Tone Mapping High Dynamic Range Images by Hessian Multiset Canonical Correlations
- PDF / 1,786,997 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 89 Downloads / 160 Views
Tone Mapping High Dynamic Range Images by Hessian Multiset Canonical Correlations N. Neelima1 · Y. Ravi Kumar2 Received: 6 April 2019 / Revised: 15 October 2019 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Tone mapping algorithms reproduce high dynamic range (HDR) images on low dynamic range images in the standard display devices such as LCD, CRT, projectors, and printers. In this paper, we propose a statistical clustering-based tone mapping technique that would be able to adapt the local content of an image as well as its color. At first, the HDR image is partitioned into many overlapped color patches and we disintegrate each color patch into three segments: patch mean, color variation and color structure. Then based on the color structure component, the extracted color patches are clustered into a number of clusters by k-means clustering technique. For each cluster, the statistical signal processing technique namely Hessian multi set canonical correlations (HesMCC) has been produced to ascertain the transform matrix. Moreover, the HesMCC are fundamentally utilized for performing the dimensionality reduction of patches and to form effective tone mapped images. Contrasting with the current strategies, the procedures in the proposed clustering-based strategy can better adapt image color and its local structures by exploiting the image in the worldwide repetition. Experimental results show that the running time of the proposed method is less about 88.32%, 92%, 68.9%, and 29.4%, while comparing with other existing tone mapping methods. Keywords HesMCC · k-means clustering · Patch mean · Color variation · Color structure · High dynamic range image · Low dynamic range image · Tone mapping
* N. Neelima [email protected] 1
Electronics and Communication Engineering, CMR Institute of Technology, Hyderabad, India
2
SINT (E) Division, DLRL, Hyderabad, India
13
Vol.:(0123456789)
8
Page 2 of 19
Sensing and Imaging
(2020) 21:8
1 Introduction The dynamic scope of a natural scene is very high; however, the camera sensors possess restricted dynamic range that brings about under or overexposure in the caught images [1]. High Dynamic Range (HDR) image is an imperative point in the improvement field of PC innovation and computational photography [2, 3]. However, the Low dynamic Range (LDR) images are displayed only in standard devices such as LCD, CRT, projectors, and printers and they can’t display the specific HDR images [4]. So, it is expected to change the dynamic range of HDR images to LDR images. The process of mapping high dynamic range image to low dynamic range image is called as tone mapping [5–7]. The mapping lessens the overall high dynamic range image in contrast to encourage the devices display with LDR [8]. The image detailed features and colors are preserved faithfully, while lessening the irradiance level by a good tone mapping algorithm [9]. Over the previous 2 decades, to build a compelling tone mapping algorithm, more number of studies has been directed. The li
Data Loading...
