Journal ArticleDOI
Modified rapid transform.
Ming Fang,Gerd Häusler +1 more
Reads0
Chats0
TLDR
The modified rapid transform (MRT) combines the well-known rapid transform with preprocessing steps and can be usefully applied as a preprocessing step in automatic inspection and pattern recognition, where shift invariance, uniqueness, and low computing time is required.Abstract:
We describe a new fast, shift-invariant transform, the modified rapid transform (MRT). The MRT combines the well-known rapid transform with preprocessing steps. Computer simulations show that for 1-D binary patterns the MRT with a sufficient number of preprocessing steps may perform shift-invariant one-to-one mapping. The modification is also efficient for 2-D patterns. The MRT can be usefully applied as a preprocessing step in automatic inspection and pattern recognition, where shift invariance, uniqueness, and low computing time is required. As an example, the use of MRT in optical character recognition is discussed.read more
Citations
More filters
Journal ArticleDOI
Algorithms for hardware-based pattern recognition
TL;DR: A hardware-accelerated image processing and classification system which is implemented on one field-programmable gate array (FPGA) and the pattern separability properties of these transforms are better than those achieved with the well-known method based on the power spectrum of the Fourier Transform.
Journal ArticleDOI
Contextual invariant-integration features for improved speaker-independent speech recognition
Florian Müller,Alfred Mertins +1 more
TL;DR: It is shown that the invariant-integration features (IIFs) can be successfully combined with additional speaker-adaptation methods to further increase the accuracy of the presented feature type.
Proceedings ArticleDOI
On the existence of complete invariant feature spaces in pattern recognition
TL;DR: This paper presents a general and model-independent analysis of the problem of feature extraction in pattern recognition and two criteria are derived which ensure the existence of a complete feature space.
Invariants for the Recognition of Planar Contour and Gray-Scale Images
TL;DR: In this paper, the authors give some results for the construction, the existence and the properties of invariants for the recognition of planar contour and gray-scale images, and different performance measures of the invariant features like completeness, robustness as well as the matter of computational complexity are discussed.
Dissertation
Computational Redundancy in Image Processing
TL;DR: It is demonstrated (mathematically and empirically) that the amount of coding and interpixel redundancy of an image has a positive effect on the speedup obtained for the image by window memoization in both software and hardware.
References
More filters
Journal ArticleDOI
Speckle masking in astronomy: triple correlation theory and applications
TL;DR: The theory of speckle masking is presented; it makes use of triple correlations and their Fourier counterparts, the bispectra, and shows algorithms for the recovery of the object from genuine astronomical Bispectra data.
Journal ArticleDOI
Optical character recognition by the method of moments
TL;DR: The selection of a set of moments that provide good discrimination between characters, the comparison of three classification schemes, the choice of a weighting vector that improves the classification performance, and a series of experiments to determine how the recognition rate is affected by the number of library feature vector sets are presented.
Journal ArticleDOI
A transformation with invariance under cyclic permutation for applications in pattern recognition
Herbert J. Reitboeck,T. P. Brody +1 more
TL;DR: A transformation that can be used to characterize patterns independent of their position is described, which is 10–100 times faster than the fast Fourier transform (depending on the number of sampling points).
Journal ArticleDOI
A class of translation invariant transforms
Meghanad D. Wagh,S. Kanetkar +1 more
TL;DR: A class of translation invariant transforms containing the R-transform is defined, and it is shown that a particular member of this class is superior to theR-transform for pattern recognition applications.
Journal ArticleDOI
A fast shape descriptor
Jun Ma,Cheng-Ke Wu,Xin-Ru Lu +2 more
TL;DR: The normalized rapid descriptors developed here and normalized Fourier descriptors (NFD) are applied to the analyses of some typical 2D images and it is shown that they both have good recognition performance.
Related Papers (5)
A transformation with invariance under cyclic permutation for applications in pattern recognition
Herbert J. Reitboeck,T. P. Brody +1 more