Abstract
It has been argued that concepts can be perceived at three main levels of abstraction. Generally, in a recognition system, object categories can be viewed at three levels of taxonomic hierarchy which are known as superordinate, basic, and subordinate levels. For instance, “horse” is a member of subordinate level which belongs to basic level of “animal” and superordinate level of “natural objects.” Our purpose in this study is to take an investigation into visual features at each taxonomic level. We first present a recognition tree which is more general in terms of inclusiveness with respect to visual representation of objects. Then we focus on visual feature definition, that is, how objects from the same conceptual category can be visually represented at each taxonomic level. For the first level we define global features based on frequency patterns to illustrate visual distinctions among artificial and natural. In contrast, our approach for the second level is based on shape descriptors which are defined by recruiting moment based representation. Finally, we show how conceptual knowledge can be utilized for visual feature definition in order to enhance recognition of subordinate categories.
Highlights
Categorization is the first step in recognition and so it is fundamental for perception, communication, and any kind of interaction with the environment [1]
We investigated visual representation of concepts at three levels of inclusiveness
For basic category representation in the second level, we proposed to utilize moment descriptors in order to capture the differences in shape rather than local patches of images
Summary
Categorization is the first step in recognition and so it is fundamental for perception, communication, and any kind of interaction with the environment [1]. According to research in conceptual developments, there exist different strategies for object categorization. Three different types of categorization are identified by cognitive science researchers based on whether the similarities are defined by their external relations or internal properties. These are known as thematic categorization, script categorization, and taxonomic categorization. In script categorization objects with similar roles or functionality are grouped together. While the members of the first two types of categorization do not necessarily share similar properties, in the taxonomic categorization, objects are grouped based on similar observable features. Thereupon, taxonomic organization is applicable to visual object categorization in which object appearance plays a determinant role in object recognition and classification
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
