Human-Centered Content-Based Image Retrieval
| Autor: | van den Broek, Egon, Kok, Thijs, Schouten, Theo E., Vuurpijl, Louis G., Rogowitz, Bernice E., Pappas, Thrasyvoulos N. |
|---|---|
| Rok vydání: | 2008 |
| Předmět: |
laypersons
Information retrieval human color perception Computer science experts Image processing IR-58738 Content-based image retrieval HMI-MR: MULTIMEDIA RETRIEVAL Field (computer science) METIS-252707 EWI-21108 M4ART Benchmarking Multimedia for Art ReTrieval (M4ART) user-system interaction Pattern recognition (psychology) Benchmark (computing) Segmentation Content-Based Image Retrieval Texture Image retrieval color categories |
| Zdroj: | Human Vision and Electronic Imaging XIII Human Vision and Electronic Imaging |
| Popis: | A breakthrough is needed in order to achieve a substantial progress in the field of Content-Based Image Retrieval (CBIR). This breakthrough can be enforced by: 1) optimizing user-system interaction, 2) combining the wealth of techniques from text-based Information Retrieval with CBIR techniques, 3) exploiting human cognitive characteristics, especially human color processing, and 4) conducting benchmarks with users for evaluating new CBIR techniques. In this paper, these guidelines are illustrated by findings from our research conducted the last five years, which have lead to the development of the online Multimedia for Art ReTrieval (M4ART) system: http://www.m4art.org. The M4ART system follows the guidelines on all four issues and is assessed on benchmarks using 5730 queries on a database of 30,000 images. Therefore, M4ART can be considered as a first step into a new era of CBIR. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|