The visible differences predictor: an algorithm for the assessment of image fidelity
Digital images and human vision
What's wrong with mean-squared error?
Digital images and human vision
Fast multiresolution image querying
SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Photobook: content-based manipulation of image databases
International Journal of Computer Vision
Principles of Digital Image Synthesis
Principles of Digital Image Synthesis
Summed-area tables for texture mapping
SIGGRAPH '84 Proceedings of the 11th annual conference on Computer graphics and interactive techniques
Large Image Collections --- Comprehension and Familiarization by Interactive Visual Analysis
SG '09 Proceedings of the 10th International Symposium on Smart Graphics
Hi-index | 0.00 |
The explosion of storage media size and bandwidth has led to huge image databases. Methods are needed to find a particular image based on a crude description by the user. Keywording is not only tedious, but also subjective and therefore often incorrect. Available visual query systems have different properties, and are mostly based on some image transformation. An alternative visual query system is introduced, which finds an image similar to a user drawn sketch, or to any other reference image. A descriptor is created for each image in the database, and for the query image. Descriptors are compared in order to find the best matches. Descriptors are computed by inserting a limited number of quasi-random rectangles in the image, and computing the average colors of the rectangles. Furthermore, a reduced color histogram is computed and stored in the descriptor. The difference between descriptors is calculated as the weighted average of CIE LUV differences between corresponding rectangles. Using the Contrast Sensitivity Function this average is adapted to the users perception. The metric used for comparing images operates in the original image space, which makes the whole algorithm intuitive and easy to understand, and enables the comparison of images sections, as well.