Journal Article10.1142/S0218001491000247
Model-based object recognition using probabilistic logic and maximum entropy
4
TL;DR: A method based on maximum entropy is developed which assigns measures of likelihood for the presence of objects in the two-dimensional image and is applied to and evaluated on real and simulated image data.
read more
Abstract: In the visual context, a reasoning system should he capable of inferring a scene description using evidence derived from data-driven processing of the iconic image data This evidence may consist of a set of curvilinear boundaries, which are obtained by grouping local edge data into extended features Using linear primitives, a framework is described which represents the information contained in pre-formed models of possible objects in the scene, and in the segmented scenes themselves A method based on maximum entropy is developed which assigns measures of likelihood for the presence of objects in the two-dimensional image This method is applied to and evaluated on real and simulated image data, and the effectiveness of the approach is discussed
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Image analysis and computer vision: 1991
TL;DR: A bibliography of nearly 1200 references related to computer vision and image analysis, arranged by subject matter is presented, covering topics including architectures; computational techniques; feature detection and segmentation; image analysis; and motion.
17
Discriminative distance measures for object detection
S. Mahamud,Martial Hebert,Reid Simmons +2 more
- 01 Jan 2002
TL;DR: A detection framework whose core component is a nearest neighbor search over object parts, and a model for the optimal distance measure that combines the discriminative powers of more elementary distance measures associated with a collection of simple feature spaces that are easy and efficient to implement is sought.
•Proceedings Article
Maximum entropy in Nilsson's probabilistic logic
Thomas B. Kane
- 20 Aug 1989
TL;DR: A new way of looking at the probability constraints enforced by the framework is proposed, which allows the expert to include conditional probabilities in the semantic tree, thus making Probabilistic Logic more expressive.
•Dissertation
Reasoning with uncertainty using Nilsson's probabilistic logic and the maximum entropy formalism
Thomas Brett Kane
- 01 Jan 1992
TL;DR: The main finding in this thesis is that Nilsson's Probabilistic Logic can be succesfully developed beyond the structure proposed by Nilsson, and a new model of entailment is presented which overcomes deficiencies, allowing Probabilists Logic the full representational power of Bayesian Inferencing.
1
Related Papers (5)
Alexander Bachmann,Irina Lulcheva +1 more
- 01 Sep 2009
Pierre Moreels,Pietro Perona +1 more
- 01 Dec 2004