Rotation-invariant Pattern Recognition System Research Articles

Position and rotation-invariant pattern recognition system by binary rings masks

In this paper, algorithms invariant to position, rotation, noise and non-homogeneous illumination are presented. Here, several manners are studied to generate binary rings mask filters and the corresponding signatures associated to each image. Also, in this work it is shown that digital systems, which are based on the -law non-linear correlation, are -invariant for . The methodologies are tested using greyscale fossil diatoms digital images (real images), and considering the great similarity between those images the results obtained are excellent. The box plot statistical analysis and the computational cost times yield that the Bessel rings masks are the best option when the images contain a homogeneous illumination and the Fourier masks digital system is the right selection when the non-homogeneous illumination and noise is presented in the images.

ニューラルネットワークによる図形の回転正規化

This paper discusses a neural network for a rotation invariant pattern recognition system. The proposed network can normalize a rotated random pattern into the unrotated standard pattern. The normalization is achieved by cascading a preceding rotation-angle extracting network and the succeedingnormalizing network. This basic structure is the same as the previously reported shifted-pattern normalizing network. The network is trained to normalize input random pattern direction into its center of gravity downwardsor in some other predetermined direction. The weight distribution viewed from the input layer in each hidden unit reveals a Fourier transform like in the radius and angle directions.

Discrimination-sensitive rotation-invariant joint-transform correlator using gradient preprocessing and circular harmonic components

The advantage of discrimination sensitivity of a preprocessed binarized joint-transform correlator (PBJTC) has been combined with the rotational tolerance of circular harmonic component (CHC) analysis to realize a JTC which gives a discrimination-sensitive, rotation-invariant pattern recognition system. Both computer simulation and experimental results are provided. The use of gradient preprocessing and adaptive binarization helps in suppressing the sidelobes otherwise associated with a conventional CHC-based JTC. The simulation study shows that such a composite JTC gives a sharp correlation peak for the rotated target and discriminates nontarget, producing a very low cross- correlation peak that stays below the detection threshold. Although it involves two additional improvisation steps (gradient preprocessing and computation of the CHCs), they can be performed prior to the correlation operation, and the simple binarization process can be realized faster optically along with a dedicated digital comparator. © 1998 Society of Photo- Optical Instrumentation Engineers. (S0091-3286(98)01301-4)

The design of rotation-invariant pattern recognition using the silicon retina

A new rotation-invariant pattern recognition system is proposed and analyzed. In this system, silicon retina cells capable of image sensing and edge extraction are used so that the system can directly process images from the real world without an extra edge detector. The rotation-invariant discrete correlation function is modified and implemented in the silicon retina structure by using the current summation. Simulation results have verified the correct function of the proposed system. Moreover, an experimental chip to implement the proposed system with a 32/spl times/32 cell array has been designed and fabricated in 0.8-/spl mu/m n-well CMOS process. Experimental results have successfully shown that the system works well for the arbitrary orientation pattern recognition.

Scale and rotation invariant pattern recognition using complex-log mapping and augmented second order neural network

A scale and rotation invariant pattern recognition system using complex-log mapping (CLM) and an augmented second order neural network (SONN) is proposed. CLM is very useful for extracting the scale and rotation invariant features. The results are, however, given in a wrap-around translated form. This problem is solved with an augmented SONN. Experimental results show that the proposed system has improved recognition performance.

Complex reference-invariant joint-transform correlator

The joint-transform correlator operation has been extended to include complex reference images. Such amplitude and phase images are common when single harmonic images (circular, radial, logarithmic, etc.) are used in correlation setups. The analysis of a rotation-invariant pattern-recognition system using joint-transform correlator principles is described, followed by experimental results that can be obtained in real time.