Title :
A new strategy for applying grammatical inference to image classification problems
Author :
Pistori, H. ; Calway, Andrew ; Flach, P.
Author_Institution :
INOVISAO Comput. Vision Lab., Dom Bosco Catholic Univ., Campo Grande, Brazil
Abstract :
This paper presents a new strategy to represent an image as a string so that standard grammar induction techniques can be used in computer vision problems. Two sets of experiments using an artificial and a real dataset have been conducted in order to explore the new strategy parameters and to have a first glimpse on its comparative performance against some standard machine learning techniques. The results are encouraging and the proposal opens new paths of exploration for syntactical pattern recognition.
Keywords :
computer vision; grammars; image classification; inference mechanisms; learning (artificial intelligence); comparative performance; computer vision problems; grammatical inference; image classification problems; image represent strategy; standard grammar induction techniques; standard machine learning techniques; syntactical pattern recognition; Dictionaries; Feature extraction; Grammar; Inference algorithms; Standards; Training; Visualization; Grammar Inference; Image Processing; Syntactical Pattern Recognition;
Conference_Titel :
Industrial Technology (ICIT), 2013 IEEE International Conference on
Conference_Location :
Cape Town
Print_ISBN :
978-1-4673-4567-5
Electronic_ISBN :
978-1-4673-4568-2
DOI :
10.1109/ICIT.2013.6505814
