ImageScape

  

Figure 13: ImageScape query built with icons.

Developer

Department of Computer Science, Leiden University, The Netherlands.

URL

http://www.wi.leidenuniv.nl/home/lim/image.scape.html. A demo of the system is available at http://ind134a.wi.leidenuniv.nl:2001/new2/imagesearch.demo.html.

References

[LLH97], [BL99].

Querying

Using the sketch interface, the user can draw an outline of the desired image. For semantic querying, the user brings icons on a canvas that represent the objects/concepts he is looking for, at the desired position in the image. Examples of object/concept categories include human faces, stone or sand, water, sky, tree or grass, points and lines (see figure 13).

Features

Edge maps of the images collected by Web crawlers are obtained using the Sobel operator and a Gaussian blurring filter. A frequency histogram of the $3\times3$ binary pixel patterns occurring in the edge image, which is called trigram vector, is computed for all images. This vector is subjected to a dimensionality reduction using a band-pass filter (see LCPDLCPD below). Various other features, used in object matching, are taken at pixel level: color, Laplacian, gradient magnitude, local binary patterns, invariant moments and Fourier descriptors.

Matching

The first step of the object matching process uses the L₁ distance on the trigram vectors to retrieve the top $1\%$ matches from the entire database. Among these, 20 matches are selected in a second step, a $20\times20$ template matching, using the most informative pixels to minimize the misdetection rate. These pixels are found as follows. For each object, a large set of positive and negative examples are used in finding the set of 256 pixels with the greatest discriminatory power, by maximazing the Kullback relative information combined with a Markov random field.