The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Hyperspectral imaging is a technique which gathers large number of images at various wavelength for the same area of Earth. Once Hyperspectral Image (HSI) has been acquired, a meaningful information can be obtained by further processing it. Processing of HSI must aim at achieving of given goals: detect and classify the elementary materials for each pixel. Hyperspectral image classification is an active...
In this work, we develop a video surveillance system to detect the disappearance of the objects selected by an operator. Proposed method is optimized to minimize the effects of shadows, partial occlusions and changes in illumination to minimize false alarms. The system is trained by extracting local features from the object to produce an alarm in the case of the disappearance.
In this study a model for data reliability in wireless sensor networks is proposed, in which machine learning methods are used. Proposed framework includes data modelling, missing data prediction, anomaly detection, data fusion and trust mechanism phases. Thus, temporal analysis is performed on the preprocessed sensor data and missing data are predicated. Then outliers on collected data are detected...
Learning from imbalanced data sets is an important problem frequently encountered in the application of classification problems. Instances of this type of problem is usually labeled with the label of class majority and minority class instances will be ignored. In this study, an ensemble based method is proposed for problems of imbalanced data set. The results obtained were compared to alternative...
In this study, gender prediction is investigated for the face images. To extract the features of the images, Local Binary Pattern (LBP) is used with its different parameters. To classify the images male or female, K-Nearest Neighbors (KNN) and Discriminant Analysis (DA) methods are used. Their performances according to the LBP parameters are compared. Also classification methods' parameters are changed...
Figure-Ground Segmentation simply means separating foreground from it's background. It has many applications in day to day life. Object recognition is one of the main applications of it. Extracting foreground from it's background is not an easy task. Various techniques are available for figure-ground segmentation. In this paper, a new approach is proposed to extract foreground from background. A high...
Moving Object detection is a challenging tool because shape and size of the object in a video vary significantly according to camera direction, partial occlusion and poses. Significant research has been carried out for detecting people in videos. Traditional methods for detecting human used sliding window approach which involved scanning various sizes of windows across an image. Hence in this work...
An attempt has been made in this paper to derive the features using the Bandelet and Shearlet Transforms. The transforms are then modified into fuzzy Bandelet and fuzzy shearlet transforms and the same are then applied on the face AT&T database to extract the fuzzy features. These features are then tested with the standard Support Vector Machine classifier to get the recognition rate of about...
We propose a systematic frame work for the automatic detection of multiple human actions within the same frame in realistic and diverse video settings. One of the major challenges is the process of recognizing and understanding of human actions from videos with large variations resulting from camera motions, changes in human appearance, pose changes, scale changes and back ground clutter etc. In this...
In the current era of technology advancements, the number of digital transmission libraries are growing terribly quickly, the necessity to expeditiously index, browse and retrieve transmission data is hyperbolic. In this paper, a technical analysis on textual data identification and extraction from image is given in which various approaches for text detection and extraction are discussed and an evaluation...
Cognitive Radio (CR) is an intelligent wireless communication system capable of sensing the environment and making decisions on how to use the available radio resource without creating any harmful interference to licensed users (Primary Users). The intelligent system module of CR provides the ability to gain the knowledge of available spectrum opportunities and reconfigure Radio Frequency (RF) operating...
Our cognitive abilities can help us communicate without any visible action or words. Brain Computer Interfaces (BCI) achieves this communication using the brain waves. But for practical applications, system using BCI must be fast and accurate. In this paper, we present a method that uses SVM classifiers over ensemble of averaged data. Averaging data over number of trails removes the random noise and...
In this paper we proposed SVM algorithm for MNIST dataset with fringe and its complementary version, inverse fringe as feature for SVM. MNIST data-set is consists of 60000 examples of training set and 10000 examples of test set. In our experiments we started with using fringe distance map as feature and found that the accuracy of system on trained data is 99.99% and on test data it is 97.14%, using...
Handwritten and machine printed (H&P) text separation from document images is a precursor to advance the performance of the OCR system. This paper demonstrates the competence of frequency domain features for the classification of H&P text words. We propose wavelet-like discrete cosine transform (WDCT) based features. We conduct an experiment on a large dataset of 2000 text words of popular...
In this paper, we target a recent challenging problem raised in image processing area: face verification in the presence of facial makeup. To the best of our knowledge, very few works have been proposed to solve this problem. In this paper, we propose a novel face verification scheme. Random subspace is applied to get multiple correlation spaces. Similarity measures among face images are calculated...
This paper presents a new technique of simultaneous sparse approximation incorporating a regularity constraint along the coefficients matrix rows. This approach is decomposed in two steps: first a sparse representation of the coefficients matrix is obtained using a simultaneous greedy method. Then, a ℓ1 penalty regularization on the derivative of nonzero coefficients enforces a piecewise constant...
Computer Vision is a field which deals with extracting, analyzing, processing and understanding the images. One of the major application of computer vision is Object Recognition. In this paper, an algorithm is proposed where, object recognition requires two tasks: (i) Object Detection and (ii) Object Classification. The former task, extracts constructive information from the image and detects the...
Support Vector Machines (SVM's) are supervised learning algorithms which can be used for analyzing patterns and classifying data. This supervised algorithm is applicable for binary class as well as multiclass classification. The core idea is to build a hyperplane which can easily separate the training examples. For binary class, SVM constructs a hyper-plane which can easily separate d-dimensional...
Recently, support vector ranking has been adopted to address the challenging person re-identification problem. However, the ranking model based on ordinary global features cannot represent the significant variation of pose and viewpoint across camera views. Thus, a novel ranking method which fuses the dense invariant features is proposed in this paper to model the variation of images across camera...
Due to the influence of both background interference and time-varying position, it is difficult to detect the moving object by computer vision in the complex background environment. This paper novelly builds a topological structure of typical features to detect object. The presented method can effectively detect the object which is scaling, rotating or in affine transformation, because of the using...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.