Region based Color Histogram Approximation Technique for Classification of Fruit Images and Fruit Grading

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.

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.

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.

Nowadays, the information processing capabilities and resource storage capabilities of computers have been greatly improved, which also provides support for the neural network technology. Convolutional neural networks have good characterization capabilities in computer vision tasks, such as image recognition technology. Aiming at the problem of high similarity image recognition and classification in a specific field, this paper proposes a high similarity image recognition and classification algorithm fused with convolutional neural networks. First, we extract the image texture features, train different types, and different resolution image sets and determine the optimal texture different parameter values. Second, we decompose the image into subimages according to the texture difference, extract the energy features of each subimage, and perform classification. Then, the input image feature vector is converted into a one-dimensional vector through the alternating 5-layer convolution and 3-layer pooling of convolutional neural networks. On this basis, different sizes of convolution kernels are used to extract different convolutions of the image features, and then use convolution to achieve the feature fusion of different dimensional convolutions. Finally, through the increase in the number of training and the increase in the amount of data, the network parameters are continuously optimized to improve the classification accuracy in the training set and in the test set. The actual accuracy of the weights is verified, and the convolutional neural network model with the highest classification accuracy is obtained. In the experiment, two image data sets of gems and apples are selected as the experimental data to classify and identify gems and determine the origin of apples. The experimental results show that the average identification accuracy of the algorithm is more than 90%.

The application of image processing has been extended to agricultural industries in recent times. As the concept of image processing has vast application in agricultural industries, fruit grading has been focused in this research. There are number of approaches available for the classification and grading of mangoes, they suffer to achieve higher performance in classification. The most approaches uses color features and shape features only. To improve the performance of classification and fruit grading, an efficient GANFIS (Genetic Adaptive Neuro Fuzzy Inference System) is presented in this paper. The GANFIS approach reads the 2D mango images and extract various features like color, shape and texture features from the input image. Over the features extracted, the genetic algorithm has been applied to perform feature selection. With the extracted features, the method applies adaptive neuro fuzzy inference technique to perform classification and grading. The classification algorithm estimates multi feature class similarity MFCS measure towards each class of mangoes to perform classification where the grading is performed based on the same being estimated within the class. The proposed GANFIS approach has achieved sensitivity (98.05%), specificity (97.39%) and Accuracy (99.18%).

Image classification, in general, is considered a hard problem, though it is necessary for many useful applications such as automatic target recognition. Indeed, no general methods exist that can work in varying scenarios and still achieve good performance across the board. In this paper, we actually identify a very interesting problem, where image classification is dangerously easy. We look at the problem of image classification, in the specific context of accurately classifying images containing highly sensitive data such as drivers licenses, credit cards and passports. Our key contribution is to build a Hierarchical Temporal Memory (HTM) network that is able to classify many sensitive images with over 90% accuracy, and use this to develop a system to automatically derive and transcribe sensitive information from image data. Our system classifies images into two groups -- sensitive and non-sensitive. The group of sensitive images can then be further analyzed. This is a real world security issue that could easily lead to privacy problems such as identity theft, since scans of passports and drivers licenses are routinely emailed or kept in digital form, and many local documents are left unencrypted. Essentially, an attacker can use data mining and machine learning techniques very effectively to breach individual privacy. Thus, our main contribution is to demonstrate the efficacy of image classification for deriving sensitive information, which could also serve as a guide for other interesting applications such as document detection and analysis. Thus, it also serves as a warning against leaving data unencrypted and again proves that security through obscurity is simply not enough.

Inspired by the pioneering work of the information bottleneck (IB) principle for Deep Neural Networks’ (DNNs) analysis, we thoroughly study the relationship among the model accuracy, and , where and are the mutual information of DNN’s output T with input X and label Y. Then, we design an information plane-based framework to evaluate the capability of DNNs (including CNNs) for image classification. Instead of each hidden layer’s output, our framework focuses on the model output T. We successfully apply our framework to many application scenarios arising in deep learning and image classification problems, such as image classification with unbalanced data distribution, model selection, and transfer learning. The experimental results verify the effectiveness of the information plane-based framework: Our framework may facilitate a quick model selection and determine the number of samples needed for each class in the unbalanced classification problem. Furthermore, the framework explains the efficiency of transfer learning in the deep learning area.

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.

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.

In this study, the authors address a challenging problem of aesthetic image classification, which is to label an input image as high‐ or low‐aesthetic quality. We take both the local and global features of images into consideration. A novel deep convolutional neural network named ILGNet is proposed, which combines both the inception modules and a connected layer of both local and global features. The ILGnet is based on GoogLeNet. Thus, it is easy to use a pre‐trained GoogLeNet for large‐scale image classification problem and fine tune their connected layers on a large‐scale database of aesthetic‐related images: AVA, i.e. domain adaptation . The experiments reveal that their model achieves the state of the arts in AVA database. Both the training and testing speeds of their model are higher than those of the original GoogLeNet.

Literature Review on Multi-Spectral Imaging for Fruits and Vegetable

Time series are widely distributed in many fields. Classical statistical methods are difficult to model the deep meaning of time series, and the deep learning methods based on recurrent neural network has great limitations when it is applied to indefinite long time series. In order to solve the above problems, a time series classification model based on computer vision is proposed, which transforms the time series classification problem into image classification problem. Firstly, three kinds of images with different linewidth corresponding to the time series are used as input to reduce the information loss in the conversion process. Secondly, the transfer learning model based on MobileNetV3-Large is used to encode the image data, and XGBoost is used for classification. The experimental results show that the classification effect of this model is better than that of the classical image classification model, and its XGBoost is also better than other ensemble methods, which proves the feasibility of computer vision method in time series classification task.

Due to large amount of image data, the accuracy and real-time performance of classification are difficult problems in image classification. On the one hand, the broad learning system (BLS) has achieved good results in the timeliness of classification. On the other hand, deep learning feature extraction effect is good, but its structure is complex and the training time is long. Therefore, based on the above advantages of both methods, this paper proposed BLS based on deep features for image classification. Firstly, a feature extractor is constructed based on the ResNet101 to obtain the deep features of the classification image. Then, the feature nodes and enhancement nodes of BLS are constructed based on the deep features. Through the experiment, our method has two performance on benchmark datasets: high classification accuracy, good real-time.

Upscaling of discrete fracture networks to continuum models such as the dual porosity/dual permeability (DPDP) model is an industry-standard approach in modelling of fractured reservoirs. While flow-based upscaling provides more accurate results than analytical methods, the application of flow-based upscaling is limited due to its high computational cost. In this work, we parametrize the fine-scale fracture geometries and assess the accuracy of several convolutional neural networks (CNNs) to learn the mapping between this parametrization and the DPDP model closures such as the upscaled fracture permeabilities and the matrix-fracture shape factors. We exploit certain similarities between this task and the problem of image classification and adopt several best practices from the state-of-the-art CNNs used for image classification. By running a sensitivity study, we identify several key features in the CNN structure which are crucial for achieving high accuracy of predictions for the DPDP model closures, and put forward the corresponding CNN architectures. Obtaining a suitable training dataset is challenging because i) it requires a dedicated effort to map the fracture geometries; ii) creating a conforming mesh for fine-scale simulations in presence of intersecting fractures typically leads to bad quality mesh elements; iii) fine-scale simulations are time-consuming. We alleviate some of these difficulties by pre-training a suitable CNN on a synthetic random linear fractures’ dataset and demonstrate that the upscaled parameters can be accurately predicted for a realistic fracture configuration from an outcrop data. The accuracy of the DPDP results with the predicted model closures is assessed by a comparison with the corresponding fine-scale discrete fracture-matrix (DFM) simulation of a two-phase flow in a realistic fracture geometry. The DPDP results match well the DFM reference solution, while being significantly faster than the latter.

A popular approach to problems in image classification is to represent the image as a bag of visual words and then employ a classifier to categorize the image. Unfortunately, a significant shortcoming of this approach is that the clustering and classification are disconnected. Since the clustering into visual words is unsupervised, the representation does not necessarily capture the aspects of the data that are most useful for classification. More seriously, the semantic relationship between clusters is lost, causing the overall classification performance to suffer. We introduce "discriminative cluster refinement" (DCR), a method that explicitly models the pairwise relationships between different visual words by exploiting their co-occurrence information. The assigned class labels are used to identify the co-occurrence patterns that are most informative for object classification. DCR employs a maximum-margin approach to generate an optimal kernel matrix for classification. One important benefit of DCR is that it integrates smoothly into existing bag-of-words information retrieval systems by employing the set of visual words generated by any clustering method. While DCR could improve a broad class of information retrieval systems, this paper focuses on object category recognition. We present a direct comparison with a state-of-the art method on the PASCAL 2006 database and show that cluster refinement results in a significant improvement in classification accuracy given a small number of training examples.