Cesar Puente's home Page

.: Cesar Puente Home Page :.

Cesar Puente is a master student at the CICESE research center.

He holds a Bachelor's degree in Computer Engineering from the Universidad Autónoma de San Luis Potosí, in San Luis Potosí city, México. He currently lives in Ensenada, México; where he is studying to get the master degree in Computer Science within the Computer Science Department of the Applied Physics Division at CICESE --- Centro de Investigación Científica y de Educación Superior de Ensenada ---.

In order to get the master degree, his thesis faces the 3D reconstruction problem having two or more images from the scene whose reconstruction is wanted. His work is a part of the Evovisión team.

USA

México

Dep. of Computer Science, CICESE Research Center

P.O. Box 434944

San Diego, CA. 92143-4944 USA

Depto. de Ciencias de la Computación, CICESE

Carr. Tijuana-Ensenada Km. 107. C.P. 22860.

Ensenada, B.C. México

e-mail: puente@cicese.mx

phone: +52 (646) 175.05.00 ext 25518

Publications

Olague, G., Puente. C. Parisian Evolution with Honeybees for Three-Dimensional Reconstruction. to appear
Genetic and Evolutionary Computation Conference. July 8-12, 2006. Seattle, WA, USA.. GECCO 2006.

Olague, G. Puente, C.. The Honeybee Search Algorithm for Three-Dimensional Reconstruction.
8 th European Workshop on Evolutionary Computation in Image Analysis and Signal Processing. Lecture Notes in Computer Science 3907. Springer-Verlag. pp. 427-437. EvoIASP2006. Nominated for Best Paper Award.

Master Thesis

Title: Tridimensional Reconstruction of the objects in a scene.

Thesis Advisors: Gustavo Olague and Jose Luis Briseño.

Briefly description:

The objective is to obtain real three-dimensional measurements; of depth, scale and size; of the objects in a scene from two or more images taken from different points of view from this scene.

This can be made based on the geometric camera acquisition process; and based on the relationship -- geometric also -- that exists between the pixels of the different images that represent the same three-dimensional point.

Because this process would have to do pixel by pixel in the images, it is tried to apply a biologically inspired technique based on the process of searching food of a beehive (called foraging process).

This technique consist in compute three-dimensional coordinates just for a few principal points of the objects; after that, some computational entities -- the bees -- will find the points between the principal ones, just like the bees, in the nature, find flower patches from one flower.

Figure. 3D measures of the objects in the scene are obtained with the bees approach.

Thesis Advances (in spanish).

1st. Advance: Theoretical frame and work proposal.

2nd. Advance: Massive triangulation and Experimentation.

3rd. Advance: [ Coming soon... ]