Pseudo Zernike Moment Invariant Research Articles

Super resolution image reconstruction using weighted combined Pseudo-Zernike moment invariants

This paper proposes a multi-image super resolution reconstruction method to estimate a high resolution (HR) image without performing exact image registration, de-blurring and de-noising of available low resolution images. Pixels in the HR image are estimated based on the weighted average of the neighborhood pixels. The weights in the averaging process measure the correlation between pixels and are calculated using a set of feature vectors based on weighted combined Pseudo-Zernike moment invariants (WCPZMIs) of optimum order. WCPZMIs are those reliable Pseudo-Zernike moment invariants (PZMIs) which are simultaneously insensitive to geometric transformations (rotation, scaling, and translation) as well as degradations (blur) and are relatively weighted according to their reconstruction capability. An energy minimization scheme is employed to select the optimal order of WCPZMIs which makes a trade-off between the quality of reconstruction and robustness to noise. An efficient way of weighting the feature vectors and the recursive approach for the computation of PZMIs are utilized to reduce the computational overload of the reconstruction process. Besides, an appropriate square-to-circle mapping followed by a radial geometric moment-to-PZM approximation is adopted to reduce the geometric and the numerical error respectively. Experimental results of the proposed method outperform as compared to similar contributions in literature.

A Near-Field Technique Based on PZMI, GA, and ANN: Application to Power Electronics Systems

In this paper, we propose a new method for modeling the electromagnetic radiation of power electronics systems. This method is based on coupling three powerful techniques: the genetic algorithm (GA) used for the optimization problem, the pseudo-Zernike moment invariant (PZMI) descriptors for pattern recognition, and the neural networks for classification of radiating sources. This modeling approach has been applied to recognize the radiating sources of a dc–dc converter. The model has been validated using measurement results of the magnetic radiation above the converter. The results of the experimental measurements have shown that the characteristics provided by the PZMI descriptors are very robust. So, the proposed method can greatly accelerate the convergence of the inverse method based on GA.

Pseudo-Zernike moment invariants to blur degradation and similarity transformation

The moment invariants have been widely used as feature descriptors against both blur degradation and similarity transformation in pattern recognition. Since Pseudo-Zernike moments outperform other moments in feature matching and object recognition, we propose a new set of Pseudo-Zernike moment invariants holding for blur and similarity transformation simultaneously in this paper to improve the match results. In order to construct the proposed invariants, we also establish the relationship between the Pseudo-Zernike moments of the distorted images and those of the original images with respect to circularly symmetric point spread function. The experimental results are presented to confirm that compared to the other moment invariants, the proposed combined invariants have better invariance and more powerful discriminating ability in terms of pattern recognition accuracy, especially when the images contain noises.

Vision-based force measurement using pseudo-zernike moment invariants

A new vision-based force measurement (VBFM) method is proposed to measure microassembly forces through analyzing pseudo-zernike moment invariants (PZMIs). First, a feature vector of PZMIs is used to describe the deformed cantilever shape in microassembly. This description indicates a function between the applied force and the feature vector of PZMIs. Then, a training set is established to map the relationship between the deformed cantilever under known forces and feature vectors; likewise, a testing set is established to map the relationship between the deformed cantilever under unknown forces and feature vectors. Finally, a support vector machine (SVM) compares feature vectors in the testing set with those ones in the training set, implements multi-class classification and estimates unknown applied forces in the testing set. Experiments on four microcantilevers of different sizes validate the proposed method. Herein, both regional and boundary PZMIs are used to constitute the feature vector. Experimental results show that if the flexural stiffness gets smaller, sensing the change of object deformation gets easier and the force measurement precision gets higher. This trend can provide a reference for mechanism design of microcantilevers and microgrippers.

IMPROVING CONVERGENCE TIME OF THE ELECTROMAGNETIC INVERSE METHOD BASED ON GENETIC ALGORITHM USING THE PZMI AND NEURAL NETWORK

In this paper we present a methodology to guarantee the convergence of the electromagnetic inverse method. This method is applied to electromagnetic compatibility (EMC) in order to overcome the di-culties of measuring the radiated electromagnetic fleld and to reduce the cost of the EMC analysis. It consists in using Genetic Algorithms (GA) to identify a model that will be used to estimate the electric and magnetic fleld radiated by the device under test. This method is based on the recognition of the equivalent radiation sources using the Near Field (NF) cartography radiated by the device. Our contribution in this fleld is to improve the ability and the convergence of the electromagnetic inverse method by using the Pseudo Zernike Moment Invariant (PZMI) descriptor and the Artiflcial Neural Network (ANN). The validation of the proposed method is performed using the NF emitted by known electric and magnetic dipoles. Our results have proved that the proposed method guarantees the convergence of the electromagnetic inverse method and that the convergence speeds up while retaining all the other performances.

Accurate pseudo Zernike moment invariants for grey-level images

Pseudo Zernike moments are orthogonal moments used to represent digital images with minimum amount of information redundancy. Pseudo Zernike moment invariants are image features that are invariant to translation, scaling and rotation which play an essential role in discriminating and classifying similar images where the performance and robustness of the classifiers are highly dependent on the accuracy of these futures. In this work, a new method is presented for accurate computation of two-dimensional pseudo Zernike moment invariants. Approximation errors are removed by using exact geometric and radial geometric moments. Invariance to translation and scaling are computed, while the rotation invariance is directly achieved as direct property of pseudo Zernike moments. Numerical experiments are conducted on a set of standard images. The obtained results demonstrate the efficiency of the proposed method.

GA-based optimal selection of PZMI features for face recognition

One of the key problems in automated face recognition system is that of handling the face image variation in terms of scale, rotation (in plane) and translation. One approach is fixing mentioned problems in recognition processes by extracting one linear transformation invariant feature. This paper presents a novel method for face recognition. Pseudo Zernike moment invariant (PZMI) which has linear transformation invariance properties and is robust in the presence of noise utilized to produce feature vectors. For decreasing computational complexity of feature extraction step, we use genetic algorithm (GA) to select the optimal feature set which contains optimal PZMI orders and corresponding repetitions. In addition, we have investigated the effect of PZMI orders on recognition rate in noisy images. Proposed scheme has been tested on the FERET database. Experimental results prove the advantages of the proposed method when compared with other PZMI-based face recognition systems.

An Efficient Feature Extraction Method with Pseudo-Zernike Moment in RBF Neural Network-Based Human Face Recognition System

This paper introduces a novel method for the recognition of human faces in digital images using a new feature extraction method that combines the global and local information in frontal view of facial images. Radial basis function (RBF) neural network with a hybrid learning algorithm (HLA) has been used as a classifier. The proposed feature extraction method includes human face localization derived from the shape information. An efficient distance measure as facial candidate threshold (FCT) is defined to distinguish between face and nonface images. Pseudo-Zernike moment invariant (PZMI) with an efficient method for selecting moment order has been used. A newly defined parameter named axis correction ratio (ACR) of images for disregarding irrelevant information of face images is introduced. In this paper, the effect of these parameters in disregarding irrelevant information in recognition rate improvement is studied. Also we evaluate the effect of orders of PZMI in recognition rate of the proposed technique as well as RBF neural network learning speed. Simulation results on the face database of Olivetti Research Laboratory (ORL) indicate that the proposed method for human face recognition yielded a recognition rate of 99.3%.

AN EFFICIENT HUMAN FACE RECOGNITION SYSTEM USING PSEUDO ZERNIKE MOMENT INVARIANT AND RADIAL BASIS FUNCTION NEURAL NETWORK

This paper introduces a novel method for the recognition of human faces in two-dimensional digital images using a new feature extraction method and Radial Basis Function (RBF) neural network with a Hybrid Learning Algorithm (HLA) as classifier. The proposed feature extraction method includes human face localization derived from the shape information using a proposed distance measure as Facial Candidate Threshold (FCT) as well as Pseudo Zernike Moment Invariant (PZMI) with a newly defined parameter named Correct Information Ratio (CIR) of images for disregarding irrelevant information of face images. In this paper, the effect of these parameters in disregarding irrelevant information in recognition rate improvement is studied. Also we evaluate the effect of orders of PZMI in recognition rate of the proposed technique as well as learning speed. Simulation results on the face database of Olivetti Research Laboratory (ORL) indicate that high order PZMI together with the derived face localization technique for extraction of feature data yielded a recognition rate of 99.3%.

Pattern recognition with moment invariants: A comparative study and new results

Moment invariants have been proposed as pattern sensitive features in classification and recognition applications. In this paper, the authors present a comprehensive study of the effectiveness of different moment invariants in pattern recognition applications by considering two sets of data: handwritten numerals and aircrafts. The authors also present a detailed study of Zernike and pseudo Zernike moment invariants including a new procedure for deriving the moment invariants. In addition, the authors introduce a new normalization scheme that reduces the large dynamic range of these invariants as well as implicit redundancies in these invariants. Based on a comprehensive study with both handwritten numerals and aircraft data, the authors show that the new method of deriving Zernike moment invariants along with the new normalization scheme yield the best overall performance even when the data are degraded by additive noise.