Game-Theoretic Integration for Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Game-Theoretic Approach to Integration of Modules
IEEE Transactions on Pattern Analysis and Machine Intelligence
Potential-Based Algorithms in On-Line Prediction and Game Theory
Machine Learning
Issues in Ground-Truthing Graphic Documents
GREC '01 Selected Papers from the Fourth International Workshop on Graphics Recognition Algorithms and Applications
Uncertainty Modeling and Model Selection for Geometric Inference
IEEE Transactions on Pattern Analysis and Machine Intelligence
A survey of table recognition: Models, observations, transformations, and inferences
International Journal on Document Analysis and Recognition
A language for specifying and comparing table recognition strategies
A language for specifying and comparing table recognition strategies
A formal analysis of why heuristic functions work
Artificial Intelligence
Hi-index | 0.00 |
There is need for more formal specification of recognition tasks. Currently, it is common to use labeled training samples to illustrate the task to be performed. The mathematical theory of games may provide more formal and complete definitions for recognition tasks. We present an imitation game that describes a wide variety of recognition tasks, including the classification of isolated patterns and structural analysis. In each round of the game, a set of ‘players' try to match the interpretation of an input produced by a set of ‘experts.' The ‘playing field' on which experts and players operate is a set of interpretations generated from legal sequences of ‘moves' for a round. The expert and player moves transform interpretations, and select interpretations for output. The distance between interpretations in the playing field is defined by a distance metric for interpretations, and the game outcome by a ranking function on distance values observed for players' interpretations. We demonstrate how this imitation game may be used to define and compare recognition tasks, and clarify the evaluation of proposed solutions.