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.
Support vector machines (SVM) were originally developed for binary classification and extended for multi-class classification. Due to their powerfulness and adaptation to hard classification problems, we have chosen them for automatic speech recognition (ASR). The aim of this paper is to investigate the use of SVM multi-class classification coupled with HMM for TIMIT phones. SVM requires that all...
This paper presents a novel stereo-based visual odometry approach that provides state-of-the-art results in real time, both indoors and outdoors. Our proposed method follows the procedure of computing optical flow and stereo disparity to minimize the re-projection error of tracked fea ture points. However, instead of following the traditional approach of performing this task using only consecutive...
A variety of camera calibration methods are available from the so-far known literature. But most of them aim at camera with conventional lens, the so-called pinhole camera model. Few attentions have been paid to camera with small field-of-view (FOV) and depth-of-field (DOF) telecentric lens. Therefore an effective calibration method is highly necessary. In this paper a new method is proposed to accurately...
With recent advances in radio-frequency identification (RFID), wireless sensor networks, and Web services, physical things are becoming an integral part of the emerging ubiquitous Web. Correlation discovery for ubiquitous things is critical for many important applications such as things search, recommendation, annotation, classification, clustering, composition, and management. In this paper, we propose...
In current biological image analysis, the temporal stage information, such as the developmental stage in the Drosophila development in situ hybridization images, is important for biological knowledge discovery. Such information is usually gained through visual inspection by experts. However, as the high-throughput imaging technology becomes increasingly popular, the demand for labor effort on annotating,...
The high computational complexity and great memory requirement prevent the SIFT algorithm from being processed realtimely. The block-parallel SIFT algorithm with boundary extension adopted by existing researches suffers from redundant storages or extra communications to process the boundaries of partitions. The block-parallel SIFT algorithm without boundary extension (pSIFT-noBE) can spontaneously...
A new feature extraction model based on image gradient is proposed. Firstly, image gradient orientation is calculated. Secondly, gradient orientation difference between image pairs is computed at each pixel. Thirdly, the cosine function value of the gradient orientation difference is used as the correlation value. Experimental results show that the correlation calculation model can be used to measure...
Clustering graphs annotated with feature vectors has recently gained much attention. The goal is to detect groups of vertices that are densely connected in the graph as well as similar with respect to their feature values. While early approaches treated all dimensions of the feature space as equally important, more advanced techniques consider the varying relevance of dimensions for different groups...
Content based image classification is a vital component of machine learning and is attaining increasing importance in the field of image processing. This paper has carried out widespread comparison of block truncation coding based techniques for feature vector extraction of images which is a precursor of image classification. A new block truncation coding (BTC) based technique using even and odd image...
The field of Human-Computer Interaction (HCI) has witnessed a tremendous growth in the past decade. The advent of tablet PCs and cell phones allowing touch-based control has been hailed warmly. The researchers in this field have also explored the potential of ‘eye-gaze’ as a possible means of interaction. Some commercial solutions have already been launched, but they are as yet expensive and offer...
Existing detection methods of abnormal movements focus on model construction and similarity identification of objects in the images. The result of detection is not satisfactory when the number of individuals in the detection area is very large. A new method is proposed to solve such difficulties by analyzing the vehicle environment and passenger groups. Firstly, human head is segmented and extracted...
Higher order image features based on Hu moment invariants have been used successfully in a variety of image analysis tasks. This study presents the application of an invariant to unequal rescaling of the image in constructing image features suitable for action recognition. These features are computed for video images and can be used for classification. Experimental results suggest that this approach...
Compressive sensing [1] [2] measurements generally do not provide as much understandable information as traditional compressed domains. On the other hand, with the rise of compressive sensing image sensors, it becomes necessary to define relevant sensing schemes. Applying the same linear projection to reduced signal supports optimizes the reconstruction time and makes the sensing strategy more suitable...
With the rapid development of microblog, the research of topic detection has been paid more attention, which has begun to transfer from the traditional news media to microblog. However, compared with the traditional fields where topic detection applied, the microblogging data is written informally and the structure of that is not rigorous, which will bring great difficulties. In the process of topic...
When faced with a complicated visual scene many animals including humans attend to important regions in a systematic serial manner. The ability to orient rapidly towards an important region in a scene allows an organism to accomplish activities, such as navigation, foraging and detecting possible prey/mates. Developing a computational model of visual attention has long been of interest as such models...
In this paper we present a method for the detection of wrong feature correspondences in a local feature based object detection system. Common visual objects in different images share not only similar local features but also a similar spatial layout of their features. We will utilize this fact in order to distinguish between correct and wrong feature correspondences. The spatial feature layout will...
The current state-of-the-art speech emotion recognition approaches focus on discrete emotion classification to suit the users' need. However, in more practical perspective, emotion is deemed complex to be individually segregated and it is a continuous process that will change dynamically over time. Subsequently, no researcher can really claim of being able to find the threshold discriminating one...
In this paper a computational alternative to classify lung nodules using computed tomography (CT) thorax images is presented. The novelty of the method is the elimination of the segmentation stage. The contribution consist of several steps. After image acquisition, eight texture features were extracted from the histogram and the gray level coocurrence matrix (with four different angles) for each CT...
In the context of a magnetic field-based indoor location system, this paper proposes a feature extraction process that uses magnetic-field temporal and spectral features in order to develop a classification model of indoor places, using only a magnetometer included in popular smartphones. We initially propose 46 features, 26 derived from the spectral evolution and 20 from the temporal one, chosen...
The technology of panoramic image construction is widely used in many conditions. As the increasingly demand of monitoring system application, the attribute of real-time is more important during the panoramic construction. This paper describes a method of fast building panoramic video and output frames in real-time. SURF algorithm is employed to extract features and a new method is developed to eliminate...
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.