Identifying a critical threat to privacy through automatic image classification

Deep Convolution Neural Network is one of the most powerful tools to solve complex problems of image classification, image recognition, financial analysis, medical diagnosis and many similar problems. A dental panoramic image consists of collection of teeth of both upper jaw and lower jaw. Automatic classification of dental panoramic images into various tooth types such as canines, incisors, premolars and molars has been a challenging task and involves crucial role of an experienced dentist. In this paper, we propose a technique for numbering and classification of the panoramic dental images. The proposed algorithm consists of four stages namely pre-processing, segmentation, numbering and classification. The pre-processed panoramic dental images are segmented using fuzzy c-mean clustering and subjected to vertical integral projection to extract a single tooth. The image dataset consists of 400 dental panoramic images collected from various dental clinics. The 400 dental images are divided into 240 training samples and 160 testing samples. The image data set is augmented by applying various transformations. Panoramic dental images are further numbered using a universal dental numbering system. Finally, the classification is done with the help of 6-layer deep convolution neural network (DCNN) consisting of 3 convolutional neural network and 3 fully connected network. The tooth is classified as canine, incisor, molar and premolar. An accuracy of 95% has been achieved for augmented database and 92% for original dataset with the proposed algorithm. The proposed numbering and classification of dental panoramic images is useful in biomedical application and postmortem recording of dental records. In case of big calamity, the system can also assist the dentist in recording post mortem dental record that is a very lengthy and arduous task.

CYBERNEWS

Neural ordinary differential equations (neural ODEs) have emerged as a novel network architecture that bridges dynamical systems and deep learning. However, the gradient obtained with the continuous adjoint method in the vanilla neural ODE is not reverse-accurate. Other approaches suffer either from an excessive memory requirement due to deep computational graphs or from limited choices for the time integration scheme, hampering their application to large-scale complex dynamical systems. To achieve accurate gradients without compromising memory efficiency and flexibility, we present a new neural ODE framework, PNODE, based on high-level discrete adjoint algorithmic differentiation. By leveraging discrete adjoint time integrators and advanced checkpointing strategies tailored for these integrators, PNODE can provide a balance between memory and computational costs, while computing the gradients consistently and accurately. We provide an open-source implementation based on PyTorch and PETSc, one of the most commonly used portable, scalable scientific computing libraries. We demonstrate the performance through extensive numerical experiments on image classification and continuous normalizing flow problems. We show that PNODE achieves the highest memory efficiency when compared with other reverse-accurate methods. On the image classification problems, PNODE is up to two times faster than the vanilla neural ODE and up to 2.3 times faster than the best existing reverse-accurate method. We also show that PNODE enables the use of the implicit time integration methods that are needed for stiff dynamical systems.

The article focuses on studying the effectiveness of two different Hybrid Neural Networks (HNNs) architectures for solving real-world image classification problems. The first approach investigated in the research is a hybridization technique that allows creation of HNN based on a classical neural network by replacing a number of hidden layers of the neural network with a variational quantum circuit, which allows to reduce the complexity of the classical part of the neural network and move part of computations to a quantum device. The second approach is a hybridization technique based on utilizing quanvolutional operations for image processing as the first quantum convolutional layer of the hybrid neural network, thus building a Quanvolutional Neural Network (QNN). QNN leverages quantum phenomena to facilitate feature extraction, enabling the model to achieve higher accuracy metrics than its classical counterpart. The effectiveness of both architectures was tested on several image classification problems. The first one is a classical image classification problem of CIFAR10 images classification, widely used as a benchmark for various imagery-related tasks. Another problem used for the effectiveness study is the problem of geospatial data analysis. The second problem represents a real-world use case where quantum computing utilization can be very fruitful in the future. For studying the effectiveness, several models were assembled: HNN with a quantum device that replaces one of the hidden layers of the neural network, QNN based on quanvolutional operation and utilizes VGG-16 architecture as a classical part of the model, and also an unmodified VGG-16 was used as a reference model. Experiments were conducted to measure the models' key efficiency metrics: maximal accuracy, complexity of a quantum part of the model and complexity of a classical part of the model. The results of the research indicated the feasibility of both approaches for solving both proposed image classification problems. Results were analyzed to outline the advantages and disadvantages of every approach in terms of selected key metrics. Experiments showed that QNN architectures proved to be a feasible and effective solution for critical practical tasks requiring higher levels of model prediction accuracy and, simultaneously, can tolerate higher processing time and significantly increased costs due to a high number of quantum operations required. Also, the results of the experiments indicated that HNN architectures proved to be a feasible solution for time-critical practical tasks that require higher processing speed and can tolerate slightly decreased accuracy of model predictions.

Objectives: The paper presents application of convolution neural network and artificial neural network for image classification problem for clothing dataset along with their performance comparison against different optimizers. The major objective of this paper is to perform image classification on fashion-mnist clothing dataset images. Methods: The methods used here are, the traditional ANN and CNN. Here image classification is performed on Fashion-mnist, clothing dataset using CNN and ANN with different optimizers. The performance of the working of ANN and CNN in classifying images from fashion-mnist dataset is compared against different optimizers namely stochastic gradient Descent, Adagrad, RMS prop and Adam optimizer. Findings: The study found that CNN worked better than ANN yielding training accuracy of 95%, 93% and testing accuracy of 91%, 89% when used with Adam and RmsProp respectively. Novelty: The novelty of this work is to present a comparative study of image classification using CNN, ANN using different optimizers, since not many studies or research articles showed the performance comparison of traditional and convolution neural networks in image classification along with different optimizers. Since the real-world scenarios of today require enormous data to be processed, CNN can fit well to diversify applications since they highly reduce the number of parameters to be trained that speeds up the training process. Moreover, to be specific on image classification problems they require the best and most prominent features to be detected and uncovered; this can be achieved using CNN since it has the concept of convolution using filters at its Core. Hence, CNN is highly recommended for such image classification applications than the traditional artificial-neural-networks because of the aforementioned reasons. Keywords: ANN (Artificial NeuralNetworks); CNN (ConvolutionNeural Networks); Optimization; SGD (Stochastic Gradient Descent); RmsProp (Root mean Square propagation); Adam (Adaptive moment estimation); AdaGrad (Adaptive Gradient)

In recent times, enormous chunks of data is being extracted from the astronomical telescopes throughout the world for better and more precise information on the astronomical object so as to classify the object. As advances in data science have been rapid, the field of data mining in astronomy (Borne in Scientific data mining in astronomy. George Mason University Fairfax, USA, 2009 [1]) has also been on an upward slope. Papers on data mining in astronomy and classification of astronomical objects (Mahabal et al. in towards real-time classification of astronomical transients, 2008 [2]; D’Isanto et al. in An analysis of feature relevance in classification of astronomical transients with machine learning methods, 2016 [3]) have paved a way for smarter manipulation of available data to extract better results. In the previous years, Artificial Neural Networks and Support Vector Machines (SVM) have been used on astronomical data to handle classification problems in the available data whereas in some cases imaging technology and lightcurves (Faraway et al. in Modern light curves for improved classification, 2014 [4]) have been used for the given problem. Image Processing has also been used for the morphological classification of galaxy images (Shamir in Automatic morphological classification of galaxy images, 2009 [5]). Our motivation is to find the which machine learning algorithm uses the least computation time and gives the best accuracy metric for classification of astronomical objects into Stars, Galaxies and Quasars based on data provided to us by the Sloan Digital Sky Survey/SkyServer (SDSS). This research gives us the best suited classification algorithm out of all the present and currently used algorithms. We have used Logistic Regression, Support Vector Machines, Random Forests and Decision Tree classifiers and compared the results obtained to come to the conclusion of the most suitable classification algorithm for the given astronomical data.

Automated image classification is an essential task of the computer vision field. The tagging of images into a set of predefined groups is referred to as image classification. The implementation of computer vision to automate image classification would be beneficial because manual image evaluation and identification can be time-consuming, particularly when there are many images of different classes. Deep learning approaches are proven to overperform existing machine learning techniques in many fields in recent years, and computer vision is one of the most notable examples. The very deep neural network (VDCNN) is a powerful deep learning model for image classification, and this paper examines it briefly using MNIST handwritten digit dataset. This dataset is used to prove the efficacy of very deep neural networks over other deep learning models. The proposed study aims to comprehend the very deep neural network architecture used to accomplish a handwritten digit recognition task. The feasibility of the proposed model is evaluated using mean accuracy, validation accuracy, and standard deviation. The study results of the very deep neural network model are compared to a convolutional neural network and convolutional neural network with batch normalization. According to the results of the comparison study, very deep neural networks achieve high accuracy of 99.1% for a handwritten dataset. The outcome of the proposed work is used to interpret how well a very deep neural network performs when compared to the other two models of deep neural networks. This proposed architecture may be used to automate the classification of handwritten digits dataset.

In this paper, we propose an approach in microscopic image classification for histological sections of human tissues. The method is based on image descriptors composed of vectors of accumulated Zernike moments. The goal is to construct a robust and precise method of image recognition and classification that can be applied in the case of histological tissue samples. Thanks to their properties Zernike moments fit these requirements. Additionally, processed Zernike moments can be made scale, translation, and rotation invariant. In a series of experiments, we verify the effectiveness of the method and its application to the presented problem of medical image classification. The results are obtained with the help of predefined classifiers provided by dedicated software. The paper presents a comparison of results and proposes an example method of improving the approach.

Object recognition is a method in the computer vision to identify and recognize objects in the picture or video. When humans see photos or watch videos, they can quickly recognize some object like a car, bus, human, cat, food, and other visual artifacts. However, how do we apply it to the computer? Classification is the technique or method in object recognition that can be used on a computer to distinguish one object from another object contained in the image or video. In this paper, the author proposes about testing some popular image binary classification algorithms used along with the results of the performance matrix of each algorithm, among these are Logistic Regression with Perceptron, Multi-Layer Perceptron (MLP), Deep Multi-Layer Perceptron, and Convolutional Neural Network (ConvNet). The author uses the Food-5K dataset to distinguish two classes of objects, namely food /non-food, and then try to train and test how accurate the computer is in recognizing food and non-food objects, where it will be useful to anyone who needs to identify a food object using auto recognizing tools. This paper is expected to contribute in the field of computer vision related algorithm that is used to solve the problem in image classification, with the state of optimal hyperparameter and validation accuracy level above 90%. From the test results obtained the level of testing accuracy using ConvNet reached above 90% and loss function less than 25% while indicating that ConvNet has a significant advantage on the image classification problem compared to the generic artificial neural network.

Classification task is one of the most common tasks in machine learning. This supervised learning problem consists in assigning each input to one of a finite number of discrete categories. Classification task appears naturally in numerous applications, such as medical image processing, speech recognition, maintenance systems, accident detection, autonomous driving etc.In the last decade methods of deep learning have proven to be extremely efficient in multiple machine learning problems, including classification. Whereas the neural network architecture might depend a lot on data type and restrictions posed by the nature of the problem (for example, real-time applications), the process of its training (i.e. finding model’s parameters) is almost always presented as loss function optimization problem.Cross-entropy is a loss function often used for multiclass classification problems, as it allows to achieve high accuracy results.Here we propose to use a generalized version of this loss based on Renyi divergence and entropy. We remark that in case of binary labels proposed generalization is reduced to cross-entropy, thus we work in the context of soft labels. Specifically, we consider a problem of image classification being solved by application of convolution neural networks with mixup regularizer. The latter expands the training set by taking convex combination of pairs of data samples and corresponding labels. Consequently, labels are no longer binary (corresponding to single class), but have a form of vector of probabilities. In such settings cross-entropy and proposed generalization with Renyi divergence and entropy are distinct, and their comparison makes sense.To measure effectiveness of the proposed loss function we consider image classification problem on benchmark CIFAR-10 dataset. This dataset consists of 60000 images belonging to 10 classes, where images are color and have the size of 32×32. Training set consists of 50000 images, and the test set contains 10000 images.For the convolution neural network, we follow [1] where the same classification task was studied with respect to different loss functions and consider the same neural network architecture in order to obtain comparable results.Experiments demonstrate superiority of the proposed method over cross-entropy for loss function parameter value α < 1. For parameter value α > 1 proposed method shows worse results than cross-entropy loss function. Finally, parameter value α = 1 corresponds to cross-entropy.

Credit card is considered as one of the most popular paying methods for online and regular purchases, due to the advancement in communication and electronic commerce systems. Thus, the fraud associated with these transactions increased significantly. The great utilization of electronic payment is highly affected by this fraudulent transactions, which requires urgent detection to solve this issue. Therefore, effective and efficient approaches to detect fraud in credit card transactions are needed. To catch the fraudulent transaction, a good fitting model is needed, hence researchers recommends the use of various Machine Learning (ML) techniques, because of its beneficial characteristics. The main aim of the research work is to implement an ensemble based ML techniques for Credit Card Fraud Detection (CCFD). The strength of our model is a combination of the forces of the three subsystems; Recursive Feature Elimination (RFE), CCFD's using ensemble classifiers, and Synthetic Minority Oversampling (S MOTE) to deal with the problem of unbalanced data to identify the most effective prediction features. The proposed model run typical tests on two real databases of public credit card transactions, including fraudulent and official ones. Based on the comparison of other ML methods, the extra tree classifier has performed better and achieved high efficiencies such as 96% of accuracy and 57.95% of F1-measure.

Identity theft has become one of the fastest growing white collar crimes in the world. It occurs when an individual's personal information such as inter alia his or her name, date of birth or credit card details is used by another individual to commit identity fraud. Identity theft can be committed via physical means or online. The increased use of the Internet for business and financial transactions, social networking and the storage of personal information has facilitated the work of identity thieves. Identity theft has an impact on the personal finances and emotional well-being of victims, and on the financial institutions and economies of countries. It presents challenges for law enforcement agencies and governments worldwide. This article examines how identity thieves use the personal information of individuals to commit identity fraud and theft, and looks at legislative solutions introduced in South Africa, the United States of America, the United Kingdom and India to combat identity theft crimes. The article examines measures introduced by the respective governments in these countries to counteract such crimes. Finally, the article will propose a way forward to counteract such crimes in the future. The study reveals that identity theft is a growing and evolving problem that requires a multi-faceted and multi-disciplinary approach by law enforcement agencies, businesses, individuals and collaboration between countries. It is advocated that businesses and institutions should take measures to protect personal information better and that individuals should be educated about their rights, and be vigilant and protect their personal information offline and in cyberspace.

A fast computationally efficient method for automatic segmentation and classification of textured images is presented. The method does not necessarily need a-priori information about the textures present in the image, thus avoiding the necessity of a training set of textures. A fast adaptive multichannel technique for autoregressive image model parameter estimation with fast tracking capabilities and a powerful statistical distance measure are appropriately interweaved to form the proposed technique. Specific properties of the estimation part of the algorithm are exploited to reduce greatly the computational complexity of the distance measure. Some interesting extensions of the method are discussed and examples are given which illustrate the performance of the algorithm. >

Cervical cancer represents a major cause of death for women. Automatic classification of cervical images from acetic acid test could serve as a promising screening tool for cervical cancer. Despite an increasing volume of studies on automatic classification of cervical images, reported methods varied markedly in terms of features and classifiers used, and therefore the performance. The classification performance using different configurations of the classifier has not been well characterized. The objective of this study was to evaluate several frequently used features and classifiers in acetic-acid cervical image based cervical intraepithelial neoplasia classification. Seven typically used color or texture-based features and four frequently used classifiers (Support Vector Machine, Random Forest, Back-Propagation Neural Network and K-Nearest Neighbors) were included in the comparison based on a balanced large sample size including 175 CIN negative and 175 CIN positive patients. The results showed that the Support Vector Machine demonstrated the best classification accuracy when a subset of features was used. The finding of this study may provide useful reference values to the development of an automatic cervical cancer screening tool.

In this Paper, we introduce a new method for automatic recognition and classification of prostate cancer biopsy images based on Gleason grading system. The introduced algorithm combines features from wavelet transform and fractal analysis domains. Biopsy images are pre-processed prior to features extraction using effective image processing algorithms to analyze textural complexity in terms of RGB color channels, edge and segmentation information. Experimental results achieved an average classification accuracy of 95 % in a set of 45 images with diversities in resolution, magnification levels, and stain colors.