Efficient Image-Based Memory Forensics for Fileless Malware Detection Using Texture Descriptors and LIME-Guided Deep Learning

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.

Power transmission line icing (PTLI) poses significant threats to the reliability and safety of electrical power systems, particularly in cold regions. Accumulation of ice on power lines can lead to severe consequences, such as line breaks, tower collapses, and widespread power outages, resulting in economic losses and infrastructure damage. This study proposes an enhanced image processing pipeline to accurately detect and match key points in PTLI images for 3D monitoring of ice thickness using binocular vision. The pipeline integrates established techniques such as multiscale retinex (MSR), oriented FAST and rotated BRIEF (ORB) and scale-invariant feature transform (SIFT) algorithms, further refined with m-estimator sample consensus (MAGSAC)-based random sampling consensus (RANSAC) optimization. The image processing steps include automatic cropping, image enhancement, feature detection, and robust key point matching, all designed to operate in challenging environments with poor lighting and noise. Experiments demonstrate that the proposed method significantly improves key point matching accuracy and computational efficiency, reducing processing time to make it suitable for real-time applications. The effectiveness of the pipeline is validated through 3D ice thickness measurements, with results showing high precision and low error rates, making it a valuable tool for monitoring power transmission lines in harsh conditions.

Object recognition is a key research area in the field of image processing and computer vision, which recognizes the object in an image and provides a proper label. In the paper, three popular feature descriptor algorithms that are Scale Invariant Feature Transform (SIFT), Speeded Up Robust Feature (SURF) and Oriented Fast and Rotated BRIEF (ORB) are used for experimental work of an object recognition system. A comparison among these three descriptors is exhibited in the paper by determining them individually and with different combinations of these three methodologies. The amount of the features extracted using these feature extraction methods are further reduced using a feature selection (k-means clustering) and a dimensionality reduction method (Locality Preserving Projection). Various classifiers i.e. K-Nearest Neighbor, Naive Bayes, Decision Tree, and Random Forest are used to classify objects based on their similarity. The focus of this article is to present a study of the performance comparison among these three feature extraction methods, particularly when their combination derives in recognizing the object more efficiently. In this paper, the authors have presented a comparative analysis view among various feature descriptors algorithms and classification models for 2D object recognition. The Caltech-101 public dataset is considered in this article for experimental work. The experiment reveals that a hybridization of SIFT, SURF and ORB method with Random Forest classification model accomplishes the best results as compared to other state-of-the-art work. The comparative analysis has been presented in terms of recognition accuracy, True Positive Rate (TPR), False Positive Rate (FPR), and Area Under Curve (AUC) parameters.

This paper explores the use of satellite remote sensing technology to observe and measure the earth's surface and classify remote sensing images using various deep learning algorithms. By importing AlexNet, VggNet, GoogleNet and MobileNet models, 90% of the data are randomly selected for training and 10% for testing, and the changes in the loss and accuracy of the validation set during training are recorded, as well as the accuracy of the best round of epochs for training.During the training process, the validation set's loss gradually decreased and converged, and the accuracy of the validation set gradually increased and stabilised. The results show that all four models are able to classify remote sensing images well, among which the highest accuracy is MobileNet model, which reaches 99.8%, and Googlenet model is the second one, which reaches 97.9%.AlexNet and VggNet models also have higher accuracy, which are 93.3% and 95.4%, respectively. Overall, the results of this paper provide an effective solution for satellite remote sensing image classification and provide a reference for the application of deep learning algorithms in remote sensing.

This study presents an automated quality inspection approach for detecting surface defects in industrial casting parts using image processing and machine learning techniques. A total of ten different feature extraction methods—Histogram of Oriented Gradients (HOG), Local Binary Patterns (LBP), Scale-Invariant Feature Transform (SIFT), Gray Level Co-occurrence Matrix (GLCM), Gabor filters, color histogram, wavelet transform, Hu moments, Zernike moments, and Fourier transform—were applied to 300×300 grayscale images. To evaluate the effect of spatial resolution, features were extracted at five different cell sizes: 25×25, 50×50, 100×100, 150×150, and 300×300. Dimensionality reduction was performed using minimum Redundancy Maximum Relevance (mRMR) and Chi-square (χ²) feature selection techniques. The resulting feature sets were classified with six different algorithms in MATLAB Classification Learner, including Fine Tree, Fine KNN, Wide Neural Network, Bagged Trees, Fine Gaussian SVM, and Binary GLM. Experimental results demonstrated that the highest accuracy rate of 99.7% was achieved with the Wide Neural Network model trained on the complete feature set at a 25×25 cell size. These findings indicate that smaller cell sizes preserve critical surface details and enhance classification performance. The study highlights that the proposed methodology can serve as a highly accurate, efficient, and practical solution for automated defect detection in the casting industry, offering strong potential for real-world industrial applications.

In various applications, such as computer vision, medical imaging and robotics, three-dimensional (3D) image registration is a significant step. It enables the alignment of various datasets into a single coordinate system, consequently providing a consistent perspective that allows further analysis. By precisely aligning images we can compare, analyze, and combine data collected in different situations. This paper presents a novel approach for 3D or z-stack microscopy and medical image registration, utilizing a combination of conventional and deep learning techniques for feature extraction and adaptive likelihood-based methods for outlier detection. The proposed method uses the Scale-invariant Feature Transform (SIFT) and the Residual Network (ResNet50) deep neural learning network to extract effective features and obtain precise and exhaustive representations of image contents. The registration approach also employs the adaptive Maximum Likelihood Estimation SAmple Consensus (MLESAC) method that optimizes outlier detection and increases noise and distortion resistance to improve the efficacy of these combined extracted features. This integrated approach demonstrates robustness, flexibility, and adaptability across a variety of imaging modalities, enabling the registration of complex images with higher precision. Experimental results show that the proposed algorithm outperforms state-of-the-art image registration methods, including conventional SIFT, SIFT with Random Sample Consensus (RANSAC), and Oriented FAST and Rotated BRIEF (ORB) methods, as well as registration software packages such as bUnwrapJ and TurboReg, in terms of Mutual Information (MI), Phase Congruency-Based (PCB) metrics, and Gradiant-based metrics (GBM), using 3D MRI and 3D serial sections of multiplex microscopy images.

Increased use of 3D digitization methods leads to large numbers of 3D models with script like cuneiform tablets, temple wall inscriptions from the Mayan empire and Minoan and Mycenaean seal imprints. Analyzing and in particular comparing those objects in our projects is a core challenge for robust symbol-spotting and transcription of ancient scripts. The discrete manifolds using irregular grids describe the objects' surface and contain complex shapes that cannot be wholly captured by a single rendering to a two dimensional plane in an image format. As the plethora of standard image descriptor extraction methods is not available on those 3D meshes we propose a novel approach adapting relevant image descriptor methods to process irregular grids. We show preliminary evaluations of our approach by performing a symbol spotting task on cuneiform tablets. Our approach proceeds in three stages: (i) We compute a local surface feature with Multi-scale Integral Invariants (MSII), (ii) for each vertex we extract radial geodesic patches which are embedded locally into a polar coordinate system, (iii) a rectangular sampling scheme converts these patches into raster image patches that are accessible to 2D image descriptors. For the symbol spotting task we compute Histogram of Oriented Gradients (HOG) and Oriented FAST and Rotated BRIEF (ORB) descriptors on the query mesh and document mesh for each vertex. Similar symbols are retrieved by sliding a geodesic patch along the document mesh. Like in many other Cultural Heritage applications we have to consider the lack of any ground-truth. Therefore we provide a qualitative analysis of the spotting results showing that a query mesh is reliably found on the document mesh.

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).

We aim at segmenting small organs (e.g., the pancreas) from abdominal CT scans. As the target often occupies a relatively small region in the input image, deep neural networks can be easily confused by the complex and variable background. To alleviate this, researchers proposed a coarse-to-fine approach [46], which used prediction from the first (coarse) stage to indicate a smaller input region for the second (fine) stage. Despite its effectiveness, this algorithm dealt with two stages individually, which lacked optimizing a global energy function, and limited its ability to incorporate multi-stage visual cues. Missing contextual information led to unsatisfying convergence in iterations, and that the fine stage sometimes produced even lower segmentation accuracy than the coarse stage. This paper presents a Recurrent Saliency Transformation Network. The key innovation is a saliency transformation module, which repeatedly converts the segmentation probability map from the previous iteration as spatial weights and applies these weights to the current iteration. This brings us two-fold benefits. In training, it allows joint optimization over the deep networks dealing with different input scales. In testing, it propagates multi-stage visual information throughout iterations to improve segmentation accuracy. Experiments in the NIH pancreas segmentation dataset demonstrate the state-of-the-art accuracy, which outperforms the previous best by an average of over 2%. Much higher accuracies are also reported on several small organs in a larger dataset collected by ourselves. In addition, our approach enjoys better convergence properties, making it more efficient and reliable in practice.

Biometrics is the study of unique characteristics present in the human body such as fingerprint, palm-print, retina, iris, footprint, etc. While other traits have been explored widely, only a few people have been considered the foot-palm region, despite having unique properties. Prior work has explored the foot shape features using length, width, major axis, minor axis, centroid, etc. but they are not reliable for personal verification due to similarity in the physical composition of two persons. It increases the demand for more unique features based on the footprint. Footprint texture features coming from creases of foot palm are unique and permanent like palmprint texture features. Hence the main objective of the paper is to investigate various kinds of texture feature techniques. These techniques will be further used in correct extraction of footprint features. After extraction of footprint features a detailed experimental analysis is performed to discover the uniqueness in foot texture. It is further utilized to test its viability as a human recognition trait. We describe a detailed feature extraction and classification technique applied to a collected footprint data-set. For feature extraction, we use three techniques: Gray Level Co-occurrence Matrix (GLCM), Histogram Oriented Gradient (HOG), and Local Binary Patterns (LBP). Feature classification is performed using four techniques: Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Ensemble Subspace Discriminant (ESD). GLCM provides less accuracy, while HOG generates a big feature vector which takes more execution time. LBP provides a trade-off between the accuracy and the execution time. Detailed quantitative experiments show: GLCM with LDA provides an accuracy of $$88.5\%$$ , HOG with Fine-KNN achieves $$86.5\%$$ accuracy and LBP with LDA achieves the accuracy of $$97.9\%$$ .

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.

Cancer is now the leading causes of death. During treatment, if an abnormal mass is detected by routine mammography after histological examination, a biopsy will be performed for further diagnosis. However, the time required to review and evaluate the biopsy slide is very long. An effective algorithm that can identify cancer tissues and reduce the rate of misdiagnosis is urgently needed. The current research methods mainly include: Capsule Network, and Deep Convolutional Neural Networks (CNNs) used in image classification, etc. This paper mainly uses Capsule Network, CNN, CNN trained on Histogram of Oriented Gradient (HOG) images, and Grey Level Co-occurrence Matrix (GLCM) to classify benign and malignant images of the tumor micro-biopsy images. The first step is to download the breast tumor micro-biopsy images from Breakhis. The second step is to preprocess the images, mainly image enhancement, augmentation, and HOG feature extraction. In the third step, the processed image data is used to train CNN and Capsule Network. The last step is to visualize the accuracy of model training and use confusion matrix to calculate the accuracy of image classification, recall rate, and so on. The results show that the accuracy of CNN with the help of transfer learning can reach 98.32%, the accuracy of CNN trained with HOG image is only 82.99%, the accuracy of CNN trained with GLCM is 92.79%, and the accuracy of capsule network can reach 92.39%.

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.

In this paper, the traffic sign recognition module of a small-scale autonomous car prototype will be presented. The process undergoing the choice of an appropriate algorithm, as well as the factors taken into consideration will be presented in the form of a case study. The current literature presents various ways of achieving the recognition of traffic signs, but most of them are computational expensive, or have difficulty in offering consistent results in conditions that are different from the prerecorded ones. Since the processing on the car is carried on an embedded platform from Nvidia (Jetson TX2), this study is based on the same board, the stream being captured with a low-cost webcam. Classical algorithms like SURF (Speeded Up Robust Features), SIFT (Scale Invariant Feature Transform) or ORB (Oriented fast and Rotated Brief) offer reliable results when the lighting condition between the reference image and the image obtained from the camera are similar. In our setup, the algorithms mentioned above start to behave badly in low light conditions. Therefore, this paper discusses the possibility of using Haar like features alongside a classifier for detecting traffic signs.

This paper presents a fast and accurate system to determine the type of blood automatically based on image processing. Blood type determination is important in emergency situations, where there is a need for blood transfusion to save lives. The traditional blood determination techniques are performed manually by a specialist in medical labs, where the result requires a long time or may be affected by human error. This may cause serious consequences or even endanger people’s lives. The proposed approach performs blood determination in real-time with low cost using any available mobile device equipped with a camera. A total of 500 blood samples were processed in this study using different image matching techniques including oriented fast and rotated brief (ORB), scale invariant feature transform (SIFT), and speed-up robust feature (SURF). The evaluation results show that our proposed system, which adopts the ORB algorithm, is the fastest and the most accurate among the state-of-the-art systems. It can achieve an accuracy of 99.6% in an average time of 250 ms.