(1) the complete title of one (or more) paper(s) published in the open literature describing the work that the author claims describes a human-competitive result, * Trujillo, L., Olague. G. Using Evolution to Learn How to Perform Interest Point Detection. to appear International Conference on Pattern Recognition. August 20-24, 2006. Hong Kong, China. ICPR 2006. * Trujillo, L., Olague. G. Synthesis of Interest Point Detectors Through Genetic Programming. to appear Genetic and Evolutionary Computation Conference. July 8-12, 2006. Seattle, WA, USA.. GECCO 2006. (2) the name, complete physical mailing address, e-mail address, and phone number of EACH author of EACH paper, Leonardo Trujillo Proyecto EvoVisi,As(Bn Departamento de Ciencias de la Computaci,As(Bn, Divisi,As(Bn de F,Am(Bsica Aplicada Centro de Investigaci,As(Bn Cient,Am(Bfica y de Educaci,As(Bn Superior de Ensenada Ensenada B.C. M,Ai(Bxico trujillo@cicese.mx Gustavo Olague Proyecto EvoVisi,As(Bn Departamento de Ciencias de la Computaci,As(Bn, Divisi,As(Bn de F,Am(Bsica Aplicada Centro de Investigaci,As(Bn Cient,Am(Bfica y de Educaci,As(Bn Superior de Ensenada Ensenada B.C. M,Ai(Bxico olague@cicese.mx (3) the name of the corresponding author (i.e., the author to whom notices will be sent concerning the competition), Gustavo Olague (4) the abstract of the paper(s), This contribution presents a novel approach for the automatic generation of a low-level feature extractor that is useful in higher-level computer vision tasks. Specifically, our work centers on the well-known computer vision problem of interest point detection. We pose interest point detection as an optimization problem, and are able to apply Genetic Programming to generate operators that exhibit human-competitive performance when compared with state-of-the-art designs. This work uses the repeatability rate that is applied as a benchmark metric in computer vision literature as part of the GP fitness function, together with a measure of the entropy related with the point distribution across the image. This two measures promote geometric stability and global separability under several types of image transformations. This paper introduces a Genetic Programming implementation that was able to discover a modified version of the DET operator proposed by Beaudet in 1978, that shows a surprisingly high-level of performance. In this work emphasis was given to the balance between genetic programming and domain knowledge expertise to obtain results that are equal or better than human created solutions. (5) a list containing one or more of the eight letters (A, B, C, D, E, F, G, or H) that correspond to the criteria (see above) that the author claims that the work satisfies, (B) The result is equal to or better than a result that was accepted as a new scientific result at the time when it was published in a peer-reviewed scientific journal. (C) The result is equal to or better than a result that was placed into a database or archive of results maintained by an internationally recognized panel of scientific experts. (D) The result is publishable in its own right as a new scientific result ,A>(B independent of the fact that the result was mechanically created. (E) The result is equal to or better than the most recent human-created solution to a long-standing problem for which there has been a succession of increasingly better human-created solutions. (F) The result is equal to or better than a result that was considered an achievement in its field at the time it was first discovered. (G) The result solves a problem of indisputable difficulty in its field. (6) a statement stating why the result satisfies the criteria that the contestant claims (see the examples below as a guide to aid in constructing this part of the submission), (B) The result is equal to or better than a result that was accepted as a new scientific result at the time when it was published in a peer-reviewed scientific journal. Numerous interest point detectors have been published in scientific journals and conference proceedings such as: Kitchen and Rosenfeld. Gray-Level Corner Detection. Pattern Recognition Letters, 1:95-102. Dreschler and Nagel. Volumetric Model and 3D trajectory of a moving car derived from monocular TV frame sequences of a street scene. Computer Graphics and Image Processing. 20:199-228. Previous version appear at ICPR Dreschler and Nagel. On the selection of critical points and local curvature extrema of region boundaries fro inter-frame matching. In Proc. International Conference on Pattern Recognition 1982. pp. 542-544. Harris and Stephens. A combined corner and edge detector. Fourth Alvey Vision Conference 1988. pp. 147-151. Foerstner. A feature based correspondence algorithm for image matching. International Archives of Photogrammetry and Remote Sensing. 26(3) pp. 150-166. (C) The result is equal to or better than a result that was placed into a database or archive of results maintained by an internationally recognized panel of scientific experts. To test our results we have used a standard test that is maintained by the Visual Geometry Group of the Robotics Research Group that can be accessed at the following address: http://www.robots.ox.ac.uk/~vgg/research/affine/ This test was originally developed by researchers from INRIA Rhone Alpes and the current test includes contributions from University of Oxford, Katholieke Universiteit Leuven, and the Center for Machine Perception at the Czech Technical University. (D) The result is publishable in its own right as a new scientific result ,A>(B independent of the fact that the result was mechanically created. The Interest Point found by Genetic Programming uses a Gaussian filter to each term of the determinant of the Hessian matrix which was unexpected and algorithmically appealing and original in its own right. (E) The result is equal to or better than the most recent human-created solution to a long-standing problem for which there has been a succession of increasingly better human-created solutions. Our Genetic Programming system was able to produce operators that outperform all operators designed by human experts on the images proposed in the test with an exception only for the case of illumination in which Harris was slightly better. Our results that will be published in ICPR 2006 and GECCO 2006 could be compared with those published at the following journal paper. Schmid, Mohr, and Bauckhage. Evaluation of Interest Point Detectors. International Journal of Computer Vision. 37(2), 151-172, 2000. (F) The result is equal to or better than a result that was considered an achievement in its field at the time it was first discovered. Our GP based approach rediscovered an improved version of Baudet corner detector. P.R. Beaudet. Rotational Invariant Image Operators. In Proc. International Conference on Pattern Recognition, Tokyo, 1978, pages 579-583. Moreover, it also proposes an operator that is based on the Difference-of-Gaussian which is a concept that has been used by researchers in similar computer vision problems but not for interest point detection. (G) The result solves a problem of indisputable difficulty in its field. Research on feature extraction is still a hot topic on computer vision. Most conferences and computer vision journals devote a special section to feature extraction. In particular researchers are trying to propose new interest point detectors to solve all kind of machine vision applications. Our methodology opens a new avenue for research on feature extraction. (7) a full citation of the paper (that is, author names; publication date; name of journal, conference, technical report, thesis, book, or book chapter; name of editors, if applicable, of the journal or edited book; publisher name; publisher city; page numbers, if applicable); * Trujillo, L., Olague. G. Using Evolution to Learn How to Perform Interest Point Detection. to appear International Conference on Pattern Recognition. August 20-24, 2006. Hong Kong, China. ICPR 2006. * Trujillo, L., Olague. G. Synthesis of Interest Point Detectors Through Genetic Programming. to appear Genetic and Evolutionary Computation Conference. July 8-12, 2006. Seattle, WA, USA.. GECCO 2006. (8) a statement either that $(B!H(Bany prize money, if any, is to be divided equally among the co-authors$(B!I(B OR a specific percentage breakdown as to how the prize money, if any, is to be divided among the co-authors; and (9) a statement stating why the judges should consider the entry as $(B!H(Bbest$(B!I(B in comparison to other entries that may also be $(B!H(Bhuman-competitive.$(B!I (Bany prize money, if any, is to be divided equally among the co-authors. We believe that this work opens a new avenue of research in the synthesis of feature detectors because it is the first time that an acceptable computer vision test is used to generate a mathematical expression that provides a set of distinctive features of an image which could help at solving problems in areas of human endeavour that matters. This work is also important because the emerging "Evolutionary Computer Vision" area could be further strengthened and hopefully new works will be developed based on the ideas reported by this work. * Olague, G., Cagnoni, S., and Lutton, E. (eds) Introduction to the Special Issue on Evolutionary Computer Vision and Image Understanding. to appear Pattern Recognition Letters, Elsevier Science. * Olague, G., Lutton, E., and Cagnoni, S. (eds) Evolutionary Computer Vision. In preparation. Evolutionary Computation, MIT Press.