Carlos A. B. Mello
ABSTRACT
This paper presents a new algorithm for filtering shadowy photos degraded by uneven light condition. The dark photos are harder to use for face recognition or even an analysis of the scene. Corrections can be made using commercial tools as Photoshop™ but this is done manually and it requires a specialized user. We propose an automatic method which inproves the visibility of the scenes. This method is based on wavelet analysis but it uses different filters.
- Bose, T., Digital Signal and Image Processing, John Wiley and Sons, New York, 2004. Google Scholar
Digital Library
- Daubechies, I., Ten Lectures on Wavelets, SIAM: Society for Industrial and Applied Mathematics, 1992. Google ScholarDigital Library
- Mallat, S. G., A wavelet tour of signal processing, Academic Press, New Jersey, 1998.Google ScholarDigital Library
- Parker, J. R., Algorithms for Image Processing and Computer Vision, John Wiley and Sons, New Jersey, 1997.Google Scholar
- Petrosian, A. A., and Meyer, F. G., Wavelets in Signal and Image Analysis, Kluwer Academic Pub, New York, 2001.Google ScholarCross Ref
- Woods, R., and Gonzalez, R., Digital image Processing, Ed. Prentice-Hall, New Jersey, 2007.Google Scholar
Index Terms
- Filtering the shadows from poorly illuminated photos
Recommendations
Filtering Multi-Layer Shadow Maps for Accurate Soft Shadows
In this paper, we introduce a novel technique for pre-filtering multi-layer shadow maps. The occluders in the scene are stored as variable-length lists of fragments for each texel. We show how this representation can be filtered by progressively merging ...
Axis-aligned filtering for interactive sampled soft shadows
We develop a simple and efficient method for soft shadows from planar area light sources, based on explicit occlusion calculation by raytracing, followed by adaptive image-space filtering. Since the method is based on Monte Carlo sampling, it is ...
Instant convolution shadows for volumetric detail mapping
In this article, we present a method for rendering dynamic scenes featuring translucent procedural volumetric detail with all-frequency soft shadows being cast from objects residing inside the view frustum. Our approach is based on an approximation of ...
Reviews
Terry P. Riopka
Mello identifies an important problem in scene analysis: poor illumination. He proposes a solution that seems to improve the visibility in some scenes. The title of the paper is misleading because there is no explicit handling of shadows. Unfortunately, the solution is really a very ad hoc application of an image filter. The paper begins with a very brief introduction to wavelet analysis, which ultimately ends up being irrelevant to the rest of the paper. The filter design is done subjectively, providing no guidance to modifying, enhancing, or creating new filters. Quantitative analysis is limited to two global, nonobject-specific metrics for only four cherry-picked example images. Overall, the only redeeming aspect of this paper is the slight possibility that the proposed filter might be of some general use. However, short of implementing and testing it yourself, there is little evidence to support the paper's claims regarding its utility. Online Computing Reviews Service
Access critical reviews of Computing literature here
Become a reviewer for Computing Reviews.
Comments