High Dynamic Range Imaging Algorithm Based on JND and Detail Enhancement

High dynamic range imaging is an emerging technology for generating high quality images. The most common method is to acquire high dynamic range images in a multi-exposure fusion manner. The biggest disadvantage of such algorithms is the "artifact" phenomenon caused by the target motion, or the time cost of avoiding "artifacts" for registration. Therefore, Therefore, a high dynamic range imaging algorithm based on the just noticeable difference (JND) and detail enhancement is proposed, which belongs to the generation of high dynamic images from a single image. According to the JND edge of the improved human visual characteristics and local variance matrix, combined with the fuzzy system to obtain the weight matrix describing the quality of different exposure images, so that different exposure images are fused into HDR images. The experimental results show that the algorithm can effectively improve the contrast and clarity of the image, and the generated image is more in line with the subjective visual effect of the human eye.

[1]  Suk-Ju Kang,et al.  Deep Recursive HDRI: Inverse Tone Mapping Using Generative Adversarial Networks , 2018, ECCV.

[2]  Zhengguo Li,et al.  Multi-scale exposure fusion via gradient domain guided image filtering , 2017, 2017 IEEE International Conference on Multimedia and Expo (ICME).

[3]  Lina J. Karam,et al.  A No-Reference Image Blur Metric Based on the Cumulative Probability of Blur Detection (CPBD) , 2011, IEEE Transactions on Image Processing.

[4]  Gabriel Eilertsen,et al.  HDR image reconstruction from a single exposure using deep CNNs , 2017, ACM Trans. Graph..

[5]  Wen-Huang Cheng,et al.  Background Extraction Using Random Walk Image Fusion , 2018, IEEE Transactions on Cybernetics.

[6]  Hiroshi Nagahashi,et al.  Cross-Parameterization for Triangular Meshes with Semantic Features , 2007 .

[7]  Monson H. Hayes,et al.  Single image-based ghost-free high dynamic range imaging using local histogram stretching and spatially-adaptive denoising , 2011, IEEE Transactions on Consumer Electronics.

[8]  Wen-Huang Cheng,et al.  A comparative study of data fusion for RGB-D based visual recognition , 2016, Pattern Recognit. Lett..

[9]  Matthew J. Kyan,et al.  Adaptive exposure fusion for high dynamic range imaging , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[10]  Anoop K. Johnson,et al.  Single shot high dynamic range imaging using power law transformation and exposure fusion , 2016, 2016 International Conference on Communication Systems and Networks (ComNet).

[11]  Xuelong Li,et al.  Exposure Fusion Using Boosting Laplacian Pyramid , 2014, IEEE Transactions on Cybernetics.

[12]  Chang-Su Kim,et al.  Dark image enhancement based onpairwise target contrast and multi-scale detail boosting , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[13]  Thomas Bashford-Rogers,et al.  ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content , 2018, Comput. Graph. Forum.

[14]  Ramazan Duvar,et al.  Fuzzy fusion based high dynamic range imaging using adaptive histogram separation , 2015, IEEE Transactions on Consumer Electronics.

[15]  Jan Kautz,et al.  Exposure Fusion , 2007, 15th Pacific Conference on Computer Graphics and Applications (PG'07).

[16]  Chih-Hsien Hsia,et al.  Multiple exposure fusion based on sharpness-controllable fuzzy feedback , 2019, J. Intell. Fuzzy Syst..

[17]  Rong Xie,et al.  Learning an Inverse Tone Mapping Network with a Generative Adversarial Regularizer , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[18]  Wolfgang Heidrich,et al.  HDR-VDP-2: a calibrated visual metric for visibility and quality predictions in all luminance conditions , 2011, SIGGRAPH 2011.

[19]  Zhengguo Li,et al.  Detail-Enhanced Multi-Scale Exposure Fusion , 2017, IEEE Transactions on Image Processing.