. 5072-5083, 2022.

8. H. Wang and M. Li, “Noise Removal and Image Enhancement Using AI-Based Super-Resolution Models,” Pattern Recognition, vol. 133, 108879, 2023.

9. H. Wang, Y. Lin, and X. Yang, “Deep Learning for Image Compression: A Review,” IEEE Access, vol. 9, pp. 18067–18081, 2021.

10. J. Xu and Z. Zhang, “Optimization of PSNR Using Hybrid Deep Learning Models,” Neural Computing & Applications, vol. 35, pp. 10327-10345, 2023.

11. Kshetri, N., Rahman, M. M., Rana, M. M., Osama, O. F., & Hutson, J. (2024). algoTRIC: Symmetric and asymmetric encryption algorithms for Cryptography A comparative analysis in AI era. arXiv preprint arXiv:2412.15237.

12. Kumar, S., & Sharma, D. (2024). A chaotic based image encryption scheme using elliptic curve cryptography and genetic algorithm. Artificial Intelligence Review, 57(4), 87.

13. L. Zhang, W. Xu, and S. Chen, “Hybrid AI Models for Image Feature Selection,” Multimedia Tools and Applications, vol. 82, no. 11, pp. 15672–15688, 2023.

14. L. Zhou and T. Liu, “Improving Image Compression Ratio with Generative Adversarial Networks,” Neural Networks, vol. 160, pp. 342-355, 2023.

15. M. Elgendy, “Digital Image Compression and Enhancement Techniques: A Review,” Springer Journal of Imaging Science, vol. 16, no. 3, pp. 315–328, 2022.

16. M. Sharma and A. Verma, “Predicting Image Quality Using Artificial Intelligence,” Journal of Visual Communication and Image Representation, vol. 87, 103079, 2022.

17. P. Singh and V. Gupta, “Feature Engineering in Image Processing: An AI Approach,” IEEE Transactions on Multimedia, vol. 25, no. 1, pp. 98–113, 2022.

18. Pandey, B. K., Pandey, D., Wairya, S., Agarwal, G., Dadeech, P., Dogiwal, S. R., & Pramanik, S. (2022). Application of integrated steganography and image compressing techniques for confidential information transmission. Cyber security and network security, 169-191.

19. Panigrahy, A. K., Maniyath, S. R., Sathiyanarayanan, M., Dholvan, M., Ramaswamy, T., Hanumanthakari, S., ... & Swain, R. (2024). A faster and robust artificial neural network-based image encryption technique with improved SSIM. IEEE Access, 12, 10818-10833.

20. Pourasad, Y., & Cavallaro, F. (2021). A novel image processing approach to enhancement and compression of X-ray images. International Journal of Environmental Research and Public Health, 18(13), 6724.

21. R. C. Gonzalez and R. E. Woods, “Digital Image Processing,” Pearson, 2018.

22. R. Mehta and S. Jain, “Deep Learning for High-Performance Image Quality Estimation,” IEEE Signal Processing Letters, vol. 29, pp. 75-79, 2022.

23. Rong, R., Shravage, C., Mary, G. S., Blesswin, A. J., Gayathri, M., Karunya, A. C. E., ... & Sambas, A. (2024). Enhanced Semantic Visual Cryptography with AI-driven error reduction for improved two-dimensional image quality and security. Measurement Science and Technology, 35(10), 105405.

24. S. Das and R. Bhandari, “Efficient Lossless Image Compression Using Machine Learning,” Multimedia Tools and Applications, vol. 81, no. 7, pp. 9595–9615, 2023.

25. Sumathi, M. S., Jain, V., Kumar, G. K., & Khan, Z. Z. (2023). Using artificial intelligence (ai) and internet of things (iot) for improving network security by hybrid cryptography approach.

26. Thalapathiraj, S., Arunnehru, J., Bharathi, V. C., Dhanasekar, R., Vijayaraja, L., Kannadasan, R., ... & Khan, A. A. (2024). A novel approach for encryption and decryption of digital imaging and communications using mathematical modelling in internet of medical things. The Journal of Engineering, 2024(12), e70038.

27. Tian, H., Yuan, Z., Zhou, J., & He, R. (2024). Application of Image Security Transmission Encryption Algorithm Based on Chaos Algorithm in Networking Systems of Artificial Intelligence. In Image Processing, Electronics and Computers (pp. 21-31). IOS Press.

28. X. He and J. Zhao, “Automating PSNR and SSIM Evaluation Using Neural Networks,” Neural Processing Letters, vol. 55, pp. 171–189, 2022.

29. X. Zhang, J. Li, and H. Wang, “A Survey of Image Encryption Algorithms Using Deep Learning,” ACM Computing Surveys, vol. 54, no. 5, 2023.

30. Y. Kim et al., “Machine Learning-Based Image Enhancement Techniques for Low-Bit Depth Images,” Computer Vision and Image Understanding, vol. 223, 103561, 2023.