Suchergebnisse

The era in which we live has become the era of big data, particularly with the spread of the concept of Internet-of-Things (IoT) and artificial-intelligence (AI). Images constitute a large portion of this data that is created and handled. Image classification is the process of identifying and labeling groups of pixels or vectors inside an image using certain criteria. Major image classification techniques divided into two categories which are supervised and unsupervised techniques. This study looks at various research, techniques, and issues of image classification. The focus is on summarizing the main advanced classification strategies and methods such as (K-Mean clustering, Fuzzy measure, Artificial Neural Networks (ANN), Decision-Tree (DT), Support-Vector-Machines (SVMs), Naive Bayes (NB), K-Nearest-Neighbor (KNN), Random-Forest (RF), etc.) that can be utilized after some update to enhance classification accuracy. Also, this study shows the common challenges and solutions in this area.

Machine learning-based techniques are used widely for the classification of images into various categories. The advancement of Convolutional Neural Network (CNN) affects the field of computer vision on a large scale. It has been applied to classify and localize objects in images. Among the fields of applications of CNN, it has been applied to understand huge unstructured astronomical data being collected every second. Galaxies have diverse and complex shapes and their morphology carries fundamental information about the whole universe. Studying these galaxies has been a tremendous task for the researchers around the world. Researchers have already applied some basic CNN models to predict the morphological classes of the galaxies. In this paper, a residual network (ResNet) model is applied for this purpose. The proposed methodology classified the galaxies depending on their shape into 37 different classes. The performance of the methodology was evaluated using the data set provided by Kaggle. In this data set, 61,578 galaxy images are given, which are classified by human eye. The model achieved nearly 98% accuracy.

"Phishing Detection using content-based image classification is an invaluable resource for any deep learning and cybersecurity professional and scholar trying to solve various cybersecurity tasks using new age technologies like Deep Learning and Computer Vision. With various rule-based phishing detection techniques at play which can be bypassed by phishers, this book provides a step-by-step approach to solve this problem using Computer Vision and Deep Learning techniques with significant accuracy. The book offers comprehensive coverage of the most essential topics, including: Programmatically reading and manipulating image data; Extracting relevant features from images; Building statistical models using image features; Using state of the art Deep Learning models for feature extraction; Build a robust phishing detection tool even with less data; Dimensionality reduction techniques; Class imbalance treatment; Feature Fusion techniques; Building performance metrics for multi-class classification task. Another unique aspect of this book is it comes with a completely reproducible code base developed by the author and shared via python notebooks for quick launch and running capabilities. They can be leveraged for further enhancing the provided models using new advancement in the field of computer vision and more advanced algorithms"--

Cover -- Half Title -- Title Page -- Copyright Page -- Table of Contents -- Preface -- Authors -- Chapter 1 Phishing and Cybersecurity -- Structure -- Objective -- Basics of Phishing in Cybersecurity -- Phishing Detection Techniques -- List (Whitelist/Blacklist)-Based -- Heuristics (Pre-Defined Rules)-Based -- Visual Similarity-Based -- Race between Phishers and Anti-Phishers -- Chapter 2 Image Processing-Based Phishing Detection Techniques -- Structure -- Objective -- Image Processing-Based Phishing Detection Techniques -- Comparison-Based Techniques -- Machine Learning-Based Techniques -- Challenges in Phishing Detection Using Website Images -- Comparison of Techniques -- Summary of Phishing Detection Using Image Processing Techniques -- Various Experimentations Using CNN -- Summary -- Chapter 3 Implementing CNN for Classifying Phishing Websites -- Structure -- Objective -- Data Selection and Pre-Processing -- Classification Using CNN -- CNN Implementation -- Label Encoding for Machine Learning Classifier -- One Hot Encoding for Deep Learning Classifier -- Performance Metrics -- Building a Convolutional Neural Network Model -- Summary -- Chapter 4 Transfer Learning Approach in Phishing Detection -- Structure -- Objective -- Classification Using Transfer Learning -- Transfer the Learning up to the Last Fully Connected Layer -- Transfer Learning Implementation in Python -- Performance Assessment of the CNN Models -- Summary -- Chapter 5 Feature Extraction and Representation Learning -- Structure -- Objective -- Classification Using Representation Learning -- Data Preparation -- Convert Images to Numpy Arrays -- Feature Extraction Using CNN Off-the-Shelf Architectures -- Xception -- VGG19 -- ResNet50 -- InceptionV3 -- InceptionResNetV2 -- MobileNet -- DenseNet121 -- Handling Class Imbalance -- Adding Synthetic Data Using SMOTE.

Augmentation techniques are crucial for accurately training convolution neural networks (CNNs). Therefore, these techniques have become the preprocessing methods. However, not every augmentation technique can be beneficial, especially those that change the image's underlying structure, such as color augmentation techniques. In this study, the effect of eight brightness scales was investigated in the task of classifying a large histopathology dataset. Four state-of-the-art CNNs were used to assess each scale's performance. The use of brightness was not beneficial in all the experiments. Among the different brightness scales, the [0.75–1.00] scale, which closely resembles the original brightness of the images, resulted in the best performance. The use of geometric augmentation yielded better performance than any brightness scale. Moreover, the results indicate that training the CNN without applying any augmentation techniques led to better results than considering brightness augmentation. Therefore, experimental results support the hypothesis that brightness augmentation techniques are not beneficial for image classification using deep-learning models and do not yield any performance gain. Furthermore, brightness augmentation techniques can significantly degrade the model's performance when they are applied with extreme values. Doi: 10.28991/ESJ-2022-06-04-015 Full Text: PDF

In this review paper, several studies and researches were surveyed for assisting future researchers to identify available techniques in the field of classification of Synthetic Aperture Radar (SAR) images. SAR images are becoming increasingly important in a variety of remote sensing applications due to the ability of SAR sensors to operate in all types of weather conditions, including day and night remote sensing for long ranges and coverage areas. Its properties of vast planning, search, rescue, mine detection, and target identification make it very attractive for surveillance and observation missions of Earth resources. With the increasing popularity and availability of these images, the need for machines has emerged to enhance the ability to identify and interpret these images effectively. This is due to the fact that SAR image processing requires the formation of an image from the measured radar scatter returns, followed by a treatment to discover and define the image's composition. After reviewing several previous studies that succeeded in achieving a classification of SAR images for specific goals, it became obvious that they could be generalized to all types of SAR images. The most prominent use of Convolutional Neural Networks (CNN) was successful in extracting features from the images and training the neural network to analyze and classify them into classes according to these features. The dataset used in this model was obtained from the Moving and Stationary Target Acquisition and Recognition (MSTAR) database, which consists of a set of SAR images of military vehicles, for which the application of the CNN approach achieved a final accuracy of 97.91% on ten different classes.

Alzheimer's Disease (AD) is the most prevailing type of dementia. The prevalence of AD is estimated to be around 5% after 65 years old and is staggering 30% for more than 85 years old in developed countries. AD destroys brain cells causing people to lose their memory, mental functions and ability to continue daily activities. The findings of this study are likely to aid specialists in their decision-making process by using patients' Magnetic Resonance Imaging (MRI) to distinguish patients with AD from Normal Control (NC). Performance evolution was applied to 346 Magnetic Resonance images from the Alzheimer's Neuroimaging Initiative (ADNI) collection. The Deep Belief Network (DBN) classifier was used to fulfill classification function. Weights were used to test the proposed method's recognition capacity, and the network was trained with a sample training set. As a result, this study offeres a new method for identifying Alzheimer's disease utilizing automated categorization. In tests, it performed admirably With 98.46% accuracy achieved for AD and NC studied classes when combining Gray Level Co-occurrence Matrix (GLCM) features with a DBN.

Ships are an integral part of maritime traffic where they play both militaries as well as non-combatant roles. This vast maritime traffic needs to be managed and monitored by identifying and recognising vessels to ensure the maritime safety and security. As an approach to find an automated and efficient solution, a deep learning model exploiting convolutional neural network (CNN) as a basic building block, has been proposed in this paper. CNN has been predominantly used in image recognition due to its automatic high-level features extraction capabilities and exceptional performance. We have used transfer learning approach using pre-trained CNNs based on VGG16 architecture to develop an algorithm that performs the different ship types classification. This paper adopts data augmentation and fine-tuning to further improve and optimize the baseline VGG16 model. The proposed model attains an average classification accuracy of 97.08% compared to the average classification accuracy of 88.54% obtained from the baseline model.

<p class="p1">With the tremendous development of computer graphic rendering technology, photorealistic computer graphic images are difficult to differentiate from photo graphic images. In this article, a method is proposed based on discrete wavelet transform based binary statistical image features to distinguish computer graphic from photo graphic images using the support vector machine classifier. Textural descriptors extracted using binary statistical image features are different for computer graphic and photo graphic which are based on learning of natural image statistic filters. Input RGB image is first converted into grayscale and decomposed into sub-bands using Haar discrete wavelet transform and then binary statistical image features are extracted. Fuzzy entropy based feature subset selection is employed to choose relevant features. Experimental results using Columbia database show that the method achieves good detection accuracy.</p>