H. Glotin and S. Tollari and P. Giraudet, Shape reasoning on mis-segmented and mis-labeled objects using approximated Fisher criterion, International Journal Computers and Graphics, Elsevier Ed., Vol 30, N 2, April 2006


To automatically determine semantics of a shape or to generate a set of keywords that describe the content of a given image, are difficult problems due to: (a) the high-dimensional problem, (b) the unsolved automatic object segmentation (mis-segmentation), and (c) the lack of well labeled large image database (mislabeling). In order to tackle (a), despite of (b), (c) and of the expensive handy image segmentation and labeling, visual features should be automatically selected to convey the most robust and discriminant information without requiring too computational cost. Therefore we ose a novel method: "Approximation of Linear Discriminant Analysis" (ALDA), which is more generic than LDA: ALDA doesn't require explicit class labeling of each training samples. We theoretically show that under weak assumption, ALDA allows efficient ranking estimation of the discriminant powers of the visual features. We apply ALDA on COREL database (10K images, 267 words) with Normalized Cuts segmentation algorithm. First we demonstrate an image classification gain of 43%, while reducing features set by a factor 10. Secondly, we demonstrate that for some words (like 'Door', 'Flag'), even low level shape features (convex hull, or moment of inertia), are more discriminant than any color or texture features.

    author = {H. Glotin and S. Tollari and P. Giraudet},
    title = {Shape reasoning on mis-segmented and mis-labeled objects using approximated Fisher criterion},
    journal = {International Journal Computers and Graphics},
    publisher = {Elsevier},     
    volume = {30},
    number = {2},
    year = {2006},