期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2015
卷号：74
期号：1
出版社：Journal of Theoretical and Applied
摘要：Object class recognition has exhibited significant progress in recent years and is now an integral component of many machine vision applications. However, object class recognition using visual attention image segmentation is a novel idea, which has only been developed in the past decade. This paper presents a comprehensive survey on object class recognition and object recognition algorithms, in addition to their applications based on visual attention region selection methods that as recently published. Additionally, increased efforts have been directed to the development of a generic method for categorizing all objects in a domain including examples such as Winn�s Method, used to recognize object classes at a glance. The Majority of object class recognition algorithms are highly dependent on shape matching results. The purpose of this review is to provide a comparison among the visual attention (bottom-up and top-down), object recognition (e.g., SIFT, SURF and PCA-SIFT) and object class recognition methods, aimed to researchers identifying the most appropriate method for a particular purpose. This survey is suitable for researchers in the pattern recognition field, providing familiarity with the existing algorithms for object classification from image acquisition steps to final output (i.e., image segmentation, object recognition and object classification). At the end of each part, the challenges, critical analysis table are provided and future directions of every method are suggested for developing new ideas end of this paper. Additionally, this approach allows researchers to find the definition of keywords and to obtain brief knowledge concerning how each method works and what obtained results are for various datasets.
