The Experts below are selected from a list of 264306 Experts worldwide ranked by ideXlab platform
Hossei Mobahi - One of the best experts on this subject based on the ideXlab platform.
-
toward a practical face recognition system robust alignment and Illumination by sparse representation
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012Co-Authors: Andrew Wagne, J Wrigh, Arvind Ganesh, Ziha Zhou, Hossei MobahiAbstract:Many classic and contemporary face recognition algorithms work well on public data sets, but degrade sharply when they are used in a real recognition system. This is mostly due to the difficulty of simultaneously handling variations in Illumination, image misalignment, and occlusion in the test image. We consider a scenario where the training images are well controlled and test images are only loosely controlled. We propose a conceptually simple face recognition system that achieves a high degree of robustness and stability to Illumination variation, image misalignment, and partial occlusion. The system uses tools from sparse representation to align a test face image to a set of frontal training images. The region of attraction of our alignment algorithm is computed empirically for public face data sets such as Multi-PIE. We demonstrate how to capture a set of training images with enough Illumination variation that they span test images taken under uncontrolled Illumination. In order to evaluate how our algorithms work under practical testing conditions, we have implemented a complete face recognition system, including a projector-based training acquisition system. Our system can efficiently and effectively recognize faces under a variety of realistic conditions, using only frontal images under the proposed Illuminations as training.
Tammy Riklinraviv - One of the best experts on this subject based on the ideXlab platform.
-
the quotient image class based re rendering and recognition with varying Illuminations
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001Co-Authors: Amnon Shashua, Tammy RiklinravivAbstract:The paper addresses the problem of "class-based" image-based recognition and rendering with varying Illumination. The rendering problem is defined as follows: Given a single input image of an object and a sample of images with varying Illumination conditions of other objects of the same general class, re-render the input image to simulate new Illumination conditions. The class-based recognition problem is similarly defined: Given a single image of an object in a database of images of other objects, some of them multiply sampled under varying Illumination, identify (match) any novel image of that object under varying Illumination with the single image of that object in the database. We focus on Lambertian surface classes and, in particular, the class of human faces. The key result in our approach is based on a definition of an Illumination invariant signature image which enables an analytic generation of the image space with varying Illumination. We show that a small database of objects-in our experiments as few as two objects-is sufficient for generating the image space with varying Illumination of any new object of the class from a single input image of that object. In many cases, the recognition results outperform by far conventional methods and the re-rendering is of remarkable quality considering the size of the database of example images and the mild preprocess required for making the algorithm work.
Andrew Wagne - One of the best experts on this subject based on the ideXlab platform.
-
toward a practical face recognition system robust alignment and Illumination by sparse representation
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012Co-Authors: Andrew Wagne, J Wrigh, Arvind Ganesh, Ziha Zhou, Hossei MobahiAbstract:Many classic and contemporary face recognition algorithms work well on public data sets, but degrade sharply when they are used in a real recognition system. This is mostly due to the difficulty of simultaneously handling variations in Illumination, image misalignment, and occlusion in the test image. We consider a scenario where the training images are well controlled and test images are only loosely controlled. We propose a conceptually simple face recognition system that achieves a high degree of robustness and stability to Illumination variation, image misalignment, and partial occlusion. The system uses tools from sparse representation to align a test face image to a set of frontal training images. The region of attraction of our alignment algorithm is computed empirically for public face data sets such as Multi-PIE. We demonstrate how to capture a set of training images with enough Illumination variation that they span test images taken under uncontrolled Illumination. In order to evaluate how our algorithms work under practical testing conditions, we have implemented a complete face recognition system, including a projector-based training acquisition system. Our system can efficiently and effectively recognize faces under a variety of realistic conditions, using only frontal images under the proposed Illuminations as training.
-
towards a practical face recognition system robust registration and Illumination by sparse representation
Computer Vision and Pattern Recognition, 2009Co-Authors: Andrew Wagne, J Wrigh, Arvind Ganesh, Ziha ZhouAbstract:Most contemporary face recognition algorithms work well under laboratory conditions but degrade when tested in less-controlled environments. This is mostly due to the difficulty of simultaneously handling variations in Illumination, alignment, pose, and occlusion. In this paper, we propose a simple and practical face recognition system that achieves a high degree of robustness and stability to all these variations. We demonstrate how to use tools from sparse representation to align a test face image with a set of frontal training images in the presence of significant registration error and occlusion. We thoroughly characterize the region of attraction for our alignment algorithm on public face datasets such as Multi-PIE. We further study how to obtain a sufficient set of training Illuminations for linearly interpolating practical lighting conditions. We have implemented a complete face recognition system, including a projector-based training acquisition system, in order to evaluate how our algorithms work under practical testing conditions. We show that our system can efficiently and effectively recognize faces under a variety of realistic conditions, using only frontal images under the proposed Illuminations as training.
Makio Tokunaga - One of the best experts on this subject based on the ideXlab platform.
-
highly inclined thin Illumination enables clear single molecule imaging in cells
Nature Methods, 2008Co-Authors: Makio Tokunaga, Naoko Imamoto, Kumiko SakatasogawaAbstract:We describe a simple Illumination method of fluorescence microscopy for molecular imaging. Illumination by a highly inclined and thin beam increases image intensity and decreases background intensity, yielding a signal/background ratio about eightfold greater than that of epi-Illumination. A high ratio yielded clear single-molecule images and three-dimensional images using cultured mammalian cells, enabling one to visualize and quantify molecular dynamics, interactions and kinetics in cells for molecular systems biology.
Jeanjacques Greffet - One of the best experts on this subject based on the ideXlab platform.
-
thermal radiation scanning tunnelling microscopy
Nature, 2006Co-Authors: Yannick De Wilde, F Formanek, Remi Carminati, Boris Gralak, Paularthur Lemoine, Karl Joulain, Jeanphilippe Mulet, Yong Chen, Jeanjacques GreffetAbstract:The resolution achievable by optical imaging is limited by the wavelength of the light used — the diffraction limit. Near-field scanning optical microscopy circumvents this limit by using a probe smaller than the wavelength of the incident light to map out the electromagnetic field at the sample surface, allowing a resolution well beyond the diffraction limit. Now a variant of this technique has been developed that does away with external Illumination altogether. The new technique, called thermal radiation scanning tunnelling microscopy or TRSTM, makes use of the thermal infrared emissions from the sample itself. Think of it as a near-field equivalent of a night-vision camera. In standard near-field scanning optical microscopy (NSOM), a subwavelength probe acts as an optical ‘stethoscope’ to map the near field produced at the sample surface by external Illumination1. This technique has been applied using visible1,2, infrared3, terahertz4 and gigahertz5,6 radiation to illuminate the sample, providing a resolution well beyond the diffraction limit. NSOM is well suited to study surface waves such as surface plasmons7 or surface-phonon polaritons8. Using an aperture NSOM with visible laser Illumination, a near-field interference pattern around a corral structure has been observed9, whose features were similar to the scanning tunnelling microscope image of the electronic waves in a quantum corral10. Here we describe an infrared NSOM that operates without any external Illumination: it is a near-field analogue of a night-vision camera, making use of the thermal infrared evanescent fields emitted by the surface, and behaves as an optical scanning tunnelling microscope11,12. We therefore term this instrument a ‘thermal radiation scanning tunnelling microscope’ (TRSTM). We show the first TRSTM images of thermally excited surface plasmons, and demonstrate spatial coherence effects in near-field thermal emission.
