Moving Object Detection and Tracking using Genetic Algorithm Enabled Extreme Learning Machine

Communication is the ultimate of man’s search for conveying his ideas, emotions, and concepts. Dance is one of the media of communication through which dancers share notion of feelings, with the spectators through gestures, i.e., mudra. Gesture recognition propagates a concept without verbal speech or listening, and in dance recognition, the notion is transferred through various dance poses and actions. This activity in a way really paves way to enhance Indian Sign Language. This study focuses to solve the mudra resemblance in Bharatanatyam through a new system developed with image processing and classification technique using histogram of oriented gradient (HOG) feature extraction techniques and support vector machine (SVM) classifier. SVM classifies the features of HOG into mudras as text labels. Popular feature vectors such as scale-invariant feature transform (SIFT), speed up robust feature (SURF), and local binary pattern (LBP) are hardened against HOG for accuracy and speediness, and this innovative proposed concept is useful for online dance learners.

This research presents a method for human detection at night in video surveillance camera. The process of detecting human at night is very challenging due to certain factors such as radiance, silhouette and low external light. A comparative study between three texture features that are Discrete Wavelet Transform (DWT), Histogram of Oriented Gradient (HOG) and Speeded Up Robust Feature (SURF) using Support Vector Machine (SVM), Naive Bayes and Adaboost classifiers are investigated using primary data extracted from a video surveillance camera at the faculty. The results show that HOG feature with Naive Bayes detect human in video surveillance better compared to DWT and SURF with SVM and AdaBoost classifiers.

Due to the advancements in digital technologies and social networking, image collections are growing exponentially. The important aim in content-based image retrieval (CBIR) is to reduce the semantic gap issue that improves the performance of image retrieval. In this paper, the objective is achieved by introducing effective visual words fusion technique based on speeded-up robust features (SURF) and histograms of oriented gradients (HOG) feature descriptors. HOG is used to extract global features, whereas SURF is used for the extraction of local features. Global features are preferred for large-scale image retrieval, whereas local features perform better on those systems that support semantic queries with close visual appearance. Moreover, SURF is scale and rotation-invariant as compared to HOG descriptor and it works better for low illumination. On the contrary, HOG performs better for scene-recognition- or activity-recognition-based applications. In the proposed technique, visual words fusion of SURF and HOG feature descriptors is carried which performed better than features fusion of SURF and HOG feature descriptors as well as state-of-the-art CBIR techniques. The proposed technique based on visual words fusion gives classification accuracy of 98.40% using support vector machine while image retrieval accuracy of 80.61%. Qualitative and quantitative analyses performed on four standard image collections namely, Corel-1000, Corel-1500, Corel-5000, and Caltech-256 demonstrate the effectiveness of the proposed technique based on visual words fusion of SURF and HOG feature descriptors.

Human action recognition from 2D videos is a demanding area due to its broad applications. Many methods have been proposed by the researchers for recognizing human actions. The improved accuracy in identifying human actions is desirable. This paper presents an improved method of human action recognition using support vector machine (SVM) classifier. This paper proposes a novel feature descriptor constructed by fusing the various investigated features. The handcrafted features such as scale invariant feature transform (SIFT) features, speed up robust features (SURF), histogram of oriented gradient (HOG) features and local binary pattern (LBP) features are obtained on online 2D action videos. The proposed method is tested on different action datasets having both static and dynamically varying backgrounds. The proposed method achieves shows best recognition rates on both static and dynamically varying backgrounds. The datasets considered for the experimentation are KTH, Weizmann, UCF101, UCF sports actions, MSR action and HMDB51.The performance of the proposed feature fusion model with SVM classifier is compared with the individual features with SVM. The fusion method showed best results. The efficiency of the classifier is also tested by comparing with the other state of the art classifiers such as k-nearest neighbors (KNN), artificial neural network (ANN) and Adaboost classifier. The method achieved an average of 94.41% recognition rate.

Feature description is a critical task in Augmented Reality Tracking. This article introduces a Convex Based Feature Descriptor (CBFD) system designed to withstand rotation, lighting, and blur variations while remaining computationally efficient. We have developed two filters capable of computing pixel intensity variations, followed by the covariance matrix of the polynomial to describe the features. The superiority of CBFD is validated through precision, recall, computation time, and feature location distance. Additionally, we provide a solution to determine the optimal block size for describing nonlinear regions, thereby enhancing resolution. The results demonstrate that CBFD achieves a average precision of 0.97 for the test image, outperforming Superpoint, Directional Intensified Tertiary Filtering (DITF), Binary Robust Independent Elementary Features (BRIEF), Binary Robust Invariant Scalable Keypoints (BRISK), Speeded Up Robust Features (SURF), and Scale Invariant Feature Transform (SIFT), which achieve scores of 0.95, 0.92, 0.72, 0.66, 0.63 and 0.50 respectively. Noteworthy is CBFD's recall value of 0.87 representing at the maximum of a 13.6% improvement over Superpoint, DITF, BRIEF, BRISK, SURF, and SIFT. Furthermore, the matching score for the test image is 0.975. The computation time for CBFD is 2.8 ms, which is at least 6.7% lower than that of other algorithms. Finally, the plot of location feature distance illustrates that CBFD exhibits minimal distance compared to DITF and Histogram of Oriented Gradients (HOG). These results highlight the speed and robustness of CBFD across various transformations.

Starting from the last century, animals identification became important for several purposes, e.g. tracking, controlling livestock transaction, and illness control. Invasive and traditional ways used to achieve such animal identification in farms or laboratories. To avoid such invasiveness and to get more accurate identification results, biometric identification methods have appeared. This paper presents an invariant biometric-based identification system to identify cattle based on their muzzle print images. This system makes use of Speeded Up Robust Feature (SURF) features extraction technique along with with minimum distance and Support Vector Machine (SVM) classifiers. The proposed system targets to get best accuracy using minimum number of SURF interest points, which minimizes the time needed for the system to complete an accurate identification. It also compares between the accuracy gained from SURF features through different classifiers. The experiments run 217 muzzle print images and the experimental results showed that our proposed approach achieved an excellent identification rate compared with other previous works.

There is a growing trend for using content‐based image retrieval (CBIR) systems these days because of the constantly growing interest in digital content. Therefore, the ability of the CBIR to perform the CBIR process will depend on the feature extraction process and its basis, for the retrieval will be done on. Numerous researchers put forward various techniques for feature extraction to enhance the nature of the system. Since features play a very key role in enhancing performance, various features can be used collectively to attain the requisite goal. To retain this in mind, we present in this paper a multifeature fusion system, where three features are integrated and form one feature to improve the situation of retrieval. For this purpose, scale‐invariant feature transform (SIFT), speeded‐up robust features (SURF), and histogram of oriented gradients (HOG) features are adopted. These features are common features that deliver information about the shape of the object and for matching purposes, two techniques of distance matching such as Euclidean and Hausdrauff distance are adopted. To assess the performance of the proposed multifeature‐based CBIR approach, experiments were conducted with the usage of a MATLAB simulator. The Corel‐1000 dataset, consisting of 10,000 images in 100 semantic classes, turned into applied, with each magnificence containing 100 images. A subset of 2500 images across 50 semantic classes was used to train the system. This research aligns with industry, innovation, and infrastructure by contributing to advancements in image processing and retrieval systems. Key characteristic descriptors, along with SIFT, SURF, HOG, texture, and multicharacteristic combinations, were extracted for retrieval functions. The results display that the usage of the Hausdrauff distance as a similarity degree outperforms Euclidean distance, accomplishing retrieval accuracies of 80.02% for HOG, 77.9% for SIFT, 79. 8% for SURF, 77.2% for texture, and 84.2% for multicharacteristic combinations, surpassing Euclidean distance results via 1.7%–3.6% across capabilities. These findings underscore the effectiveness of Hausdrauff distance in enhancing retrieval precision within the CBIR framework.

Indian sign language (ISL) is used by deaf people in India for their internal communication. Sign language recognition (SLR) system recognizes gestures of sign language and converts them into text and voice, thus enabling deaf people to communicate with others. In this paper, we have presented an automatic system for ISL hand gesture recognition. Modern features like Histogram of Oriented Gradient (HOG), Speeded Up Robust Features (SURF), Fourier Descriptors, Hu Moments, and Zernike Moments have been extracted from training images of our own created dataset. Using these features, most commonly used classifiers like Support Vector Machine (SVM), Artificial Neural Network (ANN), K-Nearest Neighbors (KNN), and Linear Discriminant Analysis (LDA) have been trained and evaluated. Comparative performance analysis of these classifiers along with experimental results is the main topic of discussion included in this paper. Moreover, a user-friendly GUI of the system allows user to select any combination of features and classifiers to perform gesture recognition from both stored file and live camera. During experiment, it is found that the system is able to recognize gestures with a recognition rate up to 98.70%.

Diabetic retinopathy (DR) and age related macular degeneration (ARMD) are among the major causes of visual impairment all over the world. DR is mainly characterized by small red spots, namely microaneurysms and bright lesions, specifically exudates. However, ARMD is mainly identified by tiny yellow or white deposits called drusen. Since exudates might be the only visible signs of the early diabetic retinopathy, there is an increase demand for automatic diagnosis of retinopathy. Exudates and drusen may share similar appearances; as a result discriminating between them plays a key role in improving screening performance. In this research, we investigative the role of bag of words approach in the automatic diagnosis of retinopathy diabetes. Initially, the color retinal images are preprocessed in order to reduce the intra and inter patient variability. Subsequently, SURF (Speeded up Robust Features), HOG (Histogram of Oriented Gradients), and LBP (Local Binary Patterns) descriptors are extracted. We proposed to use single-based and multiple-based methods to construct the visual dictionary by combining the histogram of word occurrences from each dictionary and building a single histogram. Finally, this histogram representation is fed into a support vector machine with linear kernel for classification. The introduced approach is evaluated for automatic diagnosis of normal and abnormal color retinal images with bright lesions such as drusen and exudates. This approach has been implemented on 430 color retinal images, including six publicly available datasets, in addition to one local dataset. The mean accuracies achieved are 97.2% and 99.77% for single-based and multiple-based dictionaries respectively.

Speeded Up Robust Features (SURF) algorithm is a fast robust local feature matching method. Because of the advantage of invariance of scale and rotation, the SURF algorithm has been widely used in the image registration. However, due to the acquired angle, imaging mode, different resolution, SURF algorithm becomes quite difficult in the image registration. This paper presents a normalized SURF algorithm which can reduce the impact of hue difference between remote sensing images. Combined with the idea of two-way matching, the normalized SURF is able to improve the accuracy of the image registration. The experimental results show the normalized SURF algorithm can keep greater accuracy and relatively higher speed of matching than the original SURF algorithm.

The present work demonstrates the utilization of computer-aided diagnosis system for the detection of lung cancer diseases using computer tomography (CT) images, magnetic resonance images (MRI) and X-ray images. The feature extraction process in lung cancer images has been achieved by scale invariant feature transform (SIFT), speeded up robust features (SURF), and principal component analysis (PCA) techniques. In this work, a comparative investigation of different feature extraction technique such as SIFT, SURF, and PCA has been discussed in order to find the best descriptor for feature extraction of cancerous subjects to the normal subjects in terms of two parameters named as execution time and error rate. The main aspect of these learning approaches is to find the valid key points in minimum execution time with least error. The results reveal that the SURF technique has an average execution time of 0.448 s with an average error rate value of 25.704 which is least among three techniques. Hence, SURF extraction technique is best as compared to SIFT and PCA.

위성 SAR 영상의 활용이 증가하면서 영상의 해석 및 융합을 위한 정밀 기하보정에 대한 필요성이 높아지고 있다. 특히 광역감시 목적으로 활용되기 위해 서로 다른 해상도를 갖는 SAR 영상간 정보융합도 활발해지고 있다. 일반적으로 SAR 영상의 기하보정은 위성의 궤도 및 자세정보를 활용하여 수행할 수 있지만 SAR 센서의 궤도 및 시스템 오차, 대상지형 특성에 의한 왜곡으로 인해 추가적인 보정이 필요하게 된다. SAR 영상을 통한 변화탐지나 타 영상과의 융합에 적용하기 위해서는 기하 오차 보정이 반드시 선행되어야 한다. 이를 위해 다수의 지상 기준점을 선정하고 이를 포함하는 기준 영상과 비교하여 원본 영상에서 대응점을 찾는 방식으로 정밀 기하보정을 수행할 수 있다. Speeded Up Robust Feature (SURF) 기법은 쉽고 빠르게 영상의 기준점을 찾을 수 있지만 상대적으로 해상도가 낮고 스펙클 잡음에 영향을 받는 SAR 영상에서는 활용하기가 어렵다고 알려져 있다. 본 논문에서는 SURF 기법을 위성 SAR 영상에 적용할 때 발생할 수 있는 오차를 추출하고 영상 특성에 따른 성능 변화를 분석하였다. SURF 알고리즘의 적용이 가능한 입력 변수의 적정 범위를 제시하고 그에 따른 영상 정합의 오차를 분석하여 중저해상도의 위성 SAR 영상에 대해서도 SURF 기법을 통한 기하 보정 및 영상 정합이 적용될 수 있음을 검증하였다. As applications of spaceborne SAR imagery are extended, there are increased demands for accurate registrations for better understanding and fusion of radar images. It becomes common to adopt multi-resolution SAR images to apply for wide area reconnaissance. Geometric correction of the SAR images can be performed by using satellite orbit and attitude information. However, the inherent errors of the SAR sensor's attitude and ground geographical data tend to cause geometric errors in the produced SAR image. These errors should be corrected when the SAR images are applied for multi-temporal analysis, change detection applications and image fusion with other sensor images. The undesirable ground registration errors can be corrected with respect to the true ground control points in order to produce complete SAR products. Speeded Up Robust Feature (SURF) technique is an efficient algorithm to extract ground control points from images but is considered to be inappropriate to apply to SAR images due to high speckle noises. In this paper, an attempt is made to apply SURF algorithm to SAR images for image registration and fusion. Matched points are extracted with respect to the varying parameters of Hessian and SURF matching thresholds, and the performance is analyzed by measuring the imaging matching accuracies. A number of performance measures concerning image registration are suggested to validate the use of SURF for spaceborne SAR images. Various simulations methodologies are suggested the validate the use of SURF for the geometric correction and image registrations and it is shown that a good choice of input parameters to the SURF algorithm should be made to apply for the spaceborne SAR images of moderate resolutions.

In this paper, feature subset selection from river-ice image samples for classification of river-ice types is proposed using extreme learning machine (ELM) and differential evolution feature selection (DEFS) technique called extreme learning machine-based differential evolution feature selection (ELM-DEFS). Although DEFS is a good feature selection technique, the feature weights are selected by cross over and mutation which may be trapped. So, ELM is integrated with DEFS to overcome the difficulties of selecting the weights. Feature subset selection plays the most important role to classify the river-ice types. First-and second-order statistical texture features are extracted from real river-ice images. All the original features extracted from feature extraction methods do not help in recognition of river-ice types, so it is essential to reduce the feature subset to improve classification accuracy. In this paper, experiments are conducted on real river-ice image samples with probabilistic neural network (PNN) classifier which classifies different ice types. Performances of ELM-DEFS are compared with genetic algorithm (GA) and DEFS by means of performance evaluation metrics. Experimental results show that ELM-DEFS convergence is better than both DEFS and GA in selecting top-most feature subset; ELM-DEFS-based PNN (ELM-DEFS-PNN) classifier exhibits higher performance with an accuracy of 93% which is approximately 1% higher than GA-based PNN (GA-PNN) and DEFSbased PNN (DEFS-PNN) classification.

One of the main challenges in Intelligent Vehicle is recognition of road obstacles. Our goal is to design a real-time, precise and robust pedestrian recognition system. We choose to use Speeded Up Robust Features (SURF) and a Support Vector Machine (SVM) classifier in order to perform the recognition task. Our main contribution is a method for fast computation of discriminative features for pedestrian recognition. Fast features extraction is assured by using a hierarchical codebook of scale and rotation-invariant SURF features. We evaluate our approach for pedestrian recognition in a set of images where people occur at different scales and in difficult recognition situations. The system shows good performance in visible and especially in infrared images. Besides, experimental results show that the hierarchical structure presents a major interest not only for maintaining a reasonable feature extraction time, but also for improving classification results.

Pedestrian detection is an important but challenging component of an Intelligent Transportation System. In this paper, we describe a pedestrian detection system based on a monocular vision with a Far-Infrared camera (FIR). We propose an original feature representation, called Intensity Self Similarity (ISS), adapted to pedestrian detection in FIR images. The ISS representation is based on the relative intensity self similarity within a pedestrian region of interest (ROI) hypothesis. Our system consists of two components. The first component generates pedestrian ROI hypothesis by exploiting the specific characteristics of FIR images, where pedestrian shapes may vary in large scale, but heads appear usually as light regions. Pedestrian ROI are detected, with high recall rate, due to a Hierarchical Codebook (HC) of Speeded-Up Robust Features (SURF) located in light head regions. The second component consists of pedestrian hypothesis validation, by using a pedestrian full-body classification based on the ISS representation, with Support Vector Machine (SVM). For classification, we retained two feature descriptors: the Histogram of Oriented Gradients (HOG) descriptor and the original ISS feature representation that we proposed for FIR images. The early fusion of these two features enhances significantly the system precision, attaining an F-measure for the pedestrian class of 97.7%. Moreover, this feature fusion outperforms the state-of-the-art SURF descriptor proposed previously. The experimental evaluation shows that our pedestrian detector is also robust, since it performs well in detecting pedestrians even in large scale and crowded real-world scenes.