A multiresolution spline with application to image mosaics
ACM Transactions on Graphics (TOG)
A hierarchical morphological image decomposition
Pattern Recognition Letters
Multiscale color image enhancement
Pattern Recognition Letters
Digital Color Management: Encoding Solutions
Digital Color Management: Encoding Solutions
Gradient domain high dynamic range compression
Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Multiscale Contrast Enhancement of Medical Images
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 4 - Volume 4
Color Image Enhancement by Fuzzy Intensification
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3
ACM SIGGRAPH 2003 Papers
A perceptual framework for contrast processing of high dynamic range images
ACM Transactions on Applied Perception (TAP)
IEEE Transactions on Image Processing
Gray and color image contrast enhancement by the curvelet transform
IEEE Transactions on Image Processing
Image contrast enhancement using morphological decomposition by reconstruction
WSEAS Transactions on Circuits and Systems
El-pincel: a painter cloud service for greener web pages
Proceedings of the 20th ACM international conference on Multimedia
Hi-index | 0.00 |
Study of contrast sensitivity of the human eye shows that our contrast discrimination sensitivity follows the weber law for suprathreshold levels. In this paper, we apply this fact effectively to design a contrast enhancement method for images that improves the local image contrast by controlling the local image gradient. Unlike previous methods, we achieve this without segmenting the image either in the spatial (multi-scale) or frequency (multi-resolution) domain.We pose contrast enhancement as an optimization problem that maximizes the average local contrast of an image. The optimization formulation includes a perceptual constraint derived directly from human suprathreshold contrast sensitivity function. Then, we propose a greedy heuristic, controlled by a single parameter, to approximate this optimization problem. The results generated by our method is superior to existing techniques showing none of the common artifacts of contrast enhancements like halos, hue shift, and intensity burn-outs.