Speeded Up Robust Features Research Articles

Hybrid Bag-of-Visual-Words and FeatureWiz Selection for Content-Based Visual Information Retrieval.

Recently, content-based image retrieval (CBIR) based on bag-of-visual-words (BoVW) model has been one of the most promising and increasingly active research areas. In this paper, we propose a new CBIR framework based on the visual words fusion of multiple feature descriptors to achieve an improved retrieval performance, where interest points are separately extracted from an image using features from accelerated segment test (FAST) and speeded-up robust features (SURF). The extracted keypoints are then fused together in a single keypoint feature vector and the improved RootSIFT algorithm is applied to describe the region surrounding each keypoint. Afterward, the FeatureWiz algorithm is employed to reduce features and select the best features for the BoVW learning model. To create the codebook, K-means clustering is applied to quantize visual features into a smaller set of visual words. Finally, the feature vectors extracted from the BoVW model are fed into a support vector machines (SVMs) classifier for image retrieval. An inverted index technique based on cosine distance metric is applied to sort the retrieved images to the similarity of the query image. Experiments on three benchmark datasets (Corel-1000, Caltech-10 and Oxford Flower-17) show that the presented CBIR technique can deliver comparable results to other state-of-the-art techniques, by achieving average accuracies of 92.94%, 98.40% and 84.94% on these datasets, respectively.

Offline signature verification using long short-term memory and histogram orientation gradient

The signing process is a critical step that organizations take to ensure the confidentiality of their data and to safeguard it against unauthorized penetration or access. Within the last decade, offline handwritten signature research has grown in popularity as a common method for human authentication via biometric features. It is not an easy task, despite the importance of this method; the struggle in such a system stem from the inability of any individual to sign the same signature each and every time. Additionally, we are indeed interested in the dataset’s features that could affect the model's performance; thus, from extracted features from the signature images using the histogram orientation gradient (HOG) technique. In this paper, we suggested a long short-term memory (LSTM) neural network model for signature verification, with input data from the USTig and CEDAR datasets. Our model’s predictive ability is quite outstanding: The classification accuracy efficiency LSTM for USTig was 92.4% with a run-time of 1.67 seconds and 87.7% for CEDAR with a run-time of 2.98 seconds. Our proposed method outperforms other offline signature verification approaches such as K-nearest neighbour (KNN), support vector machine (SVM), convolution neural network (CNN), speeded-up robust features (SURF), and Harris in terms of accuracy.

An FPGA-Based General-Purpose Feature Detection Algorithm for Space Applications

Spacecraft takes images for applications/missions like attitude determination, astronomy, and space situational awareness. Feature detection is a primary operation in vision-based processing systems. Although different feature detection algorithms are used for specific purposes, they need to achieve invariance by scaling, rotation, and other interference, and output robust results. This article develops a general-purpose feature detection hardware architecture based on the speeded-up robust features (SURF) algorithm. On the other hand, the efficiency of the algorithm can affect the overall system performance to a large extent, especially in real-time operations. This article presents an field-programmable gate array (FPGA)-based implementation of a modified SURF algorithm. The advantages of FPGAs including parallel and pipelining, fixed-point arithmetic, and bitwise operations are fully applied to improve the performance and efficiency of the system in terms of power consumption, and resource utilization.

A reliable matching algorithm for heterogeneous remote sensing images considering the spatial distribution of matched features

ABSTRACT Owing to the differences in sensor types,resolutions, and imaging conditions of heterologous remote sensing images, thematching results of remote sensing images, such as low accuracy, few matched pairs,and low distribution quality, are not ideal, which makes precise registrationbetween heterogeneous images difficult. To mitigate this, we propose a reliablematching algorithm for heterogeneous remote sensing images that considers thespatial distribution of the matched features. First, feature-based matchingalgorithms such as the scale-invariant feature transform (SIFT) algorithm orthe speeded-up robust features algorithm are used to match images to obtain aninitial set of matched pairs and a set of candidate features. Then, accordingto the stability of the spatial distribution of locally correctly matchedfeatures, the distance and angular proximity between matched features and theirneighbours are calculated to obtain the accuracy of the matched pairs and removeincorrectly matched pairs. Finally, the random sample consensus (RANSAC)algorithm was used to fit the transformation model between images, and thefinal matched feature selection algorithm and automatic transformation erroralgorithm were used to detect candidate features to increase the number ofmatched pairs. Experimental analysis of heterogeneous multiscale andmultitemporal optical remote sensing images demonstrates the superiorcapability of the proposed algorithm over commonly used algorithms, includingSIFT, RANSAC, locality preserving matching, learning a two-class classifier formismatch removal, and linear adaptive filtering algorithms. In particular, whenthe precision of the initially matched pair is low, the proposed algorithm canachieve excellent results.

Comparative Analysis of CNN Models and Bayesian Optimization-Based Machine Learning Algorithms in Leaf Type Classification

In this study, the leaves are classified by various Machine Learning (ML) and Deep Learning (DL) based Convolutional Neural Networks (CNN) methods. In the proposed method, first, image pre-processing is performed to increase the accuracy of the posterior process. The obtained image is a grayscale image without noise as a result of the pre-processing. These preprocessed images are used in classification with ML and DL. The Speeded Up Robust Features (SURF) are extracted from the grayscale image for ML-based learning. The features are restructured as visual words using the Bag of Visual Words (BoVW) method. Then, histograms are generated for each image according to the frequency of the visual word. Those histograms represent the new feature data. The histogram features are classified by four different ML methods, Decision Tree (DT), k-Nearest Neighbor (KNN), Naive Bayes (NB) and Support Vector Machine (SVM). Before using the ML methods, Bayesian Optimization (BO) method, which is one of the Hyperparameter Optimization (HO) algorithms, is applied to determine hyperparameters. In the classification process performed with four different ML algorithms, the best accuracy is achieved with the KNN algorithm as 98.09%. Resnet18, ResNet50, MobileNet, GoogLeNet, DenseNet, which are state-of-the-art CNN architectures, are used for DL-based learning. CNN models have higher accuracy than ML algorithms.

BOSF-SVM: A thermal image-based fault diagnosis method of circuit boards

In recent years, the lack of thermal images and the difficulty of thermal feature extraction have led to low accuracy and efficiency in the fault diagnosis of circuit boards using thermal images. To address the problem, this paper presents a simple and efficient intelligent fault diagnosis method combined with computer vision, namely the bag-of-SURF-features support vector machine (BOSF-SVM). Firstly, an improved BOF feature extraction based on SURF is proposed. The preliminary fault features of the abnormally hot components are extracted by the speeded-up robust features algorithm (SURF). In order to extract the ultimate fault features, the preliminary fault features are clustered into K clusters by K-means and substituted into the bag-of-features model (BOF) to generate a bag-of-SURF-feature vector (BOSF) for each image. Then, all of the BOSF vectors are fed into SVM to train the fault classification model. Finally, extensive experiments are conducted on two homemade thermal image datasets of circuit board faults. Experimental results show that the proposed method is effective in extracting the thermal fault features of components and reducing misdiagnosis and underdiagnosis. Also, it is economical and fast, facilitating savings in labour costs and computing resources in industrial production.

A Framework for Using UAVs to Detect Pavement Damage Based on Optimal Path Planning and Image Splicing

In order to investigate the use of unmanned aerial vehicles (UAVs) for future application in road damage detection and to provide a theoretical and technical basis for UAV road damage detection, this paper determined the recommended flight and camera parameters based on the needs of continuous road image capture and pavement disease recognition. Furthermore, to realize automatic route planning and control, continuous photography control, and image stitching and smoothing tasks, a UAV control framework for road damage detection, based on the Dijkstra algorithm, the speeded-up robust features (SURF) algorithm, the random sampling consistency (RANSAC) algorithm, and the gradual in and out weight fusion method, was also proposed in this paper. With the Canny operator, it was verified that the road stitched long image obtained by the UAV control method proposed in this paper is applicable to machine learning pavement disease identification.

Extraction of 3D distribution of potato plant CWSI based on thermal infrared image and binocular stereovision system.

As the largest component of crops, water has an important impact on the growth and development of crops. Timely, rapid, continuous, and non-destructive detection of crop water stress status is crucial for crop water-saving irrigation, production, and breeding. Indices based on leaf or canopy temperature acquired by thermal imaging are widely used for crop water stress diagnosis. However, most studies fail to achieve high-throughput, continuous water stress detection and mostly focus on two-dimension measurements. This study developed a low-cost three-dimension (3D) motion robotic system, which is equipped with a designed 3D imaging system to automatically collect potato plant data, including thermal and binocular RGB data. A method is developed to obtain 3D plant fusion point cloud with depth, temperature, and RGB color information using the acquired thermal and binocular RGB data. Firstly, the developed system is used to automatically collect the data of the potato plants in the scene. Secondly, the collected data was processed, and the green canopy was extracted from the color image, which is convenient for the speeded-up robust features algorithm to detect more effective matching features. Photogrammetry combined with structural similarity index was applied to calculate the optimal homography transform matrix between thermal and color images and used for image registration. Thirdly, based on the registration of the two images, 3D reconstruction was carried out using binocular stereo vision technology to generate the original 3D point cloud with temperature information. The original 3D point cloud data were further processed through canopy extraction, denoising, and k-means based temperature clustering steps to optimize the data. Finally, the crop water stress index (CWSI) of each point and average CWSI in the canopy were calculated, and its daily variation and influencing factors were analyzed in combination with environmental parameters. The developed system and the proposed method can effectively detect the water stress status of potato plants in 3D, which can provide support for analyzing the differences in the three-dimensional distribution and spatial and temporal variation patterns of CWSI in potato.

Point Cloud Plane Segmentation-Based Robust Image Matching for Camera Pose Estimation

The mainstream image matching method for recovering the motion of the camera is based on local feature matching, which faces the challenges of rotation, illumination, and the presence of dynamic objects. In addition, local feature matching relies on the distance between descriptors, which easily leads to lots of mismatches. In this paper, we propose a new robust image matching method for camera pose estimation, called IM_CPE. It is a novel descriptor matching method combined with 3-D point clouds for image matching. Specifically, we propose to extract feature points based on a pair of matched point cloud planes, which are generated and segmented based on depth images. Then, the feature points are matched based on the distance between their corresponding 3-D points on the point cloud planes and the distance between their descriptors. Moreover, the robustness of the matching can be guaranteed by the centroid distance of the matched point cloud planes. We evaluate the performance of IM_CPE using four well-known key point extraction algorithms, namely Scale-Invariant Feature Transform (SIFT), Speed Up Robust Feature (SURF), Features from Accelerated Segment Test (FAST), and Oriented FAST and Rotated Brief (ORB), with four sequences from the TUM RGBD dataset. According to the experimental results, compared to the original SIFT, SURF, FAST, and ORB algorithms, the NN_mAP performance of the four key point algorithms has been improved by 11.25%, 13.98%, 16.63%, and 10.53% on average, respectively, and the M.Score has also been improved by 25.15%, 23.05%, 22.28%, and 11.05% on average, respectively. The results show that the IM_CPE can be combined with the existing key points extraction algorithms and the IM_CPE can significantly improve the performance of these key points algorithms.

Improved FAST algorithm for non-uniform rotational distortion correction in OCT endoscopic imaging.

Optical Coherence Tomography (OCT) is widely used for endoscopic imaging in endoluminal organs because of its high imaging accuracy and resolution. However, OCT endoscopic imaging suffers from Non-Uniform Rotational Distortion (NURD), which can be caused by many factors, such as irregular motor rotation and changes in friction between the probe and the sheath. Correcting this distortion is essential to obtaining high-quality Optical Coherence Tomography Angiography (OCTA) images. There are two main approaches for correcting NURD: hardware-based methods and algorithm-based methods. Hardware-based methods can be costly, challenging to implement, and may not eliminate NURD. Algorithm-based methods, such as image registration, can be effective for correcting NURD but can also be prone to the problem of NURD propagation. To address this issue, we process frames by coarse and fine registration, respectively. The new reference frame is generated by filtering out the A-scan that may have the NURD problem by coarse registration. And the fine registration uses this frame to achieve the final NURD correction. In addition, we have improved the Features from Accelerated Segment Test (FAST) algorithm and put it into coarse and fine registration process. Four evaluation functions were used for the experimental results, including signal-to-noise ratio (SNR), peak signal-to-noise ratio (PSNR), mean squared error (MSE), and structural similarity index measure (SSIM). By comparing with Scale-invariant feature transform (SIFT), Speeded up robust features (SURF), Oriented FAST and Rotated BRIEF (ORB), intensity-based (Cross-correlation), and Optical Flow algorithms, our algorithm has a higher similarity between the corrected frames. Moreover, the noise in the OCTA data is better suppressed, and the vascular information is well preserved. Our image registration-based algorithm reduces the problem of NURD propagation between B-scan frames and improves the imaging quality of OCT endoscopic images.

Image Registration Algorithm for Remote Sensing Images Based on Pixel Location Information

Registration between remote sensing images has been a research focus in the field of remote sensing image processing. Most of the existing image registration algorithms applied to feature point matching are derived from image feature extraction methods, such as scale-invariant feature transform (SIFT), speed-up robust features (SURF) and Siamese neural network. Such methods encounter difficulties in achieving accurate image registration where there is a large bias in the image features or no significant feature points. Aiming to solve this problem, this paper proposes an algorithm for multi-source image registration based on geographical location information (GLI). By calculating the geographic location information that corresponds to the pixel in the image, the ideal projected pixel position of the corresponding image is obtained using spatial coordinate transformation. Additionally, the corresponding relationship between the two images is calculated by combining multiple sets of registration points. The simulation experiment illustrates that, under selected common simulation parameters, the average value of the relative registration-point error between the two images is 12.64 pixels, and the registration accuracy of the corresponding ground registration point is higher than 6.5 m. In the registration experiment involving remote sensing images from different sources, the average registration pixel error of this algorithm is 20.92 pixels, and the registration error of the image center is 21.24 pixels. In comparison, the image center registration error given by the convolutional neural network (CNN) is 142.35 pixels after the registration error is manually eliminated. For the registration of homologous and featureless remote sensing images, the SIFT algorithm can only offer one set of registration points for the correct region, and the neural network cannot achieve accurate registration results. The registration accuracy of the presented algorithm is 7.2 pixels, corresponding to a ground registration accuracy of 4.32 m and achieving more accurate registration between featureless images.

Proposing a hybrid technique of feature fusion and convolutional neural network for melanoma skin cancer detection

Skin cancer is among the most common cancer types worldwide. Automatic identification of skin cancer is complicated because of the poor contrast and apparent resemblance between skin and lesions. The rate of human death can be significantly reduced if melanoma skin cancer could be detected quickly using dermoscopy images. This research uses an anisotropic diffusion filtering method on dermoscopy images to remove multiplicative speckle noise. To do this, the fast-bounding box (FBB) method is applied here to segment the skin cancer region. We also employ 2 feature extractors to represent images. The first one is the Hybrid Feature Extractor (HFE), and second one is the convolutional neural network VGG19-based CNN. The HFE combines 3 feature extraction approaches namely, Histogram-Oriented Gradient (HOG), Local Binary Pattern (LBP), and Speed Up Robust Feature (SURF) into a single fused feature vector. The CNN method is also used to extract additional features from test and training datasets. This 2-feature vector is then fused to design the classification model. The proposed method is then employed on 2 datasets namely, ISIC 2017 and the academic torrents dataset. Our proposed method achieves 99.85%, 91.65%, and 95.70% in terms of accuracy, sensitivity, and specificity, respectively, making it more successful than previously proposed machine learning algorithms.

Automatic Detection and Classification of Insects Using Hybrid FF-GWO-CNN Algorithm

Pest detection in agricultural crop fields is the most challenging task, so an effective pest detection technique is required to detect insects automatically. Image processing techniques are widely preferred in agricultural science because they offer multiple advantages like maximal crop protection, improved crop management and productivity. On the other hand, developing the automatic pest monitoring system dramatically reduces the workforce and errors. Existing image processing approaches are limited due to the disadvantages like poor efficiency and less accuracy. Therefore, a successful image processing technique based on FF-GWO-CNN classification algorithm is introduced for effective pest monitoring and detection. The four-step image processing technique begins with image pre-processing, removing the insect image’s noise and sunlight illumination by utilizing an adaptive median filter. The insects’ size and shape are identified using the Expectation Maximization Algorithm (EMA) based clustering technique, which involves not only clustering the data but also uncovering the correlations by visualizing the global shape of an image. Speeded up robust feature (SURF) method is employed to select the best possible image features. Eventually, the image with best features is classified by introducing a hybrid FF-GWO-CNN algorithm, which combines the benefits of Firefly (FF), Grey Wolf Optimization (GWO) and Convolutional Neural Network (CNN) classification algorithm for enhancing the classification accuracy. The entire work is executed in MATLAB simulation software. The test result reveals that the suggested technique has delivered optimal performance with high accuracy of 97.5%, precision of 94%, recall of 92% and F-score value of 92%.

Towards the development of obstacle detection in railway tracks using thermal imaging

To prevent collisions between trains and objects on the railway line, rugged trains require an intelligent rail protection system. To improve railway safety and reduce the number of accidents, studies are underway. Machine learning (ML) had progressed rapidly, creating new perspectives on the subject. A technique called speed up robust features (SURF) is proposed by researchers to collect regionally and globally relevant information. In addition, taking advantage of the Ohio State University (OSU) heat walker benchmarking dataset, the effectiveness of this technique was examined under various lighting scenarios. This technology could help in reducing train accident rates and financial costs. The findings of the proposed methodology are very specific, in addition to the ability to quickly identify items (obstacles) on the railway line, both of which contribute to rail security. The proposed faster region based convolutional neural network (FR-CNN) with 2D singular spectrum analysis (SSA) improves the performance analysis of an accuracy of 90.2%, recall 95.6% and precision 94.6% when compared with an existing system YOLOv2 and YOLOv5 with 2D SSA.

Generating 3D Multispectral Point Clouds of Plants with Fusion of Snapshot Spectral and RGB-D Images.

Accurate and high-throughput plant phenotyping is important for accelerating crop breeding. Spectral imaging that can acquire both spectral and spatial information of plants related to structural, biochemical, and physiological traits becomes one of the popular phenotyping techniques. However, close-range spectral imaging of plants could be highly affected by the complex plant structure and illumination conditions, which becomes one of the main challenges for close-range plant phenotyping. In this study, we proposed a new method for generating high-quality plant 3-dimensional multispectral point clouds. Speeded-Up Robust Features and Demons was used for fusing depth and snapshot spectral images acquired at close range. A reflectance correction method for plant spectral images based on hemisphere references combined with artificial neural network was developed for eliminating the illumination effects. The proposed Speeded-Up Robust Features and Demons achieved an average structural similarity index measure of 0.931, outperforming the classic approaches with an average structural similarity index measure of 0.889 in RGB and snapshot spectral image registration. The distribution of digital number values of the references at different positions and orientations was simulated using artificial neural network with the determination coefficient (R 2) of 0.962 and root mean squared error of 0.036. Compared with the ground truth measured by ASD spectrometer, the average root mean squared error of the reflectance spectra before and after reflectance correction at different leaf positions decreased by 78.0%. For the same leaf position, the average Euclidean distances between the multiview reflectance spectra decreased by 60.7%. Our results indicate that the proposed method achieves a good performance in generating plant 3-dimensional multispectral point clouds, which is promising for close-range plant phenotyping.

Satellite image matching and registration using affine transformation and hybrid feature descriptors

Image registration (IR) is an image processing technique to determine geometrical transformation that gives the most accurate match between reference and floating images. In existing IR work, the inliers ratio and outlier's ratios are equal. This reduces the image registration accuracy. So, to avoid the outlier's ratio and increase the inliers ratio, hybrid invariant local features descriptor is proposed. This feature descriptor consists of binary-robust-invariant-scalable-key point (BRISK), speed-up-robust-feature (SURF), and feature from accelerated segment test feature (FAST). The hybrid feature descriptor extracts the relevant features from the image. Then, the feature matching step finds the correct correspondences from the two sets of features. Also, affine transformation avoids the false feature matching points. An experimental analysis shows the inliers ratio and repeatability evaluation metrics performance of individual feature descriptor, combined feature descriptor and proposed feature descriptor. The proposed hybrid feature descriptor achieves inliers ratio of 1.913 and repeatability is 0.121.

Static Pakistani Sign Language Classification using Support Vector Machine

In this study, a system is proposed that uses the Support Vector Machine (SVM) technique with Bag-of-Words (BoW) and recognizes static Pakistani Sign Language (PSL) alphabets. The application of the BoW technique with SVM, on a PSL images' dataset, has not been performed previously. Similarly, no publicly available dataset for PSL is available and previous studies have achieved a maximum classification accuracy of 91.98%. For this study, a total of 511 images are collected for 36 static PSL alphabet signs from a native signer. The Sign Language (SL) recognition system uses the collected images as input and converts them to grayscale. To segment the images, the system uses the thresholding technique and Speeded Up Robust Feature (SURF) to extract the features. The system uses K-means clustering to cluster the extracted features. To form the BoW, the system computes the Euclidean distance among SURF descriptors and clustered data. The system then uses 5-fold cross-validation to divide the codebooks obtained from the BoW into training and testing. The developed system yields an overall accuracy of 97.87% for the classification of static PSL signs at 1,500×1,500 image dimensions and 500 Bags.

Improved SURF method in digital image correlation for estimation of large rotation angle

Digital image correlation (DIC) is widely used in optical measurement techniques with the advantages of high precision, robustness and expansibility. The conventional DIC, however, is highly dependent on the accuracy of initial parameters, and there are reports [1,2] that it may fail when the rotation angle of the target specimen exceeds 7°. The combination of Speeded-Up Robust Features (SURF) with Random Sample Consensus (RANSAC) algorithm has been applied to solve this problem with limited success due to the effects of residual mismatches. An enhanced algorithm based on SURF is proposed in this study to address this problem. The transformation model between two images is obtained by RANSAC similar to existing methods. Then an angle compensation strategy is proposed to estimate the rotation angle of the deformed image to form the compensated image. Finally, an iterative process is proposed to refine the initial parameters from the reference and deformed images with a new convergence threshold. In addition, an evaluation criterion developed from a multiple ring template is proposed to compute the similarity of feature point pairs to improve the speed of convergence and sampling accuracy. Results from numerical simulation and experimental analysis show that the accuracy and robustness of the proposed method are significantly improved. Further application of the proposed method to monitor the rotating blades of a scaled model wind turbine illustrates further the capability of the proposed method.

The Concept of Big Data Management with Various Transportation Systems Sources as a Key Role in Smart Cities Development

An increasing number of devices and their communication with each other generates huge amounts of data. The efficiency of processing such large and heterogeneous data is crucial for extracting the reliable and consistent information that is needed for the effective management of smart cities within the field of transport. Data heterogeneity and volume as well as its integration and analytics are big challenges for decision-makers. The development of urban agglomerations is largely dependent on the proper management of such data. Therefore, this paper explores the role of these data repositories, their acquisition from different sources, and the ways to combine them. The main goal of this paper is to propose a concept of Smart City management based on Big Data Analytics and technology related to UAVs (Unmanned Aerial Vehicle) which may reduce costs and resource consumption. The presented concept includes successive data generation and collection, data type identification, problem and requirement identification, filtering, classification, pre-processing, and data optimization, as well as decision support analysis. A key part of this analysis utilizes computer algorithms, such as Speeded Up Robust Features (SURF) and Thresholding and Blob detection, to develop a multi-camera image recognition system for freight transport management and logistics in smart cities. The objective is to design a system that optimizes the route planning and time of vehicle passage on selected road sections, ultimately leading to the reduction of emissions. During the study, data obtained from multiple sources were compared, and the analysis uncovered different results for the same assumptions. We discuss the reasons for these variances. Overall, the results obtained in the analysis indicated that it is necessary to correct the predictions of the multi-camera image recognition system with additional methods and algorithms.

Vision-based Pakistani sign language recognition using bag-of-words and support vector machines

In order to perform their daily activities, a person is required to communicating with others. This can be a major obstacle for the deaf population of the world, who communicate using sign languages (SL). Pakistani Sign Language (PSL) is used by more than 250,000 deaf Pakistanis. Developing a SL recognition system would greatly facilitate these people. This study aimed to collect data of static and dynamic PSL alphabets and to develop a vision-based system for their recognition using Bag-of-Words (BoW) and Support Vector Machine (SVM) techniques. A total of 5120 images for 36 static PSL alphabet signs and 353 videos with 45,224 frames for 3 dynamic PSL alphabet signs were collected from 10 native signers of PSL. The developed system used the collected data as input, resized the data to various scales and converted the RGB images into grayscale. The resized grayscale images were segmented using Thresholding technique and features were extracted using Speeded Up Robust Feature (SURF). The obtained SURF descriptors were clustered using K-means clustering. A BoW was obtained by computing the Euclidean distance between the SURF descriptors and the clustered data. The codebooks were divided into training and testing using fivefold cross validation. The highest overall classification accuracy for static PSL signs was 97.80% at 750 × 750 image dimensions and 500 Bags. For dynamic PSL signs a 96.53% accuracy was obtained at 480 × 270 video resolution and 200 Bags.