基于卷积神经网络的数字图像模糊增强算法

doi:10.13229/j.cnki.jdxbgxb20210561

摘要/Abstract

摘要：

为了解决数字图像灰度信息丢失、边缘模糊导致的图像效果不佳等问题，提出基于卷积神经网络的数字图像模糊增强算法。以图像灰度级作为论域构建特征模糊集合，拟定模糊隶属度，基于模糊熵计算图像边缘灰度值，同时，构建不同光照环境下限制对比度均衡派生图、伽马转换派生图、对数转换派生图、两通道增强派生图，借此微小调整图像像素方差，强化细节信息的表达，增强隶属度；最后，通过卷积神经网络筛选图像内渡越点，以此调整图像内对比度、平均亮度与像素方差，实现数字图像的模糊增强。实验结果表明，采用本文方法增强数字图像模糊的效果较好、且不易受环境影响。

关键词: 卷积神经网络, 数字图像, 模糊增强, 模糊隶属度, 对比度, 渡越点

Abstract:

In order to solve the problems of gray information loss and poor image effect caused by edge blur of digital image， a digital image fuzzy enhancement algorithm based on convolution neural network is proposed. At the same time， restricted contrast balanced derivative image， gamma conversion derivative image， logarithmic conversion derivative image and two-channel enhancement derivative image are constructed under different lighting environments， so as to slightly adjust the variance of image pixels and enhance the expression of detail information. Finally， the convolution neural network is used to filter the transition points in the image， so as to adjust the contrast， average brightness and pixel variance in the image， and the fuzzy enhancement of the digital image was realized. Experimental results show that the proposed method can enhance the effect of digital image blur better， and is not easy to be affected by the environment.

Key words: convolutional neural network, digital image, fuzzy enhancement, fuzzy membership degree, contrast, transit point

中图分类号:

TP92

郭志军,刘帅. 基于卷积神经网络的数字图像模糊增强算法[J]. 吉林大学学报(工学版), 2022, 52(10): 2399-2404.

Zhi-jun GUO,Shuai LIU. Digital image fuzzy enhancement algorithm based on convolutional neural network[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(10): 2399-2404.

图/表 2

图1

图2

参考文献 17

1	傅博, 王瑞子, 王丽妍, 等. 基于深度卷积神经网络的水下偏色图像增强方法[J]. 吉林大学学报:理学版, 2021, 59(4): 891-899.
	Fu Bo, Wang Rui-zi, Wang Li-yan, et al. Enhancement method of underwater color cast image based on deep convolutional neural network[J]. Journal of Jilin University (Science Edition), 2021, 59(4): 891-899.
2	张慧, 常莉红, 马旭, 等. 一种基于曲波变换与引导滤波增强的图像融合方法[J]. 吉林大学学报:理学版, 2020, 58(1): 113-119.
	Zhang Hui, Chang Li-hong, MA Xu, et al. An image fusion method based on curvelet transform and guided filter enhancement[J]. Journal of Jilin University (Science Edition), 2020, 58(1): 113-119.
3	冯相辉. 一种改进的同态滤波图像增强算法[J]. 重庆邮电大学学报:自然科学版, 2020, 32(1): 138-145.
	Feng Xiang-hui. An improved homomorphic filtering image enhancement algorithm[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2020, 32(1): 138-145.
4	韩梦妍, 李良荣, 蒋凯. 基于光照图估计的Retinex低照度图像增强算法[J]. 计算机工程, 2021, 47(10): 201-206.
	Han Meng-yan, Li Liang-rong, Jiang Kai. Retinex low-illumination image enhancement algorithm based on light image estimation[J]. Computer Engineering, 2021, 47(10): 201-206.
5	刘文, 杨梅芳, 聂江天, 等. 基于局部生成对抗网络的水上低照度图像增强[J]. 计算机工程, 2021, 47(5): 16-23.
	Liu Wen, Yang Mei-fang, Nie Jiang-tian, et al. Low-light maritime image enhancement based on local generative adversarial network[J]. Computer Engineering, 2021, 47(5): 16-23.
6	房楚尧, 周知, 赵家培, 等. 基于再模糊理论的航拍图像质量检测方法[J]. 计算机工程与应用, 2019, 55(7): 199-206.
	Fang Chu-yao, Zhou Zhi, Zhao Jia-pei, et al. Detection method of aerial image quality based on re-blur theory[J]. Computer Engineering and Applications, 2019, 55(7): 199-206.
7	曹锦纲, 李金华, 郑顾平. 基于生成式对抗网络的道路交通模糊图像增强[J].智能系统学报, 2020, 15(3): 491-498.
	Cao Jin-gang, Li Jin-hua, Zheng Gu-ping. Enhancement of blurred road-traffic images based on generative adversarial network[J]. CAAI Transactions on Intelligent Systems, 2020, 15(3): 491-498.
8	于天河, 李昱祚, 兰朝凤. 基于顶帽底帽变换的仿生图像增强算法[J].计算机应用, 2020, 40(5): 1440-1445.
	Yu Tian-he, Li Yu-zuo, Lan Chao-feng. Bionic image enhancement algorithm based on top-bottom hat transformation[J]. Journal of Computer Applications, 2020, 40(5): 1440-1445.
9	侯向丹, 郑梦敬, 刘洪普, 等. 基于剪切波和改进Pal-King的医学图像增强算法研究[J]. 激光与光电子学进展, 2019, 56(3): 123-129.
	Hou Xiang-dan, Zheng Meng-jing, Liu Hong-pu, et al. Medical image enhancement algorithm based on shearlet domain and improve Pal-King algorithm[J]. Laser & Optoelectronics Progress, 2019, 56(3): 123-129.
10	吴婷. 基于非均匀有序直方图和锐化的红外图像增强[J]. 半导体光电, 2020, 41(1): 135-140.
	Wu Ting. Infrared image enhancement based on non-uniform ordered histogram and sharpening[J]. Semiconductor Optoelectronics, 2020, 41(1): 135-140.
11	刘永娜, 王利绒. 基于激光传感器的模糊图像增强研究[J]. 激光杂志, 2020, 41(3): 122-125.
	Liu Yong-na, Wang Li-rong. Research on fuzzy image enhancement based on laser sensor[J]. Laser Journal, 2020, 41(3): 122-125.
12	陈晓文, 刘光帅, 刘望华, 等. 结合LoG边缘检测和增强局部相位量化的模糊图像识别[J]. 计算机科学, 2020, 47(12): 197-204.
	Chen Xiao-wen, Liu Guang-shuai, Liu Wang-hua. Blurred image recognition based on log edge detection and enhanced local phase quantization[J]. Computer Science, 2020, 47(12): 197-204.
13	林森, 刘世本, 唐延东. 多输入融合对抗网络的水下图像增强[J].红外与激光工程, 2020, 49(5): 217-225.
	Lin Sen, Liu Shi-ben, Tang Yan-dong. Multi-input fusion adversarial network for underwater image enhancement[J]. Infrared and Laser Engineering, 2020, 49(5): 217-225.
14	王成, 张艳超. 像素级自适应融合的夜间图像增强[J]. 液晶与显示, 2019, 34(9): 888-896.
	Wang Cheng, Zhang Yan-chao. Night image enhancement based on pixel level adaptive image fusion[J]. Chinese Journal of Liquid Crystals and Displays, 2019, 34(9): 888-896.
15	王红茹, 张弓, 卢道华, 等. 基于背景光估计与颜色修正的水下图像增强[J]. 计算机工程, 2020, 46(10): 253-258.
	Wang Hong-ru, Zhang Gong, Lu Dao-hua, et al. Underwater image enhancement based on background light estimation and color correction[J]. Computer Engineering, 2020, 46(10): 253-258.
16	刘明珠, 苏桃宇, 王依宁. 压扩多尺度Retinex图像增强算法研究[J]. 哈尔滨理工大学学报, 2020, 25(5): 93-99.
	Liu Ming-zhu, Su Tao-yu, Wang Yi-ning. Research on compressed multiscale retinex image enhancement algorithms[J]. Journal of Harbin University of Science and Technology, 2020, 25(5): 93-99.
17	孙启隆, 于萍, 司振惠, 等. 基于暗通道的沙尘图像增强算法[J]. 吉林大学学报:理学版, 2021, 59(5): 1179-1187.
	Sun Qi-long, Yu Ping, Si Zhen-hui, et al. Dust image enhancement algorithm based on dark channel[J]. Journal of Jilin University(Science Edition), 2021, 59(5): 1179-1187.

相关文章 15

[1]	申铉京,张雪峰,王玉,金玉波. 像素级卷积神经网络多聚焦图像融合算法[J]. 吉林大学学报(工学版), 2022, 52(8): 1857-1864.
[2]	高明华,杨璨. 基于改进卷积神经网络的交通目标检测方法[J]. 吉林大学学报(工学版), 2022, 52(6): 1353-1361.
[3]	杨怀江,王二帅,隋永新,闫丰,周跃. 简化型残差结构和快速深度残差网络[J]. 吉林大学学报(工学版), 2022, 52(6): 1413-1421.
[4]	王学智,李清亮,李文辉. 融合迁移学习的土壤湿度预测时空模型[J]. 吉林大学学报(工学版), 2022, 52(3): 675-683.
[5]	李向军,涂洁莹,赵志宾. 基于多尺度融合卷积神经网络的熔解曲线有效性分类[J]. 吉林大学学报(工学版), 2022, 52(3): 633-639.
[6]	李先通,全威,王华,孙鹏程,安鹏进,满永兴. 基于时空特征深度学习模型的路径行程时间预测[J]. 吉林大学学报(工学版), 2022, 52(3): 557-563.
[7]	高文志,王彦军,王欣伟,张攀,李勇,董阳. 基于卷积神经网络的柴油机失火故障实时诊断[J]. 吉林大学学报(工学版), 2022, 52(2): 417-424.
[8]	张龙,徐天鹏,王朝兵,易剑昱,甄灿壮. 基于卷积门控循环网络的齿轮箱故障诊断[J]. 吉林大学学报(工学版), 2022, 52(2): 368-376.
[9]	段亮,宋春元,刘超,魏苇,吕成吉. 基于机器学习的高速列车轴承温度状态识别[J]. 吉林大学学报(工学版), 2022, 52(1): 53-62.
[10]	钟辉,康恒,吕颖达,李振建,李红,欧阳若川. 基于注意力卷积神经网络的图像篡改定位算法[J]. 吉林大学学报(工学版), 2021, 51(5): 1838-1844.
[11]	王德兴,吴若有,袁红春,宫鹏,王越. 基于多尺度注意力融合和卷积神经网络的水下图像恢复[J]. 吉林大学学报(工学版), 2021, 51(4): 1396-1404.
[12]	王柯俨,王迪,赵熹,陈静怡,李云松. 基于卷积神经网络的联合估计图像去雾算法[J]. 吉林大学学报(工学版), 2020, 50(5): 1771-1777.
[13]	李志军,杨楚皙,刘丹,孙大洋. 基于深度卷积神经网络的信息流增强图像压缩方法[J]. 吉林大学学报(工学版), 2020, 50(5): 1788-1795.
[14]	刘国华,周文斌. 基于卷积神经网络的脉搏波时频域特征混叠分类[J]. 吉林大学学报(工学版), 2020, 50(5): 1818-1825.
[15]	谌华,郭伟,闫敬文,卓文浩,吴良斌. 基于深度学习的SAR图像道路识别新方法[J]. 吉林大学学报(工学版), 2020, 50(5): 1778-1787.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed