Heuristic Role Detection of Visual Elements of Web Pages

摘要

Web pages are typically designed for visual interaction - they include many visual elements to guide the reader. However, when they are accessed in alternative forms such as in audio, these elements are not available and therefore they become inaccessible. This paper presents our ontology-based heuristic approach that automatically identifies visual elements of web pages and their roles. Our architecture has three major components: 1. automatic identification of visual elements of web pages, 2. automatic generation of heuristics as Jess rules from an ontology and 3. application of these heuristic rules to web pages for automatic annotation of visual elements and their roles. This paper first explains our architecture in detail and then presents our both technical and user evaluations of the proposed approach and architecture. Our technical evaluation shows that complexity is an important performance factor in role detection and our user evaluation shows that our proposed system has around 80% receptive accuracy, but the proposed knowledge base could be further improved for better accuracy.