Feature Descriptors for Spotting 3D Characters on Triangular Meshes

Memory forensics is an essential cybersecurity tool that comprehensively examines volatile memory to detect the malicious activity of fileless malware that can bypass disk analysis. Image-based detection techniques provide a promising solution by visualizing memory data into images to be used and analyzed by image processing tools and machine learning methods. However, the effectiveness of image-based data for detection and classification requires high computational efforts. This paper investigates the efficacy of texture-based methods in detecting and classifying memory-resident or fileless malware using different image resolutions, identifying the best feature descriptors, classifiers, and resolutions that accurately classify malware into specific families and differentiate them from benign software. Moreover, this paper uses both local and global descriptors, where local descriptors include Oriented FAST and Rotated BRIEF (ORB), Scale-Invariant Feature Transform (SIFT), and Histogram of Oriented Gradients (HOG) and global descriptors include Discrete Wavelet Transform (DWT), GIST, and Gray Level Co-occurrence Matrix (GLCM). The results indicate that as image resolution increases, most feature descriptors yield more discriminative features but require higher computational efforts in terms of time and processing resources. To address this challenge, this paper proposes a novel approach that integrates Local Interpretable Model-agnostic Explanations (LIME) with deep learning models to automatically identify and crop the most important regions of memory images. The LIME’s ROI was extracted based on ResNet50 and MobileNet models’ predictions separately, the images were resized to 128 × 128, and the sampling process was performed dynamically to speed up LIME computation. The ROIs of the images are cropped to new images with sizes of (100 × 100) in two stages: the coarse stage and the fine stage. The two generated LIME-based cropped images using ResNet50 and MobileNet are fed to the lightweight neural network to evaluate the effectiveness of the LIME-based identified regions. The results demonstrate that the LIME-based MobileNet model’s prediction improves the efficiency of the model by preserving important features with a classification accuracy of 85% on multi-class classification.

This paper attempted to detect mitotic nuclei by extracting different features from nuclei patches in the histopathology Images. We extracted features at multiple levels such as pixel, global, and local to find the best combination of features required for efficient mitosis analysis. We then passed an optimal subset of features to three different classifiers by applying the hyperparameter optimization technique. We observed the highest accuracy of 87.4 with a feature combination of the histogram of oriented gradients (HOG), oriented FAST and rotated BRIEF (ORB), center surround extremas (Censure), corner peaks, edge extract, and grayscale pixel value using tree-based pipeline optimization tool (TOPT) as the hyperparameter optimizer with support vector machine (SVM).

Plant disease detection plays a critical role in ensuring agricultural productivity and food security. Accurate and efficient identification of plant diseases can aid in timely interventions, reducing potential crop losses. This paper presents a comprehensive study involving the application of deep learning models, namely CNN, ResNet, VGG, and Inception, to grayscale plant disease image datasets for apple, grape, and corn. The datasets consist of grayscale images divided into multiple disease classes. Initial experiments using standard deep learning models demonstrated reasonable accuracy. To further enhance performance, manual feature extraction techniques, including Histogram of Oriented Gradients (HOG), Oriented FAST and Rotated BRIEF (ORB), and Scale-Invariant Feature Transform (SIFT), were applied alongside deep features extracted using pretrained VGG and ResNet models. The extracted deep learning and handcrafted features were concatenated to form a comprehensive feature set. A Random Forest Classifier (RFC) was then applied to this combined feature set, resulting in improved accuracy compared to individual models.

The image recognition method is a significant process in addressing contemporary global issues. Numerous image detection, analysis, and classification strategies are readily available, but the distinctions between these approaches remain somewhat obscure. Therefore, it is essential to clarify the differences between these techniques and subject them to rigorous analysis. This study utilizes a dataset comprising standard American Sign Language (ASL) and Indian Sign Language (ISL) hand gestures captured under various environmental conditions. The primary objective is to accurately recognize and classify these hand gestures based on their meanings, aiming for the highest achievable accuracy. A novel method for achieving this goal is proposed and compared with widely recognized models. Various pre-processing techniques are employed, including principal component analysis and histogram of gradients. The principal model incorporates Canny edge detection, Oriented FAST and Rotated BRIEF (ORB), and the bag of words technique. The dataset includes images of the 26 alphabetical signs captured from different angles. The collected data is subjected to classification using Support Vector Machines to yield valid results. The results indicate that the proposed model exhibits significantly higher efficiency than existing models.

The field of machine learning is growing in modern times, computational models are able to go beyond the performance of previous forms of artificial intelligence. The use of evaluation model ,selection of model and algorithm selecting techniques play an major role in machine learning study and also in field of industries. In this work, we made evaluation of various supervised, unsupervised machine learning classifiers for flower datasets. We made use of local features such as Histogram of gradient , Kaze, Local binary pattern(LBP) ,Oriented Fast and Rotated Brief( ORB), global features like Color Histograms, Haralick Textures , Hu Moments , fusion of both and Bag of visual words(BOVW) using Vocabulary builder K-Means clustering which represents color ,texture, shape features of image. Experiment is carried out on 20 classes of flower datasets with 100 images each. .Flower datasets have many characteristic in common like sunflower will be similar to daffodil in terms of color and texture .Hence to quantify the image we need to combine different feature descriptors like color, texture and shape features. We develop a Content based classification system to find efficiency comparison of different machine learning algorithms for classification and retrieval problems. Eleven classifiers mainly Support Vector Machine, K Nearest Neighbor, Gaussian Naive Bayes , CART, Kmeans, Linear Discriminant Analysis, Adaboost ,Logistic Regression, MLP, Random Forest, CNN are analyzed on the shape, color ,texture features. Experimentation are carried out and results are recorded using CPU as well as GPU on google cobalatory platform.

Currency is of great importance in everyday life and is the lifeline of every transaction. Even with the vast utilization of cards and other electronic payments, paper currency is still extensively used because of its convenience. There are around 10 different types of notes in Indian currency, and every banknote is different from other in dimensions. For instance, colour and pattern, size of the note, and so on. Most of the people practice the usage of Master Cards and Electronic payment and where the money is accepted for ordinary exchanges because of its accessibility. Visually impaired people undergo the difficulty of differentiating the currency papers. Currency Recognition System (CRS) may be effective for the blind and visually impaired people during the process of currency trade. In the proposed method a Currency Recognition System based on Accelerated- KAZE(AKAZE) algorithm is suggested, Accelerated-KAZE (AKAZE) algorithm is based around the concept of nonlinear diffusion filtering. It aims to provide an accurate and efficient alternative to Oriented FAST and rotated BRIEF(ORB). The proposed system is applied to Indian paper currencies. Originally, some of the preprocessing procedures are conducted on the input paper currency image. Then, colour mapping of the input image is done to distinguish colour components from depth. After this, the ROI (Region of Interest) is the essence of the input image. The AKAZE Algorithm is used to find key points and descriptors of the input image. Finally. the detection of currency is done by using brute force matcher technique, it matches descriptors & keypoints of the input image with every descriptor stored in dataset using Hamming Distance Calculation. In a real-world situation, the proposed system playa a vital role in identifying currency images with greater accuracy of 90 % which is achieved and determined. This proposed system aims to make the life of visually impaired people easier.

A new image feature descriptor for content based image retrieval using scale invariant feature transform and local derivative pattern

The paper addresses a problem of feature selection for automatic prostate segmentation in Computed Tomography (CT) planning data for radiotherapy process. The following image descriptors have been tested in 2D and 3D scenarios: standard Hounsfield Unit (HU) profiles, histogram of oriented gradient (HoG), Haar wavelets, and Modality Independent Neighborhood Descriptor (MIND). The task was to distinguish a prostate interior and exterior. 22 CT volumes with different spatial resolution and different organ outlines have been used. The k-Nearest Neighbors (kNN) classifier was applied and the following recognition measures were evaluated, with 10-fold cross-validation: accuracy, precision, sensitivity and specificity.

Cybercriminals use malware or malicious software to cause harm to the victim. Malware is a continuous source of concern for security teams. Malware analysis techniques, including static, dynamic, hybrid, and memory analysis, are used to comprehend the behavior and its impact. The aforementioned malware analysis techniques require domain knowledge to extract the artifacts from suspicious files, which is not always possible. A visualization approach, in which malware files are transformed into images, is one of the recently used techniques by researchers for malware detection and classification. In this paper, we apply four widely used techniques based on the visualization using a new dataset of memory dump files of malware families and benign classes. These visualization techniques include a histogram of oriented gradients (HOG) with multilayer perceptron (MLP), convolutional neural network (CNN) with pretrained weight of visual geometry group 16 (VGG), Transfer learning of VGG16 with support vector machine (SVM), and integration of global image descriptor (GIST) and HOG with SVM. Among the selected techniques, CNN with a pretrained weight of VGG16 outperformed the other techniques in terms of accuracy, precision, recall, and f1-score. Apart from the performance metrics, the results of selected techniques are also analyzed in terms of computational cost and memory utilization.

Several new image descriptors are presented in this paper that combine color, texture and shape information to create feature vectors for scene and object image classification. In particular, first, a new three dimensional Local Binary Patterns (3D-LBP) descriptor is proposed for color image local feature extraction. Second, three novel color HWML (HOG of Wavelet of Multiplanar LBP) descriptors are derived by computing the histogram of the orientation gradients of the Haar wavelet transformation of the original image and the 3D-LBP images. Third, the Enhanced Fisher Model (EFM) is applied for discriminatory feature extraction and the nearest neighbor classification rule is used for image classification. Finally, the Caltech 256 object categories database and the MIT scene dataset are used to show the feasibility of the proposed new methods.

Object categorization plays an important role in computer vision, semantic based image content understanding, and image retrieval. Wavelet packet transform provides a very good observation for the images by sub-band filtering. Different objects have distinctive characteristics in the sub-bands of wavelet packets, which should be discriminative for objects classification. In this paper, an object categorization method using hierarchical wavelet packet texture descriptors is proposed. Comparisons between Gabor texture descriptor, pyramid of histograms of orientation gradients (PHOG) and the proposed hierarchical wavelet packet texture descriptors on the widely used OT, Scene-13 and Sport event datasets are also given. Experimental results show that object categorization performances of the proposed texture descriptors are better than that of Gabor texture descriptor and as good as that of PHOG shape descriptor. Object categorization performances of the texture descriptors under various decomposition levels and wavelet bases are discussed. Performances of texture descriptors of global and local images with different partition patterns are also analyzed.

Technologies for 3D mesh compression: A survey

Chapter 10 - Characterization of free-form surfaces

We present an offline signature verification system based on a signature's local histogram features. Test signature is divided into zones using both the Cartesian and log polar coordinate systems and histogram of oriented gradients (HOG) is calculated for each zone. Verification is considered as a two-class classification problem and for this purpose, a user independent Support Vector Machine (SVM) model is trained using both genuine and skilled forgery signatures of a completely different set of people than those in the test set. For each feature type, a single SVM model which learns the differences of query and reference signatures' feature vectors, is trained. The fusion of all classifiers, using skilled forgeries as negative test examples, achieves a 24.30% equal error rate in the GPDS-160 signature database, with 5 references.

Wear mechanisms and severity level classification in iron ore transfer chute linings by propagating regional labels coded as embedding deep learning vectors