Database Reference
In-Depth Information
metric known as the earth mover's distance [6] which is a flow-based measure and
effectively describes the work that is required to transform the colour signature
of one image into that of another.
Simple colour features such as colour histograms are fast to compute, and are
invariant to rotation and translation as well as robust to scaling and occlusions.
On the other hand, they do not carry any information about the spatial distri-
bution of the colours. Colour coherence vectors [7] were introduced as a method
of introducing spatial information into the retrieval process. Colour coherence
vectors consist of two histograms: one histogram of coherent and one of non-
coherent pixels. The
L
1
norm is used as the distance metric between two colour
coherence vectors.
3 Conclusions
Content-based image retrieval has been a very active research area for the past
two decades, and colour features have been shown to be very useful in this
context. In this paper, we have given a brief summary of some colour features
that are commonly employed for CBIR. While space limitations don't allow us
to go into detail here, it should be noted that for eciency many descriptors
(or near equivalents) can also be derived in the compressed domain [8], while
colour features are also very useful for image browsing systems which provide
an interactive alternative to retrieval-based approaches [9].
References
1. Osman, T., Thakker, D., Schaefer, G., Lakin, P.: An integrative semantic framework
for image annotation and retrieval. In: IEEE/WIC/ACM International Conference
on Web Intelligence, pp. 366-373 (2007)
2. Rodden, K.: Evaluating Similarity-Based Visualisations as Interfaces for Image
Browsing. PhD thesis, University of Cambridge Computer Laboratory (2001)
3. Smeulders, A., Worring, M., Santini, S., Gupta, A., Jain, R.: Content-based image
retrieval at the end of the early years. IEEE Trans. Pattern Analysis and Machine
Intelligence 22, 1249-1380 (2000)
4. Stricker, M., Orengo, M.: Similarity of color images. In: Conf. on Storage and Re-
trieval for Image and Video Databases III. Proceedings of SPIE, vol. 2420, pp.
381-392 (1995)
5. Swain, M., Ballard, D.: Color indexing. Int. Journal of Computer Vision 7, 11-32
(1991)
6. Rubner, Y., Tomasi, C., Guibas, L.: The earth mover's distance as a metric for
image retrieval. Int. Journal of Computer Vision 40, 99-121 (2000)
7. Pass, G., Zabih, R.: Histogram refinement for content-based image retrieval. In: 3rd
IEEE Workshop on Applications of Computer Vision, pp. 96-102 (1996)
8. Schaefer, G.: Content-based retrieval of compressed images. In: International Work-
shop on DAtabases, TExts, Specifications and Objects, pp. 175-185 (2010)
9. Plant, W., Schaefer, G.: Visualisation and browsing of image databases. In: Lin,
W., Tao, D., Kacprzyk, J., Li, Z., Izquierdo, E., Wang, H. (eds.) Multimedia Anal-
ysis, Processing and Communications. SCI, vol. 346, pp. 3-57. Springer, Heidelberg
(2011)
