K.R. Rao

On the recognition of occluded shapes and generic faces using multiple-template expansion matching

An approach for template matching by signal expansion into a set of nonorthogonal template-similar basis functions and its generalization to multiple templates is described. The single-template method is proven to be equivalent to restoration of undergraded images using the Wiener filter and optimizes a practically defined matching criterion called discriminative signal-to-noise ratio (DSNR). Compared to the matched filtering approach which optimizes the SNR, expansion matching is more robust in conditions of noise, superposition, and severe occlusion. The multiple-template expansion filter presented is generalized to match more than one template. It is also optimal in terms of DSNR. It can be designed to elicit any desired response for each of the templates.<<ETX>>

Lattice architectures for signal expansion by Gaussian set wavelets with applications to recognition

Three issues are discussed. The first issue is the feasibility of nonorthogonal basis functions (BFs) for the representation of signals and images in particular. Novel BFs are suggested for signal expansion which are based on Gaussian sets (GSs) and Gaussian set wavelets (GSWs). Even though GSs are nonorthogonal, they are found to be quite efficient in the exploitation of local redundancies of signals. The second issue concerns a novel method of expansion for recognition applying template-similar functions as BFs. The results show significant improvement over traditional recognition methods. The third issue deals with hardware implementation of the above methods using adaptive lattice architectures that exploit the central limit.<<ETX>>

A lattice network for signal representation using Gaussian basis functions and max-energy paradigm

Describes two novel schemes for efficient representation of 1-D and 2-D signals using Gaussian basis functions (BFs). Special methods are required since the Gaussian functions are nonorthogonal. The first method employs a paradigm of maximum energy reduction interlaced with the A* heuristic search. The second method uses an adaptive lattice system to find the optimal projections of the BFs onto the signal, and a lateral-vertical suppression network to select the most efficient representation in terms of data compression.<<ETX>>

Multiple auditory template matching using expansion

In this paper we consider multiple template matching techniques for auditory localization. In our approach, auditory localization is based on extracting localization cues from the ratios of the incoming sound spectra at the two ears. Localization cues can be extracted from such ratios by matching them with stored templates of ratios of head related transfer functions. Here we compare the performance of several matching techniques in their ability to accurately extract localization cues from such ratios. We introduce a new Discriminative Matching Measure (DMM), a similarity measure to be optimized, and formulate a novel linear matching scheme which optimizes this measure. The DMM is similar to our Discriminative Signal-to-Noise Ratio measure. We compare the performance of several linear techniques, namely correlation and normalized correlation and our novel optimal matching method and also a non-linear method based on the backpropagation algorithm.<<ETX>>

Image expansion by non-orthogonal basis functions extended for optimal multiple template matching

The DSNR (discriminative signal-to-noise ratio) optimization approach is extended to include more than one template. The optimal DSNR template matching filter can be designed to elicit any desired response for each training template image while optimizing the DSNR criterion. The approach used considers additive noise as a parameter and leads to a very general formulation, of which many previous approaches are special cases. In the case of a single training image, this formulation reverts to the Wiener restoration filter or the template-similar expansion approach.<<ETX>>

A novel matching technique using image expansion into nonorthogonal wavelets

A novel approach for template matching by signal expansion into a set of nonorthogonal template similar basis functions (wavelets) is presented. It is shown that expansion matching is a special case of the general nonorthogonal expansion and is equivalent to restoration of undergraded images. Matching by expansion is quite robust in conditions of noise, superposition and severe occultation. Expansion matching also maximizes a new and more practically defined discriminative signal-to-noise ratio (DSNR). It is proved that maximizing the DSNR is equivalent to minimum squared error restoration by Wiener filters. Experimental comparisons with correlation matching (matched filtering) show that expansion matching yields much higher DSNR.<<ETX>>