[1]李 响,马荣贵,何逸煦.基于序列光圈拍摄的逆光图像重建方法[J].计算机技术与发展,2022,32(06):79-84.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 014]
　LI Xiang,MA Rong-gui,HE Yi-xu.Backlight Image Reconstruction Method Based on Sequential Aperture Shooting[J].,2022,32(06):79-84.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 014]
点击复制

基于序列光圈拍摄的逆光图像重建方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年06期
页码:
79-84
栏目:
图形与图像
出版日期:
2022-06-10

文章信息/Info

Title:
Backlight Image Reconstruction Method Based on Sequential Aperture Shooting
文章编号:
1673-629X(2022)06-0079-06
作者:
李 响; 马荣贵; 何逸煦
长安大学 信息学院,陕西 西安 710064
Author(s):
LI Xiang; MA Rong-gui; HE Yi-xu
School of Information,Chang’an University,Xi’an 710064,China
关键词:
逆光图像处理; 图像分割; 图像拼接; 图像方差; 信息熵
Keywords:
backlight image processing; image segmentation; image mosaic; image variance; information entropy
分类号:
TP317. 4
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 06. 014
摘要:
逆光图像因背景光远强于前景导致前景阴暗模糊造成图像观感不佳。 而在当前逆光图像研究中多数为对单一的前景灰暗背景正常的逆光图像进行还原处理,且处理效果难以控制。 针对上述问题,提出一种基于序列光圈的逆光图像还原方法。 该方法首先通过调节相机光圈获得一组由背景过曝前景清晰逐步转换至背景清晰前景灰暗的逆光图像并将其分为前景可用图像与背景可用图像。 然后使用改进的图像阈值分割算法进行逆光图像可用部分提取,并使用基于轮廓拟合的图像拼接算法将各前景可用图像提取部分分别与各背景可用图像提取部分拼接得到非逆光图像。 最后,通过图像逆光度分析与信息熵综合的筛选方法,将拼接得到的非逆光图像进行筛选,得到最终结果图像。 该方法相较于传统逆光图像重建方法,不但提高了处理结果的可控性,而且在保留更多原有图像的细节的同时降低了颜色失真。
Abstract:
Because the background light of backlight image is far stronger than the foreground light,the foreground is dark and fuzzy,resulting in poor image appearance. However,in the current backlight image research,most of the backlight images with normal graybackground are restored,and the processing effect is difficult to control. To solve the above problems, a method of backlight imagerestoration based on sequential aperture is proposed. Firstly,by adjusting the aperture of the camera, a group of backlight images areobtained,which are gradually converted from the background overexposed and the foreground clear to the background clear and theforeground gray,and are divided into foreground available image and background available image. Then,the improved image thresholdsegmentation algorithm is used to extract the available part of backlight image,and the image mosaic algorithm based on contour fitting isused to splice the available part of foreground image with the available part of background image to obtain the non backlight image.Finally,through the screening method of image backlight analysis and information entropy synthesis,the stitched non backlight image isscreened to get the final result image. Compared with the traditional backlight image reconstruction method,the proposed method not onlyimproves the controllability of the processing results,but also reduces the color distortion while retaining more details of the original image.

相似文献/References:

[1]蒋璐璐 王适 王宝成 李慧敏 李鑫慧.一种改进的标记分水岭遥感图像分割方法[J].计算机技术与发展,2010,(01):36.
　JIANG Lu-lu,WANG Shi,WANG Bao-cheng,et al.Segmentation of Remote Sensing Image Based on an Improved Labeling Watershed Algorithm[J].,2010,(06):36.
[2]张少娴 俞琼.基于时空相关性预测的运动估计的优化[J].计算机技术与发展,2010,(01):100.
　ZHANG Shao-xian,YU Qiong.An Optimization Method for Spatiotemporal Predictive Motion Estimation[J].,2010,(06):100.
[3]王兴 冯子亮.基于自适应初始值的FCM聚类图像分割[J].计算机技术与发展,2010,(03):101.
　WANG Xing,FENG Zi-liang.An Image Segmentation Algorithm Based on Adaptive Initialization FCM Clustering[J].,2010,(06):101.
[4]何小娜 逄焕利.基于二维直方图和改进蚁群聚类的图像分割[J].计算机技术与发展,2010,(03):128.
　HE Xiao-na,PANG Huan-li.Image Segmentation Based on Improved Ant Colony Clustering and Two- Dimensional Histogram[J].,2010,(06):128.
[5]宋淑娜 李金霞 胡学坤 高尚.一种自适应模糊阈值区间的图像分割方法[J].计算机技术与发展,2010,(05):121.
　SONG Shu-na,LI Jin-xia,HU Xue-kun,et al.A Method of Adaptive Fuzzy Threshold Region for Image Segmentation[J].,2010,(06):121.
[6]来磊 卢文科 邓开连.基于二维Tsallis交叉熵直线型图像阈值分割方法[J].计算机技术与发展,2010,(06):105.
　LAI Lei,LU Wen-ke,DENG Kai-lian.New Image Thresholding Segmentation Methods Based on Two-Dimensional Tsallis Cross-Entropy Liner-Type[J].,2010,(06):105.
[7]黄长专 王彪 杨忠.图像分割方法研究[J].计算机技术与发展,2009,(06):76.
　HUANG Chang-zhuan,WANG Biao,YANG Zhong.A Study on Image Segmentation Techniques[J].,2009,(06):76.
[8]李光耀 聂诗良.基于小波分解和模糊聚类的图像分割方法[J].计算机技术与发展,2009,(06):121.
　LI Guang-yao,NIE Shi-liang.Image Segment Algorithm Based on Wavelet Decomposition and Fuzzy Clustering Theory[J].,2009,(06):121.
[9]吴亚 汪继文.水平集图像分割中重新初始化规避的探索[J].计算机技术与发展,2009,(09):69.
　WU Ya,WANG Ji-wen.Avoidance of Re- Initialization in Level Set Image Segmentation[J].,2009,(06):69.
[10]李鑫环 陈立潮 赵红艳 赵勇.基于多小波分析与SOFM的MR图像分割算法研究[J].计算机技术与发展,2009,(09):104.
　LI Xin-huan,CHEN Li-chao,ZHAO Hong-yan,et al.Research on MR Image Segmentation Based on Multi- wavelet Analysis and SOFM[J].,2009,(06):104.

更新日期/Last Update: 2022-06-10