Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

42

AGI
2011

favoriteEmaildiscussreport

261views Artificial Intelligence» more AGI 2011»

Towards a General Vision System Based on Symbol-Relation Grammars and Bayesian Networks

13 years 2 months ago

Towards a General Vision System Based on Symbol-Relation Grammars and Bayesian Networks

Download ccc.inaoep.mx

Abstract. A novel approach to create a general vision system is presented. The proposed method is based on a visual grammar representation which is transformed to a Bayesian network which is used for object recognition. We use a symbol-relational grammar for a hierarchical description of objects, incorporating spatial relations. The structure of a Bayesian network is obtained automatically form the grammar, and its parameters are learned from examples. The method is illustrated with two examples for face recognition.

Elias Ruiz, Augusto Meléndez, Luis Enrique

Real-time Traffic

AGI 2011 | Artificial Intelligence | Bayesian Network | Relational Grammar | Visual Grammar |

claim paper

Related Content

» Context and Hierarchy in a Probabilistic Image Model

» Feature Learning for Recognition with Bayesian Networks

» Control in a 3D Reconstruction System using Selective Perception

» Person Tracking with AudioVisual Cues Using the Iterative Decoding Framework

» Selecting highdimensional mixed graphical models using minimal AIC or BIC forests

» Geospatial information integration based on the conceptualization of geographic domain

» Probabilistic Prediction of Student Affect from Hand Gestures

» Studying XCSBOA learning in Boolean functions structure encoding and random Boolean functi...

Post Info
More Details (n/a)

Added	24 Aug 2011
Updated	24 Aug 2011
Type	Journal
Year	2011
Where	AGI
Authors	Elias Ruiz, Augusto Meléndez, Luis Enrique Sucar

Comments (0)