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.
A visually impaired person comes across objects with different attributes in his navigational path, and all of those objects can't be considered as obstacles. One person's obstacle could become a landmark for another. Therefore, getting some insights about the features of the obstacles that come across will provide a significant impact on improving the navigational process of the visually impaired...
For the multisensor linear discrete time-invariant stochastic system with unknown noise variances, the new measurement system is constructed by using matrix pseudo-inverse method, which can yield many groups of new measurement sequences by cooperating work. Furthermore, the statistics characteristics of the new measurement sequences are analyzed to determine whether the sensors are faulting or not...
The optimal filtering problem is addressed for multi-rate systems with one-step auto-correlated noises. The state is updated at the highest sampling rate and the sensor has a lower sampling rate. System noise and measurement noise are one-step auto-correlated, respectively. An optimal filter in the linear minimum variance sense is proposed via an innovation analysis approach. A simulation example...
In this work, we develop a minimum mean square error (MMSE) estimator for the underdetermined systems when the signal of interest is sparse. To address the uncertainty issue introduced in the measurement system, robust approaches are developed based on stochastic and worst case optimization techniques under the minimax framework. To solve the optimization problem, different constraints on the unknown...
This paper studies a new switch QR decomposition adaptive filtering algorithm for acoustic echo cancellation (AEC). Based on the flexible p-TA-QR-LS algorithm, the proposed algorithm employs an efficient switching scheme based on voice activity detection and linear prediction, which enables it to distinguish the significant and insignificant input speech periods. The resultant variable mode p-TA-QR-LS...
Endowing users of multi-interface mobile handsets the competence to seamlessly roam among diverse heterogeneous wireless networks has become a crucial challenge confronting the network operators / service providers in the recent years. Today, we have moved far beyond the 3G communication networks, wherein, potential to handover traditionally relied on the channel quality computed from the received...
This paper proposes a matching algorithm based on Delaunay Triangulation for accurate matching between affined images. This method is suitable for images rotated, scaled, translated and affined. During the matching process, triangle nets based on Delaunay theory are constructed from feature points extracted from the images. We try to find geometric invariants from the triangle nets when the images...
Towards the problem of low rate of partial discharge (PD) recognition caused by lack of effective train samples, Fisher discriminant method is applied to improve recognition rate of PD for transformer. The discharge data produced by four PD models is collected, from which forty-four statistical characteristics are extracted. In order to solve the problem of singular matrix due to the high dimension,...
Text detection and recognition in natural scene images plays an important role in content analysis of images. In this paper, based on the characteristics of scene text, we propose a robust text detection and recognition method using Maximally Stable Extremal Regions (MSER) and Support Vector Machine (SVM). Different from the end to end text recognition, we split the recognition problem into detection...
Traditional classification algorithms often perform well when training and testing data are drawn from the identical distribution. However, in real applications, this condition may be not satisfied. Domain adaptation is an effective approach to deal with this problem. In this paper, we propose an efficient two-stage algorithm for domain adaptation. In the label transfer stage, we utilize training...
Pedestrian detection and recognition has become the basic research in various social fields. Convolutional neural networks have excellent learning ability and can recognize various patterns with robustness to some extent distortions and transformations. Yet, they need much more intermediate hidden units and cannot learning from unlabeled samples. In this paper, we purpose a latent training model based...
Convolution-based detection models (CDM) have achieved tremendous success in computer vision in last few years, such as deformable part-based models (DPM) and convolutional neural networks (CNN). The simplicity of these models allows for very large scale training to achieve higher robustness and recognition performance. However, the main bottleneck of those powerful state-of-the-art models is the...
This paper proposes a detection approach for localizing the object of specific category in images. Based on the ensemble of exemplars, a per-exemplar classifier for each exemplar is learnt, which is simple but powerful to perform well in detecting visually similar objects. Meanwhile, considering the fact that the number of negatives is always considerably larger than that of positives, the method...
Fingerprint segmentation is the key step of fingerprint image preprocessing. Efficient fingerprint segmentation technology has significance in both saving preprocessing time and improving the image quality. In this paper, on the basis of the right direction of the fingerprint ridge, we use the gradient threshold method to segment image for the first time. While there are still limitations on the performance...
Based on fisher ratio class separability measure, we propose two types of posterior probability support vector machines (PPSVMs) using binary tree structure. The first one is a some-against-rest binary tree of PPSVM classifiers (SBT), for which some classes as a cluster are divided from the rest classes at each non-leaf node. To determine the two clusters, we use the Fisher ratio separability measure...
With the rapid development of modern information technology, target recognition plays an increasingly important role in agricultural production, national defense construction. However, the existing target recognition algorithm has many limitations, such as image distortion, difficult to recognize target image or poor recognition results because of camera angles and lighting conditions. Based on the...
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.