In the current era of data-intensive applications, including OTT services, IoT, and autonomous systems, efficient image compression is indispensable in order to minimize bandwidth consumption while preserving visual quality. Conventional compression techniques frequently fail to satisfactorily balance compression ratios and the preservation of critical image details. This work introduces a novel adaptive image compression method that is area-aware and utilizes a dual-background classification system to improve data preservation. The method classified areas into major and minor backgrounds by aggregating image regions based on visual characteristics. It applied aggressive quantization to less salient regions and refined compression techniques for critical details. A saliency map, reflecting human visual perception, guides this process, ensuring the preservation of the most visually significant information. By customizing quantification to the visual priorities of a particular region, the proposed methodology enhances the quality of images and the efficacy of compression. Extensive testing demonstrates that the area- aware approach outperforms traditional compression algorithms, enhancing the visual experience and significantly reducing data traffic. This research work mainly focuses on the reducing of data size and simultaneously preserving the image quality at required regions by using of adaptive compression techniques. This is particularly relevant for applications that necessitate high-quality image transmission in a data-driven world.
References
1.
Zhang L, Li P. A review of video coding and image compression techniques for real-time applications. J Vis Commun Image Represent. 2019;1–12.
2.
V. S, S. A, G. S, S. S. Image Based Authentication Using Zero-Knowledge Protocol. International Academic Journal of Innovative Research. 2024;11(1):01–5.
3.
Yan H, Zhang L. Efficient image compression in IoT applications: A survey. IEEE Access. 2018;53910–8.
4.
Kadhum AN. Comparison Between the Yolov4 and Yolov5 Models in Detecting Faces while Wearing a Mask. International Academic Journal of Science and Engineering. 2024;11(1):1–8.
5.
Ahmed N, Natarajan T, Rao KR. Discrete Cosine Transform. IEEE Transactions on Computers. 1974;C–23(1):90–3.
6.
Sethupathi S, Singaravel G, Gowtham S, Kumar T. Cluster Head Selection for the Internet of Things (IoT) in Heterogeneous Wireless Sensor Networks (WSN) Based on Quality of Service (QoS) By Agile Process. International Journal of Advances in Engineering and Emerging Technology. 2024;(1):1–5.
7.
Bross B, Luthra A. High Efficiency Video Coding (HEVC) compression standard. IEEE Trans Circuits Syst Video Technol. 2016;(1):13–30.
8.
Yunuskhodjaeva K, Almatova U, Karimov N, Khaydarova S, Jalolova S, Bahodir A, et al. THE ROLE OF DIGITAL TECHNOLOGY IN ARCHIVING ETHNO-TOURISTIC LANDMARKS. Archives for Technical Sciences. 2025;32(1):15–22.
9.
Chen W, Zhang X. Human visual perception and its application to image processing. Image Vis Comput. 2015;12–20.
10.
Giang N, Im J, Kim D, Jung M, Kastner W. Integrating the EPCIS and Building Automation System into the Internet of Things: A Lightweight and Interoperable Approach. J Wirel Mob Networks Ubiquitous Comput Dependable Appl. 2015;(1):56–73.
11.
Lenc K, Hough J. Adaptive image compression based on perceptual importance. 2017;2025–33.
12.
Bansal M, Naidu D. Dynamic Simulation of Reactive Separation Processes Using Hybrid Modeling Approaches. Engineering Perspectives in Filtration and Separation. Jun. 2024;8–11.
13.
Anwar M, Ahmed M. Performance optimization in IoT-based image compression systems. IEEE Internet Things J. 2021;(10):8429–37.
14.
Ahmed N, Rao K. Discrete Cosine Transform and its applications in image compression. Signal Process. 2018;(3):233–41.
15.
Sayood K. Introduction to data compression. 2017;
16.
Itti L, Koch C. Computational modelling of visual attention. Nature Reviews Neuroscience. 2001;2(3):194–203.
17.
Wang L, Yang C. Saliency-driven image compression. IEEE Trans Circuits Syst Video Technol. 2019;(8):2425–37.
18.
Zhang W, Liu Z. A saliency-guided image compression algorithm based on deep learning. IEEE Trans Multimedia. 2017;(6):1291–302.
19.
Tavares M, Brito F. Region-based image compression: A survey. J Vis Commun Image Represent. 2021;102935.
20.
Li X, Wang L. Dynamic region-based encoding for adaptive image compression. IEEE Trans Image Process. 2018;(12):5857–69.
21.
Gao F, Xie L. Perceptual image compression using saliency maps. J Electron Imaging. 2020;(5):53021.
22.
Hu Q, Yang Z. Saliency-guided adaptive image compression with perceptual importance. 2019;125–34.
23.
Liao Z, Zhang D. Deep learning-based saliency detection for image compression. IEEE Trans Neural Netw Learn Syst. 2020;(3):1022–34.
24.
Xu Q, Li S. Hybrid compression strategies using deep learning and perceptual saliency for video streaming. Multimed Tools Appl. 2022;(7):8885–900.
25.
Gholami A, Hamid F. Deep perceptual image compression for video applications. IEEE Trans Circuits Syst Video Technol. 2021;(11):4156–69.
26.
Dhanasekaran R, Nagendran S. Optimization strategies for OTT streaming in bandwidth-constrained environments. Int J Netw Manag. 2020;(5):2104.
27.
Zhao Z, Liu F. Real-time visual data processing for autonomous driving: Challenges and solutions. IEEE Trans Intell Transp Syst. 2021;(6):3565–74.
28.
Kuo C, Lin W. The JPEG algorithm and its variants: A review. Signal Process Image Commun. 2018;140–52.
29.
Bossen F. AV1 video codec overview and its impact on video streaming. IEEE Trans Multimedia. 2018;(11):2931–45.
30.
Li Y, Zhang Z. A perceptually-driven image compression model using region-specific classification. J Vis Commun Image Represent. 2019;296–308.
31.
Wang H, Li X. Bandwidth-efficient video compression techniques for mobile OTT services. Mob Netw Appl. 2020;(3):734–44.
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.
,
