基于小波相位滤波的X光图像多层次模糊增强方法

Multilevel Fuzzy Enhancement Method for X-ray Images Based on Wavelet Phase Filtering

摘要

针对X光图像中细节尺度多样,采用单一的增强策略很难同时满足不同尺度细节增强需求的问题,提出一种基于小波相位滤波的X光图像多层次模糊增强方法.首先,通过直方图均衡化重新分配灰度值以提高对比度,并利用线性插值根据周围清晰像素信息对模糊局部区域的灰度值进行调整以恢复细节.其次,经灰度分布优化后的X光图像噪声点更显著,先利用Mallat算法对调整后的图像进行二维小波分解后,再结合小波相位滤波实现图像去噪,以增强图像的清晰度,实现图像质量优化.再次,将清晰度增强后的X光图像转化为直方图形式查询峰值点灰度级,定义模糊集合及隶属度函数,以模糊子集为增强层次,利用幂函数和多层次增强系数对隶属度进行优化,再遍历灰度级完成隶属度优化后实现图像细节增强.最后,将模糊域变化转回灰度域得到灰度更新结果,实现多层次模糊增强,突出图像细节和病变区域,提高诊断准确性.实验结果表明:该方法能有效凸显X光图像中的细节信息;在不同灰度级下,X光图像的频率保持在18~35Hz,频率波动相对平滑;平均梯度(MG)值可以保持在0.35以上.说明该方法对X光图像增强效果显著,有助于病变区域的精准有效分析,从而提高疾病诊断的准确性和效率.

Abstract

Aiming at the problem that the detail scales in X-ray images were diverse, it was difficult to meet the enhancement requirements of different scale details simultaneously using a single enhancement strategy, we proposed a multi-level fuzzy enhancement method for X-ray images based on wavelet phase filtering. Firstly, by using histogram equalization to redistribute grayscale values to improve contrast, and utilizing linear interpolation to adjust the grayscale values of blurry local areas based on clear pixel information around them to restore details. Secondly, after optimizing the grayscale distribution, the noise points in the X-ray image were more significant, we first used the Mallat algorithm to perform two-dimensional wavelet decomposition on the adjusted image, and then combined wavelet phase filtering to achieve image denoising, enhance image clarity, and optimize image quality. Thirdly, we converted the clarity enhanced X-ray image into a histogram format to query peak gray levels, defined fuzzy sets and membership functions, used fuzzy subsets as enhancement levels, optimized membership using power functions and multi-level enhancement coefficients, and then traversed gray levels to complete membership optimization, and achieved image detail enhancement. Finally, we reverted the fuzzy domain changes back to the grayscale domain to obtain grayscale update results, achieving multi-level fuzzy enhancement, highlighting image details and lesion areas, and improving diagnostic accuracy. The experimental results show that the proposed method can effectively highlight the detailed information in X-ray images. At different grayscale levels, the frequency of X-ray images remains between 18 Hz and 35 Hz, with relatively smooth frequency fluctuations. The mean gradient (MG) value can be maintained above 0.35. The proposed method has a significant enhancement effect on X-ray images, which helps to accurately and effectively analyze the lesion area, thereby improving the accuracy and efficiency of disease diagnosis.

关键词

直方图均衡算法 / 线性插值算法 / Mallat算法 / 二维小波分解 / 隶属度函数

Key words

histogram equalization algorithm / linear interpolation algorithm / Mallat algorithm / two-dimensional wavelet decomposition / membership function

参考文献

[1] 张云浩, 范凯, 黄从军, 等. 基于CT数据融合的三维可视化技术及数字虚拟诊疗在肾上腺肿瘤的应用研究[J]. 中国临床解剖学杂志, 2024, 42(2):201-207.

[2] (Zhang Y H, Fan K, Huang C J, et al. Research on the Application of Three-Dimensional Visualization Technology Based on CT Image Data Fusion and Digital Urology Virtual Diagnosis and Treatment in Adrenal Tumors[J]. Chinese Journal of Clinical Anatomy, 2024, 42(2):201-207.)

[3] 王燕, 张金峰, 王丽康, 等. 基于注意力机制与特征重建的水下图像增强[J]. 红外技术, 2024, 46(9):1006-1014.

[4] (Wang Y, Zhang J F, Wang L K, et al. Underwater Image Enhancement Based on Attention Mechanism and Feature Reconstruction[J]. Infrared Technology, 2024, 46(9):1006-1014.)

[5] Yu J X, Xue F B, Huo Z Q, et al. Combining Implicit and Explicit Priors for Zero-Reference Low-Light Image Enhancement and Denoising[J]. Multimedia Systems, 2025, 31(2):1-16.

[6] 王珍, 霍光磊, 兰海, 等. 基于卷积字典扩散模型的眼底图像增强算法[J]. 中国图象图形学报, 2024, 29(8):2426-2438.

[7] (Wang Z, Huo G L, Lan H, et al. Fundus Image Enhancement Algorithm Based on Convolutional Dictionary Diffusion Model[J]. Journal of Image and Graphics, 2024, 29(8):2426-2438.)

[8] Bala A A, Priya P A, Maik V. Hybrid Technique for Fundus Image Enhancement Using Modified Morphological Filter and Denoising Net[J]. The Journal of Supercomputing, 2024, 80(9):13317-13340.

[9] 王潇, 于炯, 杨嘉能, 等. 优化动态直方图均衡的水下图像增强方法[J]. 计算机仿真, 2022, 39(10):259-264.

[10] (Wang X, Yu J, Yang J N, et al. Optimized Dynamic Histogram Equalization for Underwater Image Enhancement[J]. Computer Simulation, 2022, 39(10):259-264.)

[11] 谢亚君. 超光谱图像数据中的正则化张量补全算法[J]. 工程数学学报, 2024, 41(6):1021-1040.

[12] (Xie Y J. Regularization Tensor Completion Algorithm for Hyperspectral Image Data[J]. Chinese Journal of Engineering Mathematics, 2024, 41(6):1021-1040.)

[13] 刘显德, 李笑. 任意大小图像的量子描述及双线性插值方法[J]. 计算机工程与设计, 2024, 45(8):2423-2432.

[14] (Liu X D, Li X. Quantum Representation and Bilinear Interpolation Method of Image with Arbitrary Size[J]. Computer Engineering and Design, 2024, 45(8):2423-2432.)

[15] Xie Z J, Yu D, Zhan C S, et al. Ball Screw Fault Diagnosis Based on Continuous Wavelet Transform and Two-Dimensional Convolution Neural Network[J]. Measurement and Control, 2023, 56(3/4):518-528.

[16] 田博文, 张志禹, 杨梦飞. 基于多次滑动均值滤波的混合储能功率分配与定容研究[J]. 电工技术学报, 2024, 39(5):1548-1564.

[17] (Tian B W, Zhang Z Y, Yang M F. Research on Hybrid Energy Storage Power Allocation and Capacity Determination Based on Multiple Moving Average Filtering[J]. Transactions of China Electrotechnical Society, 2024, 39(5):1548-1564.)

[18] 曾顶, 殷君君, 杨健. 基于融合距离的极化SAR图像非局部均值滤波[J]. 系统工程与电子技术, 2024, 46(5):1493-1502.

[19] (Zeng D, Yin J J, Yang J. Nonlocal Means Filter for Polarimetric SAR Images Based on Fusion Distance[J]. Systems Engineering and Electronics, 2024, 46(5):1493-1502.)

[20] 尹晓君, 冯涛, 张少谱. 基于自信息熵的直觉模糊决策系统的属性约简[J]. 重庆邮电大学学报(自然科学版), 2024, 36(3):513-523.

[21] (Yin X J, Feng T, Zhang S P. Attribute Reduction Based on the Self-information Entropy of Intuitionistic Fuzzy Decision Systems[J]. Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition), 2024,36(3):513-523.)

基金资助

广东省教育教学规划项目(2024GXJK531)