About: Illumination problem is a research topic. Over the lifetime, 93 publications have been published within this topic receiving 5859 citations.
Papers published on a yearly basis
••03 Dec 2010
TL;DR: This work proposes a framework to optimize the illumination normalization for a pair of gallery and probe face images by maximizing a correlation (MAC) between them and shows the effectiveness of this approach in face recognition across varying lighting conditions.
Abstract: Illumination variation has been one of the most intractable problems in face recognition and many approaches have been proposed to handle illumination problem in the last decades of years. The key problem is how to get stable similarity measurements between two face images of the same individual but captured under dramatically different lighting conditions. We propose a framework to optimize the illumination normalization for a pair of gallery and probe face images by maximizing a correlation (MAC) between them. The illumination normalization in the proposed framework tends to maximize the intra-individual correlations instead of both the inter- and intra-individual correlations. Experiments on Extended YaleB and CMU-PIE face databases show the effectiveness of our proposed approach in face recognition across varying lighting conditions.
TL;DR: A novel illumination invariant extraction method was proposed to deal with the illumination problem based on wavelet transform and denoising model and it was found that satisfactory recognition rate can be achieved by the proposed method.
Abstract: The recognition of frontal facial appearance with illumination is a difficult task for face recognition.In this paper,a novel illumination invariant extraction method was proposed to deal with the illumination problem based on wavelet transform and denoising model.The illumination invariant was extracted in wavelet domain by using wavelet-based denoising techniques.Through manipulating the high frequency wavelet coefficient combined with denoising model,the edge features of the illumination invariants were enhanced and more useful information was restored in illumination invariants,which could lead to an excellent face recognition performance.The experimental results on Yale face database B and CMU PIE face database show that satisfactory recognition rate can be achieved by the proposed method.
TL;DR: An efficient algorithm was tested and developed to determine the area of light propagated using the cellular automata construction method and it is hoped that the results can contribute to finding more efficient solutions to the art gallery problem as well as other computational geometry problems.
Abstract: The purpose of this study is to determine the area of light emitted by a source in an orthogonal polygon on a two-dimensional lattice using the cellular automata construction method. By applying this method, an efficient algorithm was tested and developed to determine the area of light propagated. The algorithm, although not optimal, gives a close approximation of the number of cells on the lattice that are to be illuminated. Furthermore, the algorithm acknowledged in this research is sufficient to work with any orthogonal polygon. This research is based on a classical computational geometry problem – the art gallery problem. It is hoped that the results of this research can contribute to finding more efficient solutions to the problem as well as other computational geometry problems. Introduction In 1973 during a discussion with other mathematicians, Victor Klee introduced the art gallery problem: How many guards are sufficient to guard any polygon with n vertices? The problem was called the art gallery problem or the illumination problem because it resembled a security configuration in an art gallery as well as represented the illumination of an art gallery. For example, if an owner of an art gallery wants to place cameras (source of light) such that the whole gallery will be thief proof, before that owner can configure his/her security setup, he or she will first have to answer a few questions. Questions like “What is the minimum number of cameras required in order to protect the expensive art collection?” and “Where will the cameras be placed so that the whole gallery is guarded?” There are many forms of the art gallery problem, dealing with many types of polygons. In this research we looked only at using orthogonal polygons to represent a gallery. Orthogonal polygons are polygons that have a set of mutually perpendicular axis, meeting at right angles (see fig. 1). An orthogonal polygon can also be dissected at its vertexes, resulting in squares or rectangles. GVSU McNair Scholars Journal VOLUME 7, 2003 91 A Heuristic Algorithm: Simulating Light Propagation in Orthogonal Polygons
••01 Aug 2014
TL;DR: A cross-band ear recognition to overcome the variant illumination problem and determine the individual identity (intra- and inter-variance) of the ear region using Euclidean distance.
Abstract: Ear biometric is slowly gaining its position in biometric studies. Just like fingerprint and iris, the ears are unique and have other advantages over current regular biometric methods. Besides those advantages, there are some issues arising for ear recognition. One of those is regarding the illumination. Low illumination may result in low quality image acquired resulting in low recognition rate. Based on this situation, we proposed a cross-band ear recognition to overcome the variant illumination problem. This method starts by measuring the environments illumination which will determine which type of images (i.e.: thermal or visible) acquired to be processed. Once determined, the images will undergo pre-processing before the ear region is being localized using Viola-Jones approach with Haar-like feature. The ear features will be extracted using local binary patterns operator. Euclidean distance of the feature of test image and database images will be calculated. The lowest Euclidean value will determine the individual identity (intra- and inter-variance).
Related Topics (5)
42.6K papers, 836.5K citations
Feature (machine learning)
33.9K papers, 798.7K citations
96.4K papers, 2.1M citations
Rendering (computer graphics)
41.3K papers, 776.5K citations
Feature (computer vision)
128.2K papers, 1.7M citations