Pictorial recognition of objects employing affine invariance in the frequency domain

This paper describes an efficient approach to pose invariant pictorial object recognition employing spectral signatures of image patches that correspond to object surfaces which are roughly planar. Based on Singular Value Decomposition (SVD), the affine transform is decomposed into slant, tilt, swing, scale, and 2D translation. Unlike previous log-polar representations which were not invariant to slant (i.e., foreshortening only in one direction), our log-log sampling configuration in the frequency domain yields complete affine invariance. The images are preprocessed by a novel model-based segmentation scheme that detects and segments objects that are affine-similar to members of a model set of basic geometric shapes. The segmented objects are then recognized by their signatures using multidimensional indexing in a pictorial dataset represented in the frequency domain. Experimental results with a dataset of 26 models show 100 percent recognition rates in a wide range of 3D pose parameters and imaging degradations: 0-360 degrees swing and tilt, 0-82 degrees of slant (more than 1:7 foreshortening), more than three octaves in scale change, window-limited translation, high noise levels (0 dB), and significantly reduced resolution (1:5).