论文信息 - Quality Measures for Interactive Image Retrieval with a Performance Evaluation of Two 3x3 Texel-based Methods

Quality Measures for Interactive Image Retrieval with a Performance Evaluation of Two 3x3 Texel-based Methods

The aim of the Leiden Imaging and Multi-media Group in collaboration with Philips is to develop and evaluate content-based indexing and interactive retrieval methods for large photo collections and to integrate them with annotation based methods. Ground-truth is provided by copy pairs in the Leiden Portrait Database, a database of scanned-in images of 19th-century Dutch studio portraits (“Cartes de Visite” ).

Michael S. Lew | Dee Denteneer | Dionysius P. Huijsmans

[1] Michael S. Lew,et al. 2D Pixel Trigrams for Content-Based Image Retrieval , 1998, Image Databases and Multi-Media Search.

[2] M. Lew. Content Based Image Retrieval : KLT , Projections , or Templates , 1996 .

[3] JEFFREY WOOD,et al. Invariant pattern recognition: A review , 1996, Pattern Recognit..

[4] Arnold W. M. Smeulders,et al. Image Databases and Multi-Media Search , 1998, Image Databases and Multi-Media Search.

[5] Li WangDong-Chen He,et al. Texture classification using texture spectrum , 1990, Pattern Recognit..

[6] Michael S. Lew,et al. Efficient content-based image retrieval in digital picture collections using projections: (near)-copy location , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[7] Matti Pietikäinen,et al. A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..