The sparsity and texture distribution of an image have a significant impact on its compression performance. To achieve effective compression of fundus images, this paper proposes a content adaptive block based soft compression algorithm (ABSC) based on soft compression algorithm, and improves the gradient adaptive predictor. Firstly, the image is subjected to reversible color component transformation to obtain YUV components, and then adaptive predictive encoding is applied to different components. Secondly, the Y component is differentiated into subblocks with different features based on variance, appropriate predictors are selected, and subblocks with the same continuous prediction mode are concatenated and merged to form a new set of subblocks. Finally, the corresponding predictors are selected for encoding the subblocks of the set according to the prediction mode, thus achieving adaptive block coding. The experimental results show that compared with the soft compression algorithm, the compression ratio of our algorithm on DRIVE dataset, CHASEDB1 dataset and the dataset collected by the research group is improved by 6.8%, 4.3%, and 4.1%, respectively, and is superior to typical traditional lossless compression algorithms, verifying the good performance of the new algorithm in lossless compression of fundus images.
WANGZhen, HUOGuanglei, LANHai, et al. Fundus image enhancement algorithm based on convolutional dictionary diffusion model[J]. Journal of Image and Graphics, 2024, 29(8): 2426-2438.(in Chinese)
LINMin, LINQinghao, WENGXiaoyu, et al. Improved universal lossless intra-frame coding algorithm for H.26X[J]. Journal of Harbin Institute of Technology, 2021, 53(8): 125-131.(in Chinese)
HUANGSheng, XIANGSihao, HUFeng, et al. Adaptive lossless compression of capsule endoscopy image with irregular texture[J].Computer Engineering, 2022, 48(10): 21-27. (in Chinese)
[7]
ZHUC, ZHANGH, TANGY. Lossless image compression algorithm based on long short-term memory neural network[C]//2020 5th international conference on computational intelligence and applications (ICCIA). IEEE, 2020: 82-88.
[8]
STAROSOLSKIR. New simple and efficient color space transformations for lossless image compression[J]. Journal of Visual Communication and Image Representation, 2014, 25(5): 1056-1063.
[9]
LUOZ, WANY. An efficient framework for lossless color image compression[C]//2016 International Conference on Audio, Language and Image Processing (ICALIP). IEEE, 2016: 380-384.
[10]
PATHAKK C, SARVAIYAJ N, DARJIA D. Enhanced hierarchical prediction for lossless medical image compression in the field of telemedicine application[M]. Cham: Springer International Publishing, 2023: 207-229.
XING, FANP. Soft compression for lossless image coding based on shape recognition[J]. Entropy, 2021, 23(12): 1680.
[13]
KOC B, ARNAVUTZ, SARKARD, et al. A new technique for lossless compression of color images based on hierarchical prediction, inversion, and context adaptive coding[J]. Journal of Electronic Imaging, 2019, 28(5): 053007-053007.
[14]
马智忠.基于位图的彩色图像无损压缩算法研究[D].兰州: 兰州大学, 2017.
[15]
WEINBERGERM J, SEROUSSIG, SAPIROG. The LOCO-I lossless image compression algorithm: Principles and standardization into JPEG-LS[J]. IEEE Transactions on Image processing, 2000, 9(8): 1309-1324.
[16]
WUX, MEMONN. CALIC-a context based adaptive lossless image codec[C]//1996 IEEE international conference on acoustics, speech, and signal processing conference proceedings. IEEE, 1996: 1890-1893.
ZHANGHang, YUSu. Research on bank card number recognition based on Canny edge detection[J]. Computer & Digital Engineering, 2024, 52(6): 1837-1841. (in Chinese)
GAOYingqi, GUOSong, LINing, et al. Arteriovenous classification method in fundus images based on semantic fusion[J].Journal of Image and Graphics, 2020, 25(10): 2259-2270. (in Chinese)
[21]
CHRISTOPOULOSC, SKODRASA, EBRAHIMIT. The JPEG2000 still image coding system: an overview[J]. IEEE Transactions on Consumer Electronics, 2000, 46(4): 1103-1127.