 |
 |
 |
 |
 |
 |
 |
| |
|
|
|
|
|
|
| [ Database= Inspec |
|
| Results= 195 records | |
|
] |
Record: 1
COPYRIGHT: Copyright 1999, IEE RECORD NO.: 6446098 INSPEC Abstract No: B2000-02-6135-030; C2000-02- 1250M-014 AUTHOR: Sapiro, G. CORP SOURCE: Dept. of Electr. & Comput. Eng., Minnesota Univ., Minneapolis, MN, USA TITLE: Color and illuminant voting SOURCE: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.21, no.11, p. 1210-15 ISSN: 0162-8828 CODEN: ITPIDJ PLACE OF PUBL: USA LANGUAGE: English PUBLISHER: IEEE Comput. Soc YEAR: Nov. 1999 COPYRIGHT NO: 0162-8828/99/$10.00 TREATMENT: T Theoretical or Mathematical RECORD TYPE: Journal Paper ABSTRACT: A geometric-vision approach to color constancy and illuminant estimation is presented in this paper. We show a general framework, based on ideas from the generalized probabilistic Hough transform, to estimate the illuminant and reflectance of natural images. Each image pixel "votes" for possible illuminants and the estimation is based on cumulative votes. The framework is natural for the introduction of physical constraints in the color constancy problem. We show the relationship of this work to previous algorithms for color constancy and present examples (36 Refs.) DESCRIPTORS: Hough transforms; image colour analysis; probability IDENTIFIERS: illuminant voting; color constancy; geometric-vision approach; illuminant estimation; generalized probabilistic Hough transform; reflectance; cumulative votes CLASS CODES: B6135; B0230 (Integral transforms); B0240Z (Other topics in statistics); C1250M; C1130 (Integral transforms); C1140Z (Other topics in statistics)Record: 2
COPYRIGHT: Copyright 1999, IEE RECORD NO.: 6410860 INSPEC Abstract No: C2000-01-5260B-059 AUTHOR: Funt, B.; Cardei, V.C. CORP SOURCE: Simon Fraser Univ., Burnaby, BC, Canada TITLE: Bootstrapping color constancy SOURCE: Proc. SPIE - Int. Soc. Opt. Eng. (USA), Proceedings of the SPIE - The International Society for Optical Engineering, vol.3644, p. 421-8 ISSN: 0277-786X CODEN: PSISDG PLACE OF PUBL: USA LANGUAGE: English PUBLISHER: SPIE-Int. Soc. Opt. Eng SPONSOR ORG: SPIE; Soc. Imaging Sci. & Technol CONF TITLE: Human Vision and Electronic Imaging IV CONF LOCATION: San Jose, CA, USA; 25-28 Jan. 1999 YEAR: 1999 COPYRIGHT NO: 0277-786X/99/$10.00 TREATMENT: P Practical RECORD TYPE: Conference Paper; Journal Paper ABSTRACT: Bootstrapping provides a novel approach to training a neural network to estimate the chromaticity of the illuminant in a scene given image data alone. For initial training, the network requires feedback about the accuracy of the network's current results. In the case of a network for color constancy, this feedback is the chromaticity of the incident scene illumination. In the past, perfect feedback has been used, but in the bootstrapping method feedback with a considerable degree of random error can be used to train the network instead. In particular, the grayworld algorithm, which only provides modest color constancy performance, is used to train a neural network which in the end performs better than the grayworld algorithm used to train it (10 Refs.) DESCRIPTORS: image colour analysis; learning (artificial intelligence); lighting; neural nets IDENTIFIERS: color constancy; bootstrapping; neural network training; performance; chromaticity; feedback; scene illumination; random error; grayworld algorithm; image colour CLASS CODES: C5260B (Computer vision and image processing techniques); C1250M; C1230L; C5290 (Neural computing techniques); C1230D (Neural nets)Record: 3
COPYRIGHT: Copyright 1999, IEE RECORD NO.: 6401141 INSPEC Abstract No: B1999-12-6135-202; C1999-12- 6130B-042 AUTHOR: Marini, D.; Rizzi, A.; Rossi, M. CORP SOURCE: Dipt. di Sci. dell'Inf., Milan Univ., Italy TITLE: Color constancy measurements for synthetic image generation SOURCE: Journal of Electronic Imaging, vol.8, no.4, p. 394- 403 ISSN: 1017-9909 CODEN: JEIME5 PLACE OF PUBL: USA LANGUAGE: English PUBLISHER: SPIE-Int. Soc. Opt. Eng YEAR: Oct. 1999 COPYRIGHT NO: 1017-9909/99/$10.00 TREATMENT: T Theoretical or Mathematical; X Experimental RECORD TYPE: Journal Paper ABSTRACT: Solving the color constancy problem in many applications implies the understanding of chromatic adaptation. The Retinex theory justifies chromatic adaptation, as well as other color illusions, on visual perception principles. Based on the above theory, we have derived an algorithm to solve the color constancy problem and to simulate chromatic adaptation. The evaluation of the results depends on the kind of applications considered. Since our purpose is to contribute to the problem of color rendering for photorealistic image synthesis, we have devised a specific test approach. A virtual "Mondrian" patchwork has been created by applying a rendering algorithm with a photorealistic light model to generate images under different light sources. Trichromatic values of the computer generated patches are the input data for the Retinex algorithm, computing new color corrected patches. The Euclidean and the Delta E/sub 94/* distances in the CIELAB space, between the original and Retinex color corrected trichromatic values, have been calculated. A preliminary analysis of the just noticeable difference has also been done on some colors compared to the closest MacAdam ellipses. Our work shows that the Retinex computational model is very well suited to solve the color constancy problem without any a priori information on the illuminant spectral distribution (24 Refs.) DESCRIPTORS: image colour analysis; rendering (computer graphics) IDENTIFIERS: color constancy measurements; synthetic image generation; chromatic adaptation; Retinex theory; visual perception principles; color rendering; photorealistic image synthesis; specific test approach; virtual Mondrian patchwork; rendering algorithm; photorealistic light model; computer generated patches; color corrected patches; Euclidean distance; Delta E/sub 94/* distance; MacAdam ellipses; computational model; spectral distribution CLASS CODES: B6135; C6130B (Graphics techniques); C5260B (Computer vision and image processing techniques)Record: 4
COPYRIGHT: Copyright 1999, IEE RECORD NO.: 6366035 INSPEC Abstract No: B1999-11-7230G-006 AUTHOR: Corbalan, M.; Millan, M.S.; Yzuel, M.J. CORP SOURCE: Dept. de Fisica i Enginyeria Nucl., Univ. Politecnica de Catalunya, Barcelona, Spain TITLE: Color correction against changes of light source in image acquisition by CCD camera SOURCE: Proc. SPIE - Int. Soc. Opt. Eng. (USA), Proceedings of the SPIE - The International Society for Optical Engineering, vol.3572, p. 64-8 ISSN: 0277-786X CODEN: PSISDG PLACE OF PUBL: USA LANGUAGE: English PUBLISHER: SPIE-Int. Soc. Opt. Eng SPONSOR ORG: SPIE; Univ. Nacional de Colombia; Univ. Valle; Univ. Ind. Santander; et al CONF TITLE: 3rd Iberoamerican Optics Meeting and 6th Latin American Meeting on Optics, Lasers, and Their Applications CONF LOCATION: Cartagena de Indias, Colombia; 28 Sept.-2 Oct. 1998 YEAR: 1999 COPYRIGHT NO: 0277-786X/99/$10.00 TREATMENT: X Experimental RECORD TYPE: Conference Paper; Journal Paper ABSTRACT: Color cameras usually have a device called white balance that allows one to capture a white reference without predominant colors. In this work we analyze the compensating mechanism of white balance in a color CCD camera to evaluate if the compensation permits to establish resemblances with the process of color constancy that takes place in the human visual system. We use common lightings and a camera with dichroic mirrors and three CCD sensors to capture a color image with color quality (7 Refs.) DESCRIPTORS: cameras; CCD image sensors; image colour analysis IDENTIFIERS: color correction; light source; image acquisition; CCD camera; white balance; compensation; dichroic mirror; color constancy CLASS CODES: B7230G (Image sensors); B2570H (Other field effect integrated circuits)Record: 6
COPYRIGHT: Copyright 1999, IEE RECORD NO.: 6315421 INSPEC Abstract No: A1999-18-8732Q-001 AUTHOR: Bauml, K.-H. CORP SOURCE: Inst. fur Psychol., Regensburg Univ., Germany TITLE: Color constancy: the role of image surfaces in illuminant adjustment SOURCE: Journal of the Optical Society of America A (Optics, Image Science and Vision), vol.16, no.7, p. 1521-30 ISSN: 0740-3232 CODEN: JOAOD6 PLACE OF PUBL: USA LANGUAGE: English PUBLISHER: Opt. Soc. America YEAR: July 1999 COPYRIGHT NO: 0740-3232/99/071521-10$15.00 TREATMENT: X Experimental RECORD TYPE: Journal Paper ABSTRACT: Previous studies on color constancy have found that the color appearance of a test surface varies both as a function of the illumination in the image and as a function of the image surfaces. To what extent these two effects interact is investigated here. To address this issue theoretically, a restrictive von Kries model is formulated that assumes that the scaling of the cone signals in response to an illuminant change does not depend on image surfaces. Subjects saw CRT simulations of illuminated surfaces and, for a number of different illuminants and surface collections, adjusted a test light so that it appeared achromatic and had a certain brightness. Consistent with previous studies, the settings showed a high degree of illuminant adjustment and also showed an adjustment to the surfaces in the image. The proposed von Kries model provided a good, although not perfect, description of the data, thus indicating that the illuminant adjustment was largely the same under the different surface collections. These results together with those from several previous studies suggest that image surfaces play only a minor role in the illuminant adjustment of our visual system (43 Refs.) DESCRIPTORS: brightness; colour vision; lighting; optical images; visual perception IDENTIFIERS: image surfaces; illuminant adjustment; color constancy; color appearance; test surface; illumination; restrictive von Kries model; scaling; cone signals; illuminant change; CRT simulations; subjects; illuminated surfaces; illuminants; surface collections; test light; achromatic light; brightness; visual system CLASS CODES: A8732Q (Scales for light and colour detection in vision); A8732S (Psychophysics of vision, visual perception, binocular vision)Record: 7
COPYRIGHT: Copyright 1999, IEE RECORD NO.: 6305291 INSPEC Abstract No: C1999-09-5260B-107 AUTHOR: Drew, M.S.; Jie Wei; Ze-Nian Li CORP SOURCE: Sch. of Comput. Sci., Simon Fraser Univ., Vancouver, BC, Canada TITLE: Illumination-invariant image retrieval and video segmentation SOURCE: Pattern Recognition, vol.32, no.8, p. 1369-88 ISSN: 0031-3203 CODEN: PTNRA8 PLACE OF PUBL: UK LANGUAGE: English PUBLISHER: Elsevier YEAR: Aug. 1999 COPYRIGHT NO: 0031-3203/99/$20.00 TREATMENT: T Theoretical or Mathematical; X Experimental RECORD TYPE: Journal Paper ABSTRACT: We show that a very simple method of discounting illumination changes is adequate for both image retrieval and video segmentation tasks. We develop a feature vector of only 36 values that can also be used for both these objectives as well as for retrieval of video proxy images from a database. The new image metric is based on a color- channel-normalization step, followed by reduction of dimensionality by going to a chromaticity space. Treating chromaticity histograms as images, we perform an effective low-pass filtering of the histogram by first reducing its resolution via a wavelet-based compression and then by a DCT transformation followed by zonal coding. We show that the color constancy step-color band normalization can be carried out in the compressed domain for images that are stored in compressed form, and that only a small amount of image information need be decompressed in order to calculate the new metric. The new method performs better than previous methods tested for image or texture recognition (30 Refs.) DESCRIPTORS: data compression; discrete cosine transforms; image coding; image retrieval; image segmentation; lighting; video signal processing; visual databases; wavelet transforms IDENTIFIERS: illumination-invariance; image retrieval; video segmentation; database; image metric; color-channel- normalization; dimensionality; chromaticity space; low-pass filtering; wavelet transform; image compression; DCT transform; zonal coding; Schust methods CLASS CODES: C5260B (Computer vision and image processing techniques); C6160S (Spatial and pictorial databases); C5260D; C1260S; C1130 (Integral transforms)Record: 8
COPYRIGHT: Copyright 1999, IEE RECORD NO.: 6301620 INSPEC Abstract No: B1999-09-6135-056; C1999-09- 5260B-067 AUTHOR: Marini, D.; Rizzi, A.; Carati, C. CORP SOURCE: Dipt. di Sci. dell'Inf., Milan Univ., Italy TITLE: Color constancy effects measurement of the Retinex theory SOURCE: Proc. SPIE - Int. Soc. Opt. Eng. (USA), Proceedings of the SPIE - The International Society for Optical Engineering, vol.3648, p. 249-56 ISSN: 0277-786X CODEN: PSISDG PLACE OF PUBL: USA LANGUAGE: English PUBLISHER: SPIE-Int. Soc. Opt. Eng SPONSOR ORG: SPIE: Soc. Imaging Sci. & Technol CONF TITLE: Color Imaging: Device-Independent Color, Color Hardcopy, and Graphic Arts IV CONF LOCATION: San Jose, CA, USA; 26-29 Jan. 1999 YEAR: 1998 COPYRIGHT NO: 0277-786X/98/$10.00 TREATMENT: A Application; P Practical RECORD TYPE: Conference Paper; Journal Paper ABSTRACT: Understanding chromatic adaptation is a necessary step to solve the color constancy problem for a variety of application purposes. Retinex theory justifies chromatic adaptation, as well as other color illusions, on visual perception principles. Based on the above theory, we have derived an algorithm to solve the color constancy problem and to simulate chromatic adaption. The evaluation of the result depends on the kind of applications considered. Since our purpose is to contribute to the problem of color rendering on computer system display for photorealistic image synthesis, we have devised a specific test approach. A virtual "Mondrian" patchwork has been created by applying a rendering algorithm with a photorealistic light model to generate images under different light sources. Trichromatic values of the computer generated patches are the input data for the Retinex algorithm, which computes new color corrected patches. The Euclidean distance in CIELAB space, between the original and Retinex color corrected trichromatic values, has been calculated, showing that the Retinex computational model is very well suited to solve the color constancy problem without any information on the illuminant spectral distribution (17 Refs.) DESCRIPTORS: computational geometry; image colour analysis; rendering (computer graphics) IDENTIFIERS: color constancy effects measurement; Retinex theory; chromatic adaptation; visual perception principles; color rendering; photorealistic image synthesis; photorealistic light model; computer generated patches; Euclidean distance; CIELAB space; illuminant spectral distribution CLASS CODES: B6135; C5260B (Computer vision and image processing techniques); C6130B (Graphics techniques); C4260 (Computational geometry); C1160 (Combinatorial mathematics)Record: 12
COPYRIGHT: Copyright 1999, IEE RECORD NO.: 6195097 INSPEC Abstract No: B1999-04-6135-188; C1999-04- 5260B-227 AUTHOR: Paulus, D.; Csink, L.; Niemann, H. CORP SOURCE: Lehrstuhl fur Mustererkennung, Erlangen-Nurnberg Univ., Germany TITLE: Color cluster rotation SOURCE: Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269), p. 3 vol. (lxxi+962+984+1013), 161-5 vol.1 PLACE OF PUBL: USA ISBN: 0818688211 LANGUAGE: English PUBLISHER: IEEE Comput. Soc; Los Alamitos, CA, USA SPONSOR ORG: IEEE Signal Process. Soc CONF TITLE: Proceedings of IPCIP'98 International Conference on Image Processing CONF LOCATION: Chicago, IL, USA; 4-7 Oct. 1998 YEAR: 1998 COPYRIGHT NO: 0 8186 8821 1/98/$10.00 TREATMENT: T Theoretical or Mathematical; X Experimental RECORD TYPE: Conference Paper ABSTRACT: The distribution of color values in color images depends on the illumination which varies widely under real-world conditions. We present a new approach for color normalization which adjusts the statistical properties of the distribution to predefined values. We introduce two algorithms based on geometric manipulations of the color cluster. Our new color rotation algorithm is tested on some natural and synthetic images (10 Refs.) DESCRIPTORS: computer vision; image colour analysis; image recognition; statistical analysis IDENTIFIERS: color cluster rotation; color values distribution; color images; illumination; color normalization; statistical properties; geometric manipulations; color rotation algorithm; synthetic images; natural images; computer vision; color constancy algorithms; cluster analysis CLASS CODES: B6135; B0240Z (Other topics in statistics); C5260B (Computer vision and image processing techniques); C1140Z (Other topics in statistics)Record: 13
COPYRIGHT: Copyright 1999, IEE RECORD NO.: 6172398 INSPEC Abstract No: A1999-07-8732N-001 AUTHOR: Nakauchi, S.; Uchida, T.; Usui, S. CORP SOURCE: Dept. of Inf. & Comput. Sci., Toyohashi Univ. of Technol., Japan TITLE: Discrimination of illumination and reflectance changes on color constancy SOURCE: Transactions of the Institute of Electronics, Information and Communication Engineers A, vol.J82-A, no.1, p. 168-78 ISSN: 0913-5707 CODEN: DJTAER PLACE OF PUBL: Japan LANGUAGE: Japanese PUBLISHER: Inst. Electron. Inf. & Commun. Eng YEAR: Jan. 1999 TREATMENT: T Theoretical or Mathematical; X Experimental RECORD TYPE: Journal Paper ABSTRACT: Color constancy is defined as the invariance of the perceived color of an object despite changing illuminant color. Psychophysical studies have shown that we have apparent color and surface color perception, and the color constancy is realized only on the surface color perception. In this article, influence of surround stimuli on the apparent/surface color perception was investigated by psychophysical experiments measuring difference thresholds for the chromaticity of the center stimulus affected by surround stimuli with the staircase method. We also proposed a model for apparent/surface color perception and predicted the difference thresholds for a variety of surround stimuli. Experimental results were well explained by the model which calculates the surface color by subtracting the illuminant color from the apparent color independent of size and position of surround stimuli (18 Refs.) DESCRIPTORS: colour vision; psychology; reflectivity IDENTIFIERS: illumination changes; reflectance changes; color constancy; perceived color; psychophysical studies; surface color perception; surround stimuli; difference thresholds; chromaticity; staircase method; apparent color CLASS CODES: A8732N (Colour vision: detection, adaptation and discrimination)Record: 14
COPYRIGHT: Copyright 1999, IEE RECORD NO.: 6153812 INSPEC Abstract No: B1999-03-6135-066; C1999-03- 5260B-104 AUTHOR: Finlayson, G.D.; Hubel, P.M.; Hordley, S. CORP SOURCE: Colour Res. Group, Derby Univ., UK TITLE: Color by correlation SOURCE: Fifth Color Imaging Conference: Color Science, Systems and Applications. Proceedings, p. xvii+310, 6-11 PLACE OF PUBL: USA ISBN: 0892082062 LANGUAGE: English PUBLISHER: Soc. Imaging Sci. & Technol; Springfield, VA, USA SPONSOR ORG: Soc. Imaging Sci. & Technol.; SID CONF TITLE: Proceedings of Fifth Color Imaging Conference: Color Science, Systems and Applications CONF LOCATION: Scottsdale, AZ, USA; 17-20 Nov. 1997 YEAR: 1997 TREATMENT: P Practical RECORD TYPE: Conference Paper ABSTRACT: Under a large variety of scene illuminants, a human observer sees the same range of colors; a white piece of paper remains resolutely white independent of the color of light under which it is seen. In contrast, color imaging systems (e.g. digital cameras) are less color constant in that they will often infer the color of the scene illuminant incorrectly. Unless the color constancy problem is solved, color appearance models cannot be used to guide image processing, and such processing is necessary for accurate (and acceptable) color reproduction. In this paper we present a new theory of color constancy, Color by Correlation, which solves for the white-point in images by exploiting the correlation that exists between image colors and scene illuminants. For example, because the reddest red camera measurement can only occur under the reddest red light we say that the reddest camera measurement correlates strongly with the reddest light. Importantly all camera measurements correlate to a greater or lesser degree with different colors of light. By examining the correlation between all image colors and all lights we show that it is possible to make a very accurate estimate of the color of the scene illuminant. Color by Correlation not only performs significantly better than other methods but is a simple, elegant solution to a problem that has eluded scientists working on color for over a century (27 Refs.) DESCRIPTORS: colour vision; image colour analysis; reproduction (copying) IDENTIFIERS: correlation; color imaging; color appearance models; image processing; color reproduction; color constancy; Color by Correlation CLASS CODES: B6135; C5260B (Computer vision and image processing techniques)Record: 20
COPYRIGHT: Copyright 1998, IEE RECORD NO.: 6074266 INSPEC Abstract No: B9812-6140C-438; C9812-5260B-252 AUTHOR: Fang-Hsuan Cheng; Wen-Hsing Hsu; Te-Wei Chen CORP SOURCE: Dept. of Comput. Sci. & Inf. Eng., Chung-Hua Univ., Hsinchu, Taiwan TITLE: Recovering colors in an image with chromatic illuminant SOURCE: IEEE Transactions on Image Processing, vol.7, no.11, p. 1524-33 ISSN: 1057-7149 CODEN: IIPRE4 PLACE OF PUBL: USA LANGUAGE: English PUBLISHER: IEEE YEAR: Nov. 1998 COPYRIGHT NO: 1057-7149/98/$10.00 TREATMENT: T Theoretical or Mathematical RECORD TYPE: Journal Paper ABSTRACT: Colors in a scene change under different illuminants. By adopting models that are used to describe human color constancy, the maximum-spectral-value method is proposed to estimate the illuminant from the maximum distribution of reflected lights in an image. From the experimental results, the proposed method recovers colors well with different illuminants (25 Refs.) DESCRIPTORS: image colour analysis; image reconstruction; spectral analysis IDENTIFIERS: chromatic illuminant; scene; maximum-spectral-value method; maximum distribution; reflected lights; image color recovery CLASS CODES: B6140C (Optical information, image and video signal processing); C5260B (Computer vision and image processing techniques); C1250 (Pattern recognition)Record: 24
COPYRIGHT: Copyright 1998, IEE RECORD NO.: 6015934 INSPEC Abstract No: B9810-6140C-419; C9810-5260B-214 AUTHOR: Sapiro, G. CORP SOURCE: Minnesota Univ., Minneapolis, MN, USA TITLE: Bilinear voting SOURCE: Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271), p. 1164, 178-83 PLACE OF PUBL: India ISBN: 8173192219 LANGUAGE: English PUBLISHER: Narosa Publishing House; New Delhi, India CONF TITLE: Proceedings of IEEE 6th International Conference on Computer Vision CONF LOCATION: Bombay, India; 4-7 Jan. 1998 YEAR: 1998 TREATMENT: T Theoretical or Mathematical RECORD TYPE: Conference Paper ABSTRACT: A geometric-vision approach to solve bilinear problems in general, and the color constancy and illuminant estimation problem in particular, is presented in this paper. We show a general framework, based on ideas from the generalized (probabilistic) Hough transform, to estimate the unknown variables in the bilinear form. In the case of illuminant and reflectance estimation in natural images, each image pixel "votes" for possible illuminants (or reflectance), and the estimation is based on cumulative votes. In the general case, the voting is for the parameters of the bilinear model. The framework is natural for the introduction of physical constraints. For the case of illuminant estimation, we briefly show the relation of this work with previous algorithms for color constancy, and present examples (29 Refs.) DESCRIPTORS: computer vision; Hough transforms IDENTIFIERS: geometric-vision; bilinear problems; color constancy; illuminant estimation; Hough transform; voting CLASS CODES: B6140C (Optical information, image and video signal processing); B0230 (Integral transforms); C5260B (Computer vision and image processing techniques); C1250 (Pattern recognition); C1130 (Integral transforms)Record: 27
COPYRIGHT: Copyright 1998, IEE RECORD NO.: 5911588 INSPEC Abstract No: A9812-8732N-003; C9806-1250-214 AUTHOR: Takebe, K.; Nakauchi, S.; Usui, S. CORP SOURCE: Dept. of Inf. & Comput. Sci., Toyohashi Univ. of Technol., Japan TITLE: A neural network model for color constancy in shadows SOURCE: Proceedings of Fifteenth International Display Research Conference. Asia Display '95, p. xxvi+981, 683-6 PLACE OF PUBL: USA LANGUAGE: English PUBLISHER: Inst. Telev. Eng. Japan & SID; Tokyo, Japan & Santa Ana, CA, USA SPONSOR ORG: Inst. Telev. Eng. Japan; SID CONF TITLE: Proceedings of 15th International Display Research Conference CONF LOCATION: Hamamatsu, Japan; 16-18 Oct. 1995 YEAR: 1995 TREATMENT: T Theoretical or Mathematical RECORD TYPE: Conference Paper ABSTRACT: This article describes a computational model for color constancy in shadows which includes two visual modules for recovering both spatial distribution of illuminant and reflectances of object surfaces from the input scene. Each module has a line process which interprets whether a given edge is derived from reflectance edge or illuminant edge based on the prior knowledge of shadows such as brightness mainly changes at the boundary of a shadowed area. Simulation results, using Mondrian images, showed that the proposed model correctly detected shadow edge and illuminant colors, and successfully removed them from the input scene. This suggests that it is necessary to recover both surface reflectance and spatial distribution of illuminant to achieve color constancy in shadows (6 Refs.) DESCRIPTORS: brightness; colour vision; edge detection; image colour analysis; modelling; neural nets; reflectivity; visual perception IDENTIFIERS: color constancy in shadows; neural network model; computational model; visual modules; spatial distribution of illuminant; reflectances of object surfaces; input scene; line process; prior knowledge of shadows; Mondrian images; simulation; shadow edge; illuminant colors; under- constrained problem; energy function; retinex theory; color vision; color perception CLASS CODES: A8732N (Colour vision: detection, adaptation and discrimination); A8732S (Psychophysics of vision, visual perception, binocular vision); A8710 (General, theoretical, and mathematical biophysics); C1250 (Pattern recognition); C1230D (Neural nets); C1290L (Systems theory applications in biology and medicine); C1220 (Simulation, modelling and identification)Record: 33
COPYRIGHT: Copyright 1998, IEE RECORD NO.: 5836140 INSPEC Abstract No: B9803-6140C-597; C9803-5260B-394 AUTHOR: In Kyu Park; Il Dong Yun; Sang Uk Lee EDITOR: Chin, R.; Pong, T.-C. CORP SOURCE: Lab. of Real Time Vision, Seoul Nat. Univ., South Korea TITLE: A color normalization algorithm for image indexing SOURCE: Computer Vision - ACCV '98. Third Asian Conference on Computer Vision. Proceedings, p. 2 vol. (xxiv+761+757), 96-103 vol.1 PLACE OF PUBL: Germany ISBN: 3540639306 LANGUAGE: English PUBLISHER: Springer-Verlag; Berlin, Germany SPONSOR ORG: IEEE Hong Kong Sect.; Hong Kong Univ. Sci. & Technol.; Hong Kong Ind. Dept CONF TITLE: Computer Vision - ACCV'98 CONF LOCATION: Hong Kong; 8-10 Jan. 1998 YEAR: 1997 TREATMENT: T Theoretical or Mathematical RECORD TYPE: Conference Paper ABSTRACT: In this paper, a color normalization algorithm is proposed to compensate the difference of illumination between two images, which could be used for pre-processing, i.e., color constancy step in a histogram-based indexing algorithm. Unlike traditional color constancy algorithms, are attempt to transform the query image, so that the lighting condition is adjusted to be same with the reference image. The proposed algorithm assumes the Maloney and Wandel's reflectance model (1986), and normalizes the magnitude of color components of input image. Experiments are carried out to evaluate the proposed algorithm. In the experiments, it is shown that the transformed lighting condition is almost same as the reference image in the color histogram domain. In addition, it is also shown that the performance of Swain's color indexing can be enhanced by combining the proposed algorithm (12 Refs.) DESCRIPTORS: image colour analysis; indexing IDENTIFIERS: color normalization; image indexing; difference of illumination; histogram-based indexing; color constancy; color indexing CLASS CODES: B6140C (Optical information, image and video signal processing); C5260B (Computer vision and image processing techniques); C1250 (Pattern recognition)Record: 35
COPYRIGHT: Copyright 1998, IEE RECORD NO.: 5808088 INSPEC Abstract No: B9802-6140C-462; C9802-1250-203 AUTHOR: Jobson, D.J.; Rahman, Z.-U.; Woodell, G.A. CORP SOURCE: NASA Langley Res. Center, Hampton, VA, USA TITLE: Retinex image processing: improved fidelity to direct visual observation SOURCE: Final Program and Proceedings of IS&T/SID Fourth Color Imaging Conference: Color Science, Systems and Applications, p. xvi+248, 124-6 PLACE OF PUBL: USA ISBN: 0892081961 LANGUAGE: English PUBLISHER: Soc. Imaging Sci. & Technol; Springfield, VA, USA SPONSOR ORG: Soc. Imaging Sci. & Technol.; Soc. Inf. Display CONF TITLE: Proceedings of the Fourth Color Imaging Conference: Color Science, Systems and Applications CONF LOCATION: Scottsdale, AZ, USA; 19-22 Nov. 1996 YEAR: 1996 TREATMENT: P Practical; X Experimental RECORD TYPE: Conference Paper ABSTRACT: Recorded color images differ from direct human viewing by the lack of dynamic range compression and color constancy. Research is summarized which develops the center/surround retinex concept originated by E. Land (1986) through a single-scale design to a multi-scale design with color restoration (MSRCR). The MSRCR synthesizes dynamic range compression, color constancy, and color rendition and, thereby, approaches fidelity to direct observation (7 Refs.) DESCRIPTORS: image coding; image colour analysis; image enhancement; image restoration; visual perception IDENTIFIERS: retinex image processing; improved fidelity; direct visual observation; recorded color images; center/surround retinex concept; single-scale design; multi-scale design; color restoration; dynamic range compression; color constancy; color rendition; image enhancement; digital photoprocessing; digital darkroom CLASS CODES: B6140C (Optical information, image and video signal processing); C1250 (Pattern recognition); C5260B (Computer vision and image processing techniques)Record: 36
COPYRIGHT: Copyright 1998, IEE RECORD NO.: 5808072 INSPEC Abstract No: C9802-1250-196 AUTHOR: Funt, B.; Cardei, V.; Barnard, K. CORP SOURCE: Sch. of Comput. Sci., Simon Fraser Univ., Burnaby, BC, Canada TITLE: Learning color constancy SOURCE: Final Program and Proceedings of IS&T/SID Fourth Color Imaging Conference: Color Science, Systems and Applications, p. xvi+248, 58-60 PLACE OF PUBL: USA ISBN: 0892081961 LANGUAGE: English PUBLISHER: Soc. Imaging Sci. & Technol; Springfield, VA, USA SPONSOR ORG: Soc. Imaging Sci. & Technol.; Soc. Inf. Display CONF TITLE: Proceedings of the Fourth Color Imaging Conference: Color Science, Systems and Applications CONF LOCATION: Scottsdale, AZ, USA; 19-22 Nov. 1996 YEAR: 1996 TREATMENT: X Experimental RECORD TYPE: Conference Paper ABSTRACT: We decided to test a surprisingly simple hypothesis; namely, that the relationship between an image of a scene and the chromaticity of scene illumination could be learned by a neural network. The thought was that if this relationship could be extracted by a neural network, then the trained network would be able to determine a scene's illuminant from its image, which would then allow correction of the image colors to those relative to a standard illuminance, thereby providing color constancy. Using a database of surface reflectances and illuminants, along with the spectral sensitivity functions of our camera, we generated thousands of images of randomly selected illuminants lighting scenes' of 1 to 60 randomly selected reflectances. During the learning phase the network is provided the image data along with the chromaticity of its illuminant. After training, the network outputs (very quickly) the chromaticity of the illumination given only the image data. We obtained surprisingly good estimates of the ambient illumination lighting from the network even when applied to scenes in our lab that were completely unrelated to the training data (10 Refs.) DESCRIPTORS: backpropagation; image colour analysis; perceptrons IDENTIFIERS: learning color constancy; scene image; chromaticity of scene illumination; neural network; image colors correction; standard illuminance; database of surface reflectances; camera spectral sensitivity functions; randomly selected illuminants; chromaticity resolution; ambient illumination lighting; adaptive model; perceptron; backpropagation; angular error; gamut mapping CLASS CODES: C1250 (Pattern recognition); C1230D (Neural nets); C1260 (Information theory)Record: 37
COPYRIGHT: Copyright 1997, IEE RECORD NO.: 5761545 INSPEC Abstract No: C9801-3390C-032 AUTHOR: Marini, D.; Rizzi, A. CORP SOURCE: Dipt. di Sci. dell'Inf., Milan Univ., Italy TITLE: Non-supervised chromatic illuminant: corrector for autonomous robots SOURCE: Proceedings Second EUROMICRO Workshop on Advanced Mobile Robots (Cat. No.97TB100193), p. x+175, 126-32 PLACE OF PUBL: USA ISBN: 0818681748 LANGUAGE: English PUBLISHER: IEEE Comput. Soc; Los Alamitos, CA, USA SPONSOR ORG: Univ. Studi di Brescia; Comune di Brescia; Consiglio Nat. Ricerche; Camera di Commercio, Ind. Artigianato e Agricoltura - Brescia; Credito Agrario Bresciano S.P.A.; Tiesse Robot; Azienda Servizi Municipalizzati Brescia; Brescia Central del Latte CONF TITLE: Proceedings Second EUROMICRO Workshop on Advanced Mobile Robots CONF LOCATION: Brescia, Italy; 22-24 Oct. 1997 YEAR: 1997 COPYRIGHT NO: 0 8186 8174 8/97/$10.00 TREATMENT: T Theoretical or Mathematical; X Experimental RECORD TYPE: Conference Paper ABSTRACT: One of the well-known problems in colour image interpretation is the colour-constancy problem. Autonomous robots that use colour information to select objects or landmarks can be deceived in presence of heavy coloured illuminants. Classic chromatic filtering presupposes detailed information about light source characteristics, but this is not always possible. The presence of emergency lights or different kinds of light sources can heavily influence object colour. Retinex theory, by Land and McCann (1971), can resolve these problems. This theory gives color perception on a color space based on three brightness computed as relative reflectance along multiple exploration paths of the perceived scene. This paper considers the application of this theory in order to allow automatic colour detection in autonomous robots. The algorithm has been tested on simple coloured scenes illuminated with different light sources. The results obtained are compared (15 Refs.) DESCRIPTORS: brightness; image colour analysis; light sources; mobile robots; path planning; reflectivity; robot vision IDENTIFIERS: chromatic illuminant; autonomous mobile robots; colour image interpretation; colour-constancy; chromatic filtering; light sources; object colour; Retinex theory; brightness; relative reflectance; automatic colour detection CLASS CODES: C3390C (Mobile robots); C1250 (Pattern recognition); C5260B (Computer vision and image processing techniques)Record: 40
COPYRIGHT: Copyright 1997, IEE RECORD NO.: 5744757 INSPEC Abstract No: B9712-6140C-434; C9712-1250-183 AUTHOR: Lenz, R.; Meer, P. CORP SOURCE: Dept. of Electr. Eng., Linkoping Univ., Sweden TITLE: Color image normalization through illuminant recovery SOURCE: 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (Cat. No.97CB36052), p. 5 vol. (xxii+xxv+xxiv+xxii+4156), 3141-4 vol.4 PLACE OF PUBL: USA ISBN: 0818679190 LANGUAGE: English PUBLISHER: IEEE Comput. Soc. Press; Los Alamitos, CA, USA SPONSOR ORG: IEEE Signal Process. Soc.; DPG; GI; ITG; TUM CONF TITLE: 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing CONF LOCATION: Munich, Germany; 21-24 April 1997 YEAR: 1997 COPYRIGHT NO: 0 8186 7919 0/97/$10.00 TREATMENT: T Theoretical or Mathematical; X Experimental RECORD TYPE: Conference Paper ABSTRACT: The information in a color image is always a function of the illuminating source, the geometry, the reflectance properties of the object and the characteristic of the camera. Separating the influence of the spectral distribution of the illumination and the reflectance properties of the object is known as the color constancy problem. Successful separation is important for vision and pattern recognition tasks, quality control in the graphic arts and image database applications. We describe an approach to the color constancy problem which is based on statistical assumptions about the distribution of colors. It uses the eigenvector system of the logarithmic spectra in a large database of color samples and employs methods from robust statistics to recover the illumination spectrum. We illustrate the performance of the algorithm with a simulation in which the effect of the illumination by the standard A-source is eliminated (10 Refs.) DESCRIPTORS: eigenvalues and eigenfunctions; image colour analysis; image sampling; pattern recognition; reflectivity; spectral analysis; statistical analysis; visual databases IDENTIFIERS: color image normalization; illuminant recovery; illuminating source; geometry; reflectance properties; camera; spectral distribution; color constancy problem; pattern recognition; vision recognition; quality control; graphic arts; image database applications; statistical assumptions; color distribution; eigenvector system; logarithmic spectra; color samples; robust statistics; illumination spectrum recovery; algotithm performance; simulation CLASS CODES: B6140C (Optical information, image and video signal processing); B0240Z (Other topics in statistics); C1250 (Pattern recognition); C5260B (Computer vision and image processing techniques); C1140Z (Other topics in statistics)
|
||||||||||||||||||||||||||||||||||||||
|
||||||||||||||||||||||||||||||||||||||
 | ||||||||||||||||||||||||||||||||||||||
| FirstSearch. Copyright 1992-1999 OCLC as to electronic presentation and platform. All rights reserved. | ||||||||||||||||||||||||||||||||||||||