1. P. S. Churchland and T. J. Sejnowski. The Computational Brain. MIT Press, 1992.
   Keywords: brain, perception, artificial intelligence.

   Abstract: This attractive and well-illustrated volume falls somewhere between a trade book and a textbook, with a style well suited for the Scientific American reader, as well as the active scientist, who may know something of either computer science or neuroscience but welcomes a crisp narrative that includes the necessary background from each discipline.... The reader will be well rewarded who seeks to understand, from well-chosen examples, how to merge the analysis of neuroscientific data with the developments of computational principles." -- Michael A. Arbib, Science The Computational Brain is the first unified and broadly accessible book to bring together computational concepts and behavioral data within a neurobiological framework. Churchland and Sejnowski address the foundational ideas of the emerging field of computational neuroscience, examine a diverse range of neural network models, and consider future directions of the field.

   
   

   @Book{chur_sejn_92,
   author = {Churchland, P. S. and Sejnowski, T. J.},
   editor = {Cambridge},
   title = {The Computational Brain},
   publisher = {MIT Press},
   year = {1992},
   url = {http://psyche.cs.monash.edu.au/v1/psyche-1-03-bridgeman.html},
   abstract = {This attractive and well-illustrated volume falls somewhere between a trade book and a textbook, with a style well suited for the Scientific American reader, as well as the active scientist, who may know something of either computer science or neuroscience but welcomes a crisp narrative that includes the necessary background from each discipline.... The reader will be well rewarded who seeks to understand, from well-chosen examples, how to merge the analysis of neuroscientific data with the developments of computational principles." -- Michael A. Arbib, Science The Computational Brain is the first unified and broadly accessible book to bring together computational concepts and behavioral data within a neurobiological framework. Churchland and Sejnowski address the foundational ideas of the emerging field of computational neuroscience, examine a diverse range of neural network models, and consider future directions of the field.}, rating = {B}, keywords = {brain, perception, artificial intelligence} 
   }
   




2. E. Shimon. Visual perception. 1992.
   Keywords: artificial vision.
   

   @book{edel_92,
   author = {E. Shimon},
   title = {Visual perception},
   text = {Edelman, S. (1992b), Visual perception, In Shapiro, Stuart C., (ed.), Encyclopedia of Artificial Intelligence. (Wiley-Interscience, New York), 1655--1664.},
   year = {1992},
   url = {http://kybele.psych.cornell.edu/~edelman/Course/perception/perception.html},
   keywords = {artificial vision},
   rating = {C} 
   }
   

1. J. J. Atick. Entropy minimization: A design principle for sensory perception?. International Journal of Neural Systems, (3):81-90, 1992.
   Keywords: information theory, statistics, perception.
   

   @Article{atic_92,
   author = {Atick, J. J.},
   title = {Entropy minimization: A design principle for sensory perception?},
   journal = {International Journal of Neural Systems},
   year = {1992},
   number = {3},
   pages = {81-90},
   rating = {B},
   keywords = {information theory, statistics, perception} 
   }
   




2. Claude Lobry. A propos du sens des textes mathématiques, un exemple: la théorie des bifurcations dynamiques. Annales de l'Institut Fourier, 1992.
   Keywords: mathematics, dynamical systems.
   

   Comments: très intéressants commentaires sur le théorème de Poincaré-Andronov-Hopf. Un passage enrichissant dans l'analyse non standard.

   
   

   @article{lobr_92,
   author = {Lobry, Claude},
   title = {A propos du sens des textes mathématiques, un exemple: la théorie des "bifurcations dynamiques"},
   journal = {Annales de l'Institut Fourier},
   year = {1992},
   keywords = {mathematics, dynamical systems},
   rating = {C},
   url = {http://annalif.ujf-grenoble.fr/TexteScan/aif_1992__42_1-2/aif_1992__42_1-2_327_0/aif_1992__42_1-2_327_0.pdf},
   comments = {très intéressants commentaires sur le théorème de Poincaré-Andronov-Hopf. Un passage enrichissant dans l'analyse non standard.} 
   }
   




3. Claude Lobry. A propos du sens des textes mathématiques, un exemple: la théorie des bifurcations dynamiques. Annales de l'Institut Fourier, 1992.
   Keywords: mathematics, dynamical systems.
   

   Comments: très intéressants commentaires sur le théorème de Poincaré-Andronov-Hopf. Un passage enrichissant dans l'analyse non standard.

   
   

   @article{lobr_92,
   author = {Lobry, Claude},
   title = {A propos du sens des textes mathématiques, un exemple: la théorie des "bifurcations dynamiques"},
   journal = {Annales de l'Institut Fourier},
   year = {1992},
   keywords = {mathematics, dynamical systems},
   rating = {C},
   url = {http://annalif.ujf-grenoble.fr/TexteScan/aif_1992__42_1-2/aif_1992__42_1-2_327_0/aif_1992__42_1-2_327_0.pdf},
   comments = {très intéressants commentaires sur le théorème de Poincaré-Andronov-Hopf. Un passage enrichissant dans l'analyse non standard.} 
   }
   




4. David H. Marimont and Brian A. Wandell. Linear models of surface and illuminant spectra. JOSA A, 9(11):1905-1913, 1992.

   Abstract: We describe procedures for creating efficient spectral representations for color. The representations generalize conventional tristimulus representations, which are based on the peripheral encoding by the human eye. We use low-dimensional linear models to approximate the spectral properties of surfaces and illuminants with respect to a collection of sensing devices. We choose the linear-model basis functions by minimizing the error in approximating sensor responses for collections of surfaces and illuminants. These linear models offer some conceptual simplifications for applications such as printer calibration; they also perform substantially better than principal-components approximations for computer-graphics applications.

   
   

   Comments: PCA sur reflectances devrait bien sûr tenir en compte le fait qu'on observe via des capteurs. reste très insuffisant, mais déjà mieux que d'hab.

   
   

   @Article{mari_wand_92,
   author = {Marimont, David H. and Wandell, Brian A.},
   title = {Linear models of surface and illuminant spectra},
   journal = {JOSA A},
   year = {1992},
   volume = {9},
   number = {11},
   pages = {1905-1913},
   url = {ftp://white.stanford.edu/users/brian/color/MarimontWandell1992.pdf},
   abstract = {We describe procedures for creating efficient spectral representations for color. The representations generalize conventional tristimulus representations, which are based on the peripheral encoding by the human eye. We use low-dimensional linear models to approximate the spectral properties of surfaces and illuminants with respect to a collection of sensing devices. We choose the linear-model basis functions by minimizing the error in approximating sensor responses for collections of surfaces and illuminants. These linear models offer some conceptual simplifications for applications such as printer calibration; they also perform substantially better than principal-components approximations for computer-graphics applications.},
   comments = {PCA sur reflectances devrait bien sûr tenir en compte le fait qu'on observe via des capteurs. reste très insuffisant, mais déjà mieux que d'hab.},
   rating = {C},
   keywoards = {color constancy, reflectance} 
   }
   




5. P. B. L. Meijer. An Experimental System for Auditory Image Representations. IEEE Transactions on Biomedical Engineering, 39(2):112-121, 1992.
   Keywords: sensory substitution.

   Abstract: This paper presents an experimental system for the conversion of images into sound patterns. The system was designed to provide auditory image representations within some of the known limitations of the human hearing system, possibly as a step towards the development of a vision substitution device for the blind. The application of an invertible (1-to-1) image-to-sound mapping ensures the preservation of visual information. The system implementation involves a pipelined special purpose computer connected to a standard television camera. The time-multiplexed sound representations, resulting from a real-time image-to-sound conversion, represent images up to a resolution of 64 × 64 pixels with 16 grey-tones per pixel. A novel design and the use of standard components have made for a low-cost portable prototype conversion system having a power dissipation suitable for battery operation. Computerized sampling of the system output and subsequent calculation of the approximate inverse (sound-to-image) mapping provided the first convincing experimental evidence for the preservation of visual information in the sound representations of complicated images. However, the actual resolution obtainable with human perception of these sound representations remains to be evaluated.

   
   

   @Article{meij_92,
   author = {Meijer, P. B. L.},
   title = {An Experimental System for Auditory Image Representations},
   journal = {IEEE Transactions on Biomedical Engineering},
   year = {1992},
   number = {2},
   volume = {39},
   pages = {112-121},
   url = {http://www.seeingwithsound.com/voicebme.html},
   rating = {C},
   keywords = {sensory substitution},
   abstract = {This paper presents an experimental system for the conversion of images into sound patterns. The system was designed to provide auditory image representations within some of the known limitations of the human hearing system, possibly as a step towards the development of a vision substitution device for the blind. The application of an invertible (1-to-1) image-to-sound mapping ensures the preservation of visual information. The system implementation involves a pipelined special purpose computer connected to a standard television camera. The time-multiplexed sound representations, resulting from a real-time image-to-sound conversion, represent images up to a resolution of 64 × 64 pixels with 16 grey-tones per pixel. A novel design and the use of standard components have made for a low-cost portable prototype conversion system having a power dissipation suitable for battery operation. Computerized sampling of the system output and subsequent calculation of the approximate inverse (sound-to-image) mapping provided the first convincing experimental evidence for the preservation of visual information in the sound representations of complicated images. However, the actual resolution obtainable with human perception of these sound representations remains to be evaluated.} 
   }
   




6. Roger N. Shepard. The perceptual organization of colors: an adaptation to regurarities of the terrestrial world ?. Barlow/Cosmides/Toobu, The adapted Mind, pp 495-532, 1992.
   Keywords: color, perception, ecology.
   

   Comments: classique, mais à mon avis pose de faux problèmes.

   
   

   @ARTICLE{shep_92,
   AUTHOR = {Shepard, Roger N.},
   TITLE = {The perceptual organization of colors: an adaptation to regurarities of the terrestrial world ?},
   JOURNAL = {Barlow/Cosmides/Toobu, The adapted Mind},
   YEAR = {1992},
   pages = {495-532},
   abstract = {},
   rating = {B},
   comments = {classique, mais à mon avis pose de faux problèmes.},
   keywords = {color, perception, ecology} 
   }
   

1. O.D. Faugeras, Q.-T. Luong, and S. J. Maybank. Camera Self-Calibration: Theory and Experiments. In European Conference on Computer Vision, pages 321-334, 1992.
   Keywords: artificial vision.

   Abstract: The problem of finding the internal orientation of a camera (camera calibration) is extremely important for practical applications. In this paper a complete method for calibrating a camera is presented. In contrast with existing methods it does not require a calibration object with a known 3D shape. The new method requires only point matches from image sequences. It is shown, using experiments with noisy data, that it is possible to calibrate a camera just by pointing it at the environment...

   
   

   Comments: Le problème d'auto-calibration d'une caméra consiste à retrouver les 6 paramètres (extrinsisèque) décrivant la position de la caméra, et les 1-9 paramètres (intrinsèques) décrivant son ajustement, à partir de la mise en correspondance d'un certain nombre de points dans plusieurs images prises avec la caméra. La relation vérifiée entre les paires de points pour deux images donne les équations de Kruppa, qu'on peut résoudre exactement (couteux, instable) ou par la méthode de continuation.

   
   

   @inproceedings{faug_92,
   author = {Faugeras, O.D. and Luong, Q.-T. and Maybank, S. J.},
   title = {Camera Self-Calibration: Theory and Experiments},
   booktitle = {European Conference on Computer Vision},
   pages = {321-334},
   year = {1992},
   url = {citeseer.nj.nec.com/faugeras92camera.html},
   comments = {Le problème d'auto-calibration d'une caméra consiste à retrouver les 6 paramètres (extrinsisèque) décrivant la position de la caméra, et les 1-9 paramètres (intrinsèques) décrivant son ajustement, à partir de la mise en correspondance d'un certain nombre de points dans plusieurs images prises avec la caméra. La relation vérifiée entre les paires de points pour deux images donne les équations de Kruppa, qu'on peut résoudre exactement (couteux, instable) ou par la méthode de continuation.},
   abstract = {The problem of finding the internal orientation of a camera (camera calibration) is extremely important for practical applications. In this paper a complete method for calibrating a camera is presented. In contrast with existing methods it does not require a calibration object with a known 3D shape. The new method requires only point matches from image sequences. It is shown, using experiments with noisy data, that it is possible to calibrate a camera just by pointing it at the environment...},
   keywords = {artificial vision},
   rating = {B} 
   }
   

All the ressources below are referenced through direct links, for easier use as a library of introductory and comprehensive papers on various subjects. If a paper of yours is on this list and you do not want your homepage to be bypassed, just send me an email.

Comments and ratings are for personnal use, they do not claim to reflect academic value. It is only an indication of their relevance with respect to my own interests and the success they happened to have in the scientific community.

This document was translated from BibT_EX by bibtex2html