Image compression scheme based on region of interest recognition

Abstract

With the development of networks, many fields now demand higher quality in specific image areas, such as main characters in photos, lesion areas in medical images, and features in remote sensing. At the same time, these fields need to manage data storage and transmission effectively for subsequent analysis and application. In order to meet the demand for image compression in modern society, this paper proposes an image compression scheme based on region of interest (ROI) recognition, dividing images into ROI and non-ROI regions and processing them with lossless and lossy compression, respectively, to improve efficiency and ensure ROI quality. The scheme uses the object detection network YOLOv4 to recognize the ROI of the image, designs an image block difference transformation to transform the image pixels into smaller values, designs a lossless DC encoding for the ROI of the image based on the difference between adjacent pixels, and designs a lossy DC encoding with quantization coding for the non-ROI of the image. Experimental analysis of uncompressed images shows the scheme effectively enhances compression efficiency while maintaining ROI quality, proving its practical value.