Sorting of rice grains using Zernike moments

The paper proposes a neural network technique to classify numerals using Zernike moments that are invariant to rotation only. In order to make them invariant to scale and shift, we introduce modified Zernike moments based on regular moments. Owing to the large number of Zernike moments used, it is computationally more efficient to select a subset of them that can discriminate as well as the original set. The subset is determined using stepwise discriminant analysis. The performance of a subset is examined through its comparison to the original set. The results are shown of using such a scheme to classify scaled, rotated, and shifted binary images and images that have been perturbed with random noise. In addition to the neural network approach, the Fisher's classifier is also used, which is a parametric classifier. A comparative study of their performances shows that the neural network approach produces better classification accuracy than the Fisher's classifier. When a suitable subset of Zernike moments is used, the classifiers perform well, just like the original set. The performance of the classifiers is also examined. The computational time is greatly reduced when a suitable subset of Zernike moments is used.

This work proposes a new approach to find the generating function (GF) of the Zernike polynomials in two dimensional form. Combining the methods of GFs and discrete-time systems, we can develop two dimensional digital systems for systematic generation of entire orders of Zernike polynomials. We establish two different formulas for the GF of the radial Zernike polynomials based on both the degree and the azimuthal order of the radial polynomials. In this paper, we use four terms recurrence relation instead of the ordinary three terms recursion to calculate the radial Zernike polynomials and their GFs using unilateral 2D Z-transform. A spatio-temporal implementation scheme is developed for generation of the radial Zernike polynomials. Since Zernike moments (ZMs) are invariant with respect to rotation, translation and scaling, the experimental schemes show the image classification applications by using the proposed algorithm.

Zernike Moments (ZMs) have been widely used in pattern recognition and image analysis due to their merits of near-zero information redundancy and rotation invariance. However, the discrete sampling error introduced by state-of-the-art algorithms degrades their rotation invariance. In this paper, a novel algorithm for computing the accurate ZMs of binary images is presented. The new algorithm is based on Non-Symmetry Anti-Packing Image Representation (NAIR) and it computes the accurate ZMs of the whole image by summing up the ZMs of all rectangular regions without introducing the discrete sampling error. The experimental results in this paper show that the NAIR-based algorithm for accurate ZMs is faster than the state-of-the-art accurate algorithms.

In this work we present an optical-digital system that uses a liquid crystal display (LCD)for the approximate reconstruction of binary images by using the Zernike moments. We use the fact that, each Zernike polynomial can be mapped as an intensity distribution and therefore can be readily displayed with a LCD in an optical incoherent system. On the other hand, the reconstruction of the input image can be obtained from a discrete sum of the data matrices corresponding to the Zernike images weighted by suitable coefficients. These can be numerically computed by using their orthogonality property. The Zernike images acquired by the optical-digital system generate a basis set for the image reconstruction, which depends on both LCD and CCD sensor spatial resolution. The reconstruction is implemented with only thirty six real-valued Zernike moments.

Ladar range images have attracted considerable attention in automatic target recognition fields. In this paper, Zernike moments (ZMs) are applied to classify the target of the range image from an arbitrary azimuth angle. However, ZMs suffer from high computational costs. To improve the performance of target recognition based on small samples, even-order ZMs with serial-parallel backpropagation neural networks (BPNNs) are applied to recognize the target of the range image. It is found that the rotation invariance and classified performance of the even-order ZMs are both better than for odd-order moments and for moments compressed by principal component analysis. The experimental results demonstrate that combining the even-order ZMs with serial-parallel BPNNs can significantly improve the recognition rate for small samples.

We consider the use of Zernike moments (ZMs) for rotation- and scale-invariant classification of images. It is well known that ZMs are rotation-invariant only. We make use of the major benefit of the Fourier-Mellin (FM) transformation, which changes the rotation and the scale into translation. We introduce a new algorithm, which fuses the ZMs with the FM transform and is invariant under both rotation and scaling. Two sets of images were used to test the proposed algorithm. Experimental results reveal that the proposed algorithm has much better recognition rate than using ZMs within a variation of rotation between 0 and 360 deg, and scaling down and up between 25% and 400% of the original size.

Aims/ objectives: To demontrate effectiveness of Zernike Moments for Image Classification. Zernike moment(ZM) is an excellent region-based moment which has attracted the attentions of many image processing researchers since its first application to image analysis. Many papers have been published on several works done on ZM but no single paper ever give a detailed information of how the computation of ZM is done from the time the image is captured to the computation of ZM. This work showed how to effectively apply ZM on RGB images. We have demonstrated the effectiveness of Zernike moment in image classification system. A neuro-genetic intelligent system has been built with PNN classifier. The feature extracted viz ZM and Geometric features were further subjected to GA to bring the best combinatorial features for optimal accuracy. The algebraic structure of our novel fitness function enabled the GA to select the best results. The 10-fold CV used enabled the whole system to be unbiased giving a classification accuracy of 90.05%. A demonstration of affine properties of ZM are comprehensively stated and explained. In summary, the ZM enabled the classifier to have improved accuracy of 91% as compared with Geometric features with 89% accuracy.

Finite precision error analysis of Zernike moments computation schemes and a new, efficient, robust recursive algorithm

This paper describes a neural network (NN) based system for recognition and pose estimation of an unoccluded three-dimensional (3-D) object from any single two-dimensional (2-D) perspective view. The approach is invariant to translation, orientation, and scale. First, the binary silhouette of the object is obtained and normalized for translation and scale. Then, the object is represented by a set of rotation invariant features derived from the complex orthogonal pseudo-Zernike moments of the image. The recognition scheme combines the decisions of a bank of multilayer perceptron NN classifiers operating in parallel on the same data. These classifiers have different topologies and internal parameters, but are trained on the same set of exemplar perspective views of the objects. Next, two pose parameters, elevation and aspect angles, are obtained by a novel two-stage NN system consisting of a quadrant classifier followed by NN angle estimators. Performance is tested on clean and noisy data bases of military ground vehicles. Comparative studies with three other classifiers (a single NN, the weighted nearest-neighbor classifier, and a binary decision tree) are carried out.

We present a way to construct a complete set of scaling rotation and translation invariants extract directly from Zernike moments. Zernike moment can be constructed by Radial moment. In our method in order to construct invariant Zernike moment is to achieve invariant Radial moment which is component of Zernike moment. We use matrix form to denote relationship between Radial and Zernike moment, which makes derivation more comprehensible. The translation invariant Radial moment is first introduced, for it is most complicated part of all the three invariant. Rotation and scaling invariant Radial moment is achieved by normalizing the factor caused by rotation and scaling. The form of invariant radial moment is to combine three parts of invariant. Some experiment has done to test the performance of invariance. In this experiment we take an image library containing 23,329 files which are built by translation rotation and zoom in out of one origin Latin character image. Most of the value of standard deviation ratio by mean of proposed moments is nearly 1%. In addition, retrieval experiment is to test the discrimination ability. MPEG-7 CE shape1 - Part A library is taken in this experiment. The recall rate in part A1 is 96.6% and is 100% in part A2.

Explicit invariance of Cartesian Zernike moments

Given the demand for developing the efficient Machine Learning (ML) classification models for healthcare data, and the potentiality of Bio-Inspired Optimization (BIO) algorithms to tackle the problem of high dimensional data, we investigate the range of ML classification models trained with the optimal subset of features of PD data set for efficient PD classification. We used two BIO algorithms, Genetic Algorithm (GA) and Binary Particle Swarm Optimization (BPSO), to determine the optimal subset of features of PD data set. The data set chosen for investigation comprises 756 observations (rows or records) taken over 755 attributes (columns or dimensions or features) from 252 PD patients. We employed MaxAbsolute feature scaling method to normalize the data and one hold cross-validation method to avoid biased results. Accordingly, the data is split in to training and testing set in the ratio of 70% and 30%. Subsequently, we employed GA and BPSO algorithms separately on 11 ML classifiers (Logistic Regression (LR), linear Support Vector Machine (lSVM), radial basis function Support Vector Machine (rSVM), Gaussian Naïve Bayes (GNB), Gaussian Process Classifier (GPC), k-Nearest Neighbor (kNN), Decision Tree (DT), Random Forest (RF), Multilayer Perceptron (MLP), Ada Boost (AB) and Quadratic Discriminant Analysis (QDA)), to determine the optimal subset of features (reduction of dimensionality) contributing to the highest classification accuracy. Among all the bio-inspired ML classifiers employed: GA-inspired MLP produced the maximum dimensionality reduction of 52.32% by selecting only 359 features and delivering 85.1% of the classification accuracy; GA-inspired AB delivered the maximum classification accuracy of 90.7% producing the dimensionality reduction of 41.43% by selecting only 441 features; And, BPSO-inspired GNB produced the maximum dimensionality reduction of 47.14% by selecting 396 features and delivering the classification accuracy of 79.3%; BPSOMLP delivered the maximum classification accuracy of 89% and produced 46.48% of the dimensionality reduction by selecting only 403 features.

A novel two stage template matching method for rotation and illumination invariance

Cancer classification using a novel gene selection approach by means of shuffling based on data clustering with optimization

Gender classification based on facial features plays a central role in numerous intelligent applications such as surveillance cameras, interactive advertising, and human-computer interaction. This study aimed to compare two deep models, YOLOv9 and ResNet50, on face detection and gender classification, focusing on accuracy and inference speed. YOLOv9 performed well in terms of speed, with an inference time of 332 ms per image and a processing speed of 3 fps, and had a precision of 86.8%, 86.1% of recall, and 86.54% of F1-score. These performance characteristics make YOLOv9 suitable for real-time applications with high-speed response demands, even with moderately low classification accuracy. Conversely, ResNet50 was applied directly to gender classification after data preparation on images and had high classification accuracy, with a precision of 93.6%, 92% of recall, and 92.79% of F1-score. Its inference time was slower at 446.33 ms per image, with a 2.24 fps processing speed and a long training time of 9 hours and 18 minutes. These results show that YOLOv9 has high performance within a time scope of face detection, with reference to detecting enough faces within short timeframes with a limited number of computational resources, whereas ResNet50 has better classification accuracy. Depending on particular use case scenario demands, one corresponding model with a preferred feature can be selected: YOLOv9, if high-speed response is a concern during real-time applications, and ResNet50, if high classification accuracy is a concern.