Object Recognition as Classification via Visual Properties
This work addresses conceptual modeling in AI and computer vision, offering a novel theoretical framework, but it appears incremental as it builds on existing teleosemantic and faceted organization ideas without presenting empirical results.
The paper tackles the problem of object recognition by proposing a teleosemantic approach that distinguishes between substance concepts for recognition and classification concepts for categorization, demonstrating that object recognition can be viewed as classification via visual properties. It presents a process based on Ranganathan's faceted knowledge organization and mentions the MultiMedia UKC project for building a resource.
We base our work on the teleosemantic modelling of concepts as abilities implementing the distinct functions of recognition and classification. Accordingly, we model two types of concepts - substance concepts suited for object recognition exploiting visual properties, and classification concepts suited for classification of substance concepts exploiting linguistically grounded properties. The goal in this paper is to demonstrate that object recognition can be construed as classification via visual properties, as distinct from work in mainstream computer vision. Towards that, we present an object recognition process based on Ranganathan's four-phased faceted knowledge organization process, grounded in the teleosemantic distinctions of substance concept and classification concept. We also briefly introduce the ongoing project MultiMedia UKC, whose aim is to build an object recognition resource following our proposed process