Recovering the Shading Image under Known Illumination
CRV '04 Proceedings of the 1st Canadian Conference on Computer and Robot Vision
Metal highlight spots removal based on multi-light-sources and total variation inpainting
Proceedings of the 2006 ACM international conference on Virtual reality continuum and its applications
Bayesian object extraction from uncalibrated image pairs
Image Communication
Color Subspaces as Photometric Invariants
International Journal of Computer Vision
Separating corneal reflections for illumination estimation
Neurocomputing
Evolutive Parametric Approach for Specular Correction in the Dichromatic Reflection Model
HAIS '08 Proceedings of the 3rd international workshop on Hybrid Artificial Intelligence Systems
Bayesian Reflectance Component Separation
KES '09 Proceedings of the 13th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems: Part II
Correspondence search in the presence of specular highlights using specular-free two-band images
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part II
A view-invariant and anti-reflection algorithm for car body extraction and color classification
Multimedia Tools and Applications
| Hi-index | 0.00 |
The presence of highlights, which in dielectric inhomogeneousobjects are linear combination of specular and diffusereflection components, is inevitable. A number of methodshave been developed to separate these reflection components.To our knowledge, all methods that use a singleinput image require explicit color segmentation to deal withmulticolored surfaces. Unfortunately, for complex texturedimages, current color segmentation algorithms are stillproblematic to segment correctly. Consequently, a methodwithout explicit color segmentation becomes indispensable,and this paper presents such a method. The method is basedsolely on colors, particularly chromaticity, without requiringany geometrical parameter information. One of the basicideas is to compare the intensity logarithmic differentiationof specular-free images and input images iteratively.The specular-free image is a pseudo-code of diffuse componentsthat can be generated by shifting a pixel's intensityand chromaticity nonlinearly while retaining its hue. Allprocesses in the method are done locally, involving a maximumof only two pixels. The experimental results on naturalimages show that the proposed method is accurate and robustunder known scene illumination chromaticity. Unlikethe existing methods that use a single image, our methodis effective for textured objects with complex multicoloredscenes.