Histogram of gradient and binarized statistical image features of wavelet subband-based palmprint features extraction

Facial Expression Recognition (FER), also known as Facial Emotion Recognition, is an active topic in computer vision and machine learning fields. This paper analyzes different feature extraction and classification methods to propose an efficient facial expression recognition system. We have studied several feature extraction methods, including Histogram of Oriented Gradients (HOG), face-encoding, and the features extracted by a VGG16 Network. For classification, different classical classifiers, including Support Vector Machines (SVM), Adaptive Boosting (AdaBoost), and Logistic Regression, are evaluated with these features. Besides, we have trained a ResNet50 model from scratch and also tuned a ResNet50 which is pre-trained on VGGFace2 dataset. Finally, a part-based ensemble classifier is also proposed by focusing on different parts of face images. The experimental results provided on FER-2013 Dataset show that the tuned model of ResNet50 with a complete image of face, achieves higher performance than the other methods.

One of the most common causes of death worldwide is skin cancer and its incidence is increasing. To achieve optimal treatment and improve clinical outcomes for patients, precision skin cancer detection and classification approaches are required, which can be achieved through the application of feature extraction and machine learning algorithms. The development of such algorithms to identify important patterns from skin cancer image datasets enables early detection and more accurate classification and more effective treatment. Although previous studies have tried to detect skin cancer using feature extraction techniques such as HFF, HOG, and GLCM, some weaknesses still need to be improved. This research aims to combine various feature extraction methods such as Gray Level Co-occurrence Matrix, Histogram Oriented Gradients, and Local Binary Patterns and machine learning algorithms such as Support Vector Machine, Random Forest, and Gaussian Naïve Bayes in the classification process between Melanoma and Nevus skin cancers. In this research, the number of datasets used is 17,397 derived from the ISIC Dataset. The results showed that the Histogram Oriented Gradients method with Support Vector Machine algorithm achieved the highest accuracy of 92%. The combination of Gray Level Co-occurrence Matrix and Local Binary Patterns with Random Forest algorithm also achieved an accuracy of 92%, the combination of Gray Level Co-occurrence Matrix, Histogram Oriented Gradients, and Local Binary Patterns with Random Forest algorithm also resulted in an accuracy of 92%. These findings suggest that the combination of various feature extraction methods and machine learning algorithms can improve accuracy in skin cancer classification, which in turn can contribute to early detection and more effective treatment.

In many medical applications, feature selection is obvious; but in medical domains, selecting features and creating a feature vector may require more effort. The wavelet transform (WT) technique is used to identify the characteristic points of an electrocardiogram (ECG) signal with fairly good accuracy, even in the presence of severe high-frequency and low-frequency noise. Principal component analysis (PCA) is a suitable technique for ECG data analysis, feature extraction, and image processing — an important technique that is not based upon a probability model. The aim of the paper is to derive better diagnostic parameters for reducing the size of ECG data while preserving morphology, which can be done by PCA. In this analysis, PCA is used for decorrelation of ECG signals, noise, and artifacts from various raw ECG data sets. The aim of this paper is twofold: first, to describe an elegant algorithm that uses WT alone to identify the characteristic points of an ECG signal; and second, to use a composite WT-based PCA method for redundant data reduction and better feature extraction. PCA scatter plots can be observed as a good basis for feature selection to account for cardiac abnormalities. The study is analyzed with higher-order statistics, in contrast to the conventional methods that use only geometric characteristics of feature waves and lower-order statistics. A new algorithm — viz. PCA variance estimator — is developed for this analysis, and the results are also obtained for different combinations of leads to find correlations for feature classification and useful diagnostic information. PCA scatter plots of various chest and augmented ECG leads are obtained to examine the varying orientations of the ECG data in different quadrants, indicating the cardiac events and abnormalities. The efficacy of the PCA algorithm is tested on different leads of 12-channel ECG data; file no. 01 of the Common Standards for Electrocardiography (CSE) database is used for this study. Better feature extraction is obtained for some specific combinations of leads, and significant improvement in signal quality is achieved by identifying the noise and artifact components. The quadrant analysis discussed in this paper highlights the filtering requirements for further ECG processing after performing PCA, as a primary step for decorrelation and dimensionality reduction. The values of the parameters obtained from the results of PCA are also compared with those of wavelet methods.

The preservation of traditional batik patterns, often transmitted orally and through direct practice across generations, faces significant challenges in the modern era. Globalization introduces the risk of cultural homogenization, potentially diminishing the uniqueness and diversity of these patterns. Furthermore, the manual recognition of batik motifs is labor-intensive, time-consuming, and requires specialized expertise, rendering it unsuitable for large-scale preservation initiatives. Consequently, the development of technology-based solutions capable of documenting, analyzing, and recognizing batik patterns with efficiency and precision is imperative for safeguarding this cultural heritage. This study aims to address these challenges by developing an automated system for recognizing batik patterns, focusing on Javanese batik motifs—Kawung, Megamendung, and Parang—which serve as foundational designs for the evolution of batik in other regions. The proposed methodology integrates two feature extraction techniques, Histogram of Oriented Gradients (HOG) and Texture Moments, with the Random Forest machine learning algorithm. The research process encompasses four key stages: pre-processing, feature extraction, classification, and system evaluation, where the accuracy of individual and combined feature extraction methods is analyzed. Experimental results reveal that the HOG method achieves an accuracy of 78.99%, while the Texture Moments method yields 81.88%. Notably, the combination of these two methods enhances system performance, achieving the highest accuracy of 86.23%, representing a 4.65% improvement over the single methods. These findings underscore the efficacy of integrating HOG and Texture Moments with the Random Forest algorithm for automated batik pattern recognition.

Investigation of acoustic and visual features for pig cough classification

Vehicle classification is vital to an intelligent transport system. To obtain a high accuracy, it is the most crucial process to extract reliable and distinguishable features of vehicles. A feature extraction method using a lightweight convolutional network for vehicle classification is proposed. The main contributions are threefold: (1) a lightweight network named LWNet with two convolution layers is proposed to extract the features of the vehicles; (2) Hu moment is integrated with spatial location information to improve its own describing and distinguishing ability; and (3) histogram of oriented gradient (HOG) feature is extracted from the complete image, and then the above two kinds of features are combined with HOG to form the vector. And then, a support vector machine is trained to obtain the classification model. Vehicles are classified into six categories, i.e., large bus, car, motorcycle, minibus, truck, and van. The experimental results have demonstrated that the classification accuracy can achieve 97.39%, which is 3.81% higher than that obtained from the conventional methods. In addition, for this vehicle classification task, the proposed lightweight convolutional network can achieve comparable or even higher performance compared to the deep convolutional neural networks, while the proposed method does not need the support of a graphics processing unit and has much lower complexity without the training process.

Face recognition is efficiently used in computer vision, pattern recognition, biometric, law enforcement, surveillance, criminal investigations, and missing person detection. However, face recognition is still a challenging task under variant illuminations, pose, expression, occlusion, and background. In this paper, we proposed a cascading of histogram of oriented gradients (HOG) and local binary pattern (LBP) feature extraction method on ORL face dataset, which can improve recognition rates while also addressing pose, scale, expression, and variant illumination issues. The facial recognition network was trained using various classifiers such as with KNN, SVM, and random forest (RF). The results have been shown that the accuracy rate of the combined LBP and HOG feature extraction method is better than individual LBP or HOG features for ORL database face recognition.

Research in automated object detection has mainly addressed detection in 2-D intensity images. The best performing systems exhibit a high degree of robustness to variation in object scale, rotation and viewpoint. Depending on the context of the detection task, rotation and viewpoint can be controlled for, but estimating object scale is usually not possible without additional sensing apparatus. Objects must be searched for at all scales where they are likely to be present. Range sensors allow for direct distance measurements to be taken and the generation of range maps or point clouds that when co-registered against standard 2-D visual images create 3-D images. Knowledge of depth obviates the need to search over the entire scale space for an object, but this also allows for the object's scale itself to be incorporated into the detection scheme. Most existing object detection schemes use range only to constrain the detection search space or to discard detections that do not match the expected object scale. This paper presents a novel feature extraction and detection method that calculates scale proportionate histograms of oriented gradients (Pro-HOG) by exploiting known depth in an image. Pro-HOG is evaluated against a reference implementation of the original histograms of oriented gradients (HOG) feature extractor for detection of images of cars in the PASCAL Visual Object Classes 2007 dataset. High quality detection results are achieved on the real world Earthmine dataset using a Pro-HOG feature detector trained with the PASCAL VOC 2007 dataset. It is demonstrated that Pro-HOG's detection accuracy is comparable to HOG but at much reduced computational overhead.

Palmprints have been broadly used for personal authentication because they are highly accurate and incur low cost. Most previous works have focused on two-dimensional (2-D) palmprint recognition in the past decade. Unfortunately, 2-D palmprint recognition systems lose the shape information when capturing palmprint images. Moreover, such 2-D palmprint images can be easily forged or affected by noise. Hence, three-dimensional (3-D) palmprint recognition has been regarded as a promising way to further improve the performance of palmprint recognition systems. We have developed a simple, but efficient method for 3-D palmprint recognition by using local features. We first utilize shape index representation to describe the geometry of local regions in 3-D palmprint data. Then, we extract local binary pattern and Gabor wavelet features from the shape index image. The two types of complementary features are finally fused at a score level for further improvements. The experimental results on the Hong Kong Polytechnic 3-D palmprint database, which contains 8000 samples from 400 palms, illustrate the effectiveness of the proposed method.

Grantha script, which was used for writing sacred texts in Sanskrit language. Grantha script contains valuable information, but these historical document images suffer from noises present in the original document due to its degradation, faint ink strokes, unwanted impurities, background images, bleed through, aging of the palm leaves and so on. It includes handwritten characters and also it is an extinct language. The incentive behind this research work include presenting a novel recognition system for modern Grantha script characters and also confirming the link between Malayalam and Grantha script. After pre-processing the input image, universe of discourse is selected. Feature extraction plays a vital role in the proposed recognition process. The proposed method uses HOOSC (Histogram of Orientation Shape Context) feature extraction, which is new in character recognition, but used in some other area and ANN (Artificial Neural Network) for classification. Feature extraction methods which are used for other languages and that can be used in Grantha script like HOG (Histogram of Oriented Gradients), Gabor features, Zoning, and Invariant Moments provides classification accuracy of 84%, 76.3%, 76%, and 52% respectively. The recognized characters are mapped to corresponding Malayalam characters, and proposed method provides an accuracy of about 96.5%.

Handwritten character recognition techniques are quickly developed during past years. In this paper, we summarize both feature extraction and classification recognition methods of off-line handwritten characters recognition. The feature extraction methods mainly include two classes: statistic features and structure features, and the classification methods usually covers pattern matching, statistical classifier, neural network classifier, etc. These techniques are analyzed and comprised, and the technology trends of handwritten character recognition are also discussed.

An accurate diagnosis is significant for the treatment of any disease in its early stage. Content-Based Medical Image Retrieval (CBMIR) is used to find similar medical images in a huge database to help radiologists in diagnosis. The main difficulty in CBMIR is semantic gaps between the lower-level visual details, captured by computer-aided tools and higher-level semantic details captured by humans. Many existing methods such as Manhattan Distance, Triplet Deep Hashing, and Transfer Learning techniques for CBMIR were developed but showed lower efficiency and the computational cost was high. To solve such issues, a new feature extraction approach is proposed using Histogram of Gradient (HoG) with Local Ternary Pattern (LTP) to automatically retrieve medical images from the Contrast-Enhanced Magnetic Resonance Imaging (CE-MRI) database. Adam optimization algorithm is utilized to select features and the Euclidean measure calculates the similarity for query images. From the experimental analysis, it is clearly showing that the proposed HoG-LTP method achieves higher accuracy of 98.8%, a sensitivity of 98.5%, and a specificity of 99.416%, which is better when compared to the existing Random Forest (RF) method which displayed an accuracy, sensitivity, and specificity of 81.1%, 81.7% and 90.5% respectively.

So far, there exist many publicly available palmprint databases. However, not all of them have provided the corresponding region of interest (ROI) images. If everyone uses their own extracted ROI images for performance testing, the final accuracy is not strictly comparable. Since ROI localization is the critical stage of palmprint recognition. The location precision has a significant impact on the final recognition accuracy, especially in unconstrained scenarios. This problem has limited the applications of palmprint recognition. However, many currently published surveys only focus on feature extraction and classification methods. Throughout these years, many new ROI localization methods have been proposed. In this chapter, we will group the existing ROI localization methods into different categories, analyze their basic ideas, reproduce some of the codes, make comparisons of their performances, and provide further directions. We hope this could be a useful reference for further research.

To address the low accuracy problem of playground detection under complex background, the accurate playground localization based on multi-feature extraction and cascade classifier is proposed in this paper. It is difficult to utilize this information to separate objects from the complex background. Therefore, we adopt multi-feature extraction method to make the playgrounds more easily to be detected. The proposed localization method is partitioned into two modules: feature extraction and classification. First, multi feature extraction method combining histogram of oriented gradients (HOG) and Haar is utilized to extract features from raw images. HOG can authentically capture the shape information, which is extracted to characterize the local region. Haar can improve the image eigenvalue calculation effectively. Afterwards, cascade classifier based on AdaBoost algorithm is adopted to classify the extracted features. Finally we conduct the experiments with our proposed methodology on a publicly accessible remote sensing images from Google Earth. The results demonstrate that the proposed framework has a better effect with achieving high levels of recall, precision and F-score compared to the state-of-the-art alternatives, without sacrificing computational soundness. What is more, the results indicate that the proposed playground 1ocalisation method has strong robustness under different complex backgrounds with high detection rate.

Because of high dimensionality, correlation among covariates, and noise contained in data, dimension reduction (DR) techniques are often employed to the application of machine learning algorithms. Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and their kernel variants (KPCA, KLDA) are among the most popular DR methods. Recently, Supervised Kernel Principal Component Analysis (SKPCA) has been shown as another successful alternative. In this paper, brief reviews of these popular techniques are presented first. We then conduct a comparative performance study based on three simulated datasets, after which the performance of the techniques are evaluated through application to a pattern recognition problem in face image analysis. The gender classification problem is considered on MORPH-II and FG-NET, two popular longitudinal face aging databases. Several feature extraction methods are used, including biologically-inspired features (BIF), local binary patterns (LBP), histogram of oriented gradients (HOG), and the Active Appearance Model (AAM). After applications of DR methods, a linear support vector machine (SVM) is deployed with gender classification accuracy rates exceeding 95% on MORPH-II, competitive with benchmark results. A parallel computational approach is also proposed, attaining faster processing speeds and similar recognition rates on MORPH-II. Our computational approach can be applied to practical gender classification systems and generalized to other face analysis tasks, such as race classification and age prediction.