Optimized Deep Learning-Based Image Compression Using Convolutional Autoencoders
DOI:
https://doi.org/10.64137/31079458/IJCSEI-V2I1P106Keywords:
Deep Learning, Image Compression, Autoencoder, PSNR, SSIM, Convolutional Neural NetworkAbstract
This study presents an optimized image compression framework based on deep learning, specifically a convolutional autoencoder. Traditional compression methods such as JPEG and PNG rely on fixed mathematical transformations, which often lead to quality degradation at high compression ratios. To address these limitations, the proposed system adopts a data-driven approach that learns compact and efficient image representations through end-to-end training. The framework integrates convolutional encoding, latent space quantization, entropy coding, and decoding mechanisms to ensure efficient storage and transmission. Experimental evaluation was conducted using benchmark datasets, and performance was assessed using metrics such as Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and compression ratio. The results demonstrate that the model achieves a compression ratio exceeding 133:1 with minimal perceptual quality loss, maintaining stable PSNR and SSIM values across varying compression strategies. Furthermore, the model exhibits fast convergence, strong generalization capability, and real-time processing performance, making it suitable for deployment in resource-constrained environments. Despite challenges such as computational training cost and minor loss of high-frequency details, the proposed approach significantly improves compression efficiency and visual quality. These findings highlight the potential of deep learning–based methods in advancing next-generation image compression systems.
References
[1] Afrin, and M. A. Mamun, "A Comprehensive Review of Deep Learning Methods for Hyperspectral Image Compression," 2024 3rd International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE), Gazipur, Bangladesh, pp. 1-6, 2024, doi: https://doi.org/10.1109/ICAEEE62219.2024.10561710
[2] M. Zhang, H. Li, and Q. Wu, “Recent advances in traditional and deep image compression techniques,” IEEE Access, vol. 11, pp. 38901–38915, 2023. https://doi.org/10.1109/ACCESS.2023.3269123.
[3] A.Kumar and S. Singh, “Data-driven image compression for next-generation multimedia systems,” IEEE Transactions on Multimedia, vol. 25, pp. 3456–3468, 2023. doi:10.1109/TMM.2023.3271120.
[4] J. Chen, Z. Wang, and L. Zhang, “Convolutional autoencoder-based optimized image compression,” IEEE Transactions on Image Processing, vol. 32, pp. 1456–1468, 2023. doi:10.1109/TIP.2023.3256789.
[5] H. Park and J. Lee, “Deep neural network approaches for efficient image compression,” IEEE Access, vol. 12, pp. 11234–11248, 2024. doi:10.1109/ACCESS.2024.3345678.
[6] H. Cheng, Z. Zhang, and F. Chen, “Attention-guided transformer for learned image compression,” IEEE Transactions on Multimedia, vol. 26, pp. 1123–1135, 2024. doi:10.1109/TMM.2024.3357890.
[7] S. Kim and M. Lee, “Efficient vision transformer for scalable image compression,” IEEE Access, vol. 12, pp. 22345–22358, 2024. doi:10.1109/ACCESS.2024.3361122.
[8] X. Zhao, Y. Li, and Q. Zhang, “Content-adaptive image compression using attention mechanisms,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 34, no. 2, pp. 1456–1468, 2025. doi:10.1109/TCSVT.2025.3378901.
[9] R. Patel and K. Singh, “Lightweight deep image compression for edge devices,” IEEE Access, vol. 13, pp. 55678–55690, 2025. doi:10.1109/ACCESS.2025.3384567.
[10] A.Hassan, M. Ali, and S. Noor, “Hybrid entropy-deep learning framework for optimized image compression,” IEEE Transactions on Image Processing, vol. 34, pp. 1023–1035, 2025. doi:10.1109/TIP.2025.3390012.
[11] Mustafa Al-Khafaji and Nehad T A Ramaha, “Hybrid deep learning architecture for scalable and high-quality image compression,” Scientific Reports, vol. 15, no. 1, Jul. 2025, doi: https://doi.org/10.1038/s41598-025-06481-0.
[12] H. Liao and Y. Li, “LC-TMNet: learned lossless medical image compression with tunable multi-scale network,” PeerJ Computer Science, vol. 10, p. e2511, Dec. 2024, doi: https://doi.org/10.7717/peerj-cs.2511.
[13] H. Sun et al., “A survey and benchmark evaluation for neural-network-based lossless universal compressors toward multi-source data,” Front. Comput. Sci., vol. 19, 2025, Doi: https://doi.org/10.1007/s11704-024-40300-5.
[14] Z. Duan, M. A. F. Hossain, J. He, and F. Zhu, “Balancing the encoder and decoder complexity in image compression for classification,” EURASIP Journal on Image and Video Processing, vol. 2024, no. 1, Oct. 2024, doi: https://doi.org/10.1186/s13640-024-00652-1.
[15] X. Zhang and X. Wu, “LVQAC: Lattice Vector Quantization Coupled With Spatially Adaptive Companding for Efficient Learned Image Compression,” Thecvf.com, pp. 10239–10248, 2023, Accessed: Mar. 27, 2026. [Online]. Available: https://openaccess.thecvf.com/content/CVPR2023/html/Zhang_LVQAC_Lattice_Vector_Quantization_Coupled_With_Spatially_Adaptive_Companding_for_CVPR_2023_paper.html
[16] P. Abhiram and R. Khetavath, “Efficient deep learning models for image compression in embedded systems,” IEEE Access, vol. 12, pp. 4021–4035, 2024.
[17] M. Yasin and A. Abdulazeez, “Deep neural networks in image compression: Methods and performance,” Int. J. Comput. Vision Signal Process., vol. 8, no. 1, pp. 1–14, 2021.
[18] A.Mobeen, S. Gupta, and R. Kumar, “Transform and deep learning-based approaches in image compression,” Int. J. Inf. Technol., vol. 13, no. 3, pp. 1511–1522, 2021.
[19] Prativadibhayankaram, S. J. Kim, and M. Lee, “Deep architectures for enhanced perceptual quality in learned image compression,” IEEE Trans. Circuits Syst. Video Technol., vol. 33, no. 5, pp. 1789–1802, 2023.
[20] M. Naseri and F. Akbari, “Deep learned compression for wireless image transmission,” IEEE Commun. Lett., vol. 28, no. 3, pp. 615–619, 2024.
