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.
In this study, an automated method that is based on image intensities for geometric registration of multi-sensor/multi-resolution imagery acquired from EO-1 Hyperion and IKONOS satellite platforms is proposed. Method performs an area-based transformation to register images of different spectral and spatial resolution with high geometric accuracy. Method basically compares similarity of intensities...
In this paper, a classification system based on association rule to determine the types of power quality event is presented. Firstly, a single feature vector representing three phase event signal is obtained by applying the wavelet transform to event signals in this system. The inputs of generating association rules algorithm are obtained by applying proper transform process to these feature vectors...
In this paper, the robustness of the measures that are used for image registration are tested for common distortions seen in images. Luminance Transform Operation (LTO) is proposed to be used in image registration applications. Performance of the LTO is compared to the Normilized Cross Correlation (NCC) and Mutual Information (MI) measures. Image registration process is carried out between different...
In this paper, a large number of features are extracted from raw EEG data and then feature selection and classification are performed ,for brain computer interface (BCI) applications using motor imaginary movements. As the feature selection method, mRMR (minimum Redundancy Maximum Relevance) method, which is a fast method to select relevant and non redundant feature set, is chosen. Using a number...
Applications such as robotics and augmented reality (AR) require 3D tracking of rigid objects. In robotic applications, the availability of accurate and robust pose estimates increases reliability, whereas in AR scenarios reliable pose estimates decrease jitter. Pure vision sensor based 3D trackers require either manual initializations of pose or off-line training stages. On the other hand, trackers...
Computer vision based athlete tracking systems use different methods to segment players from the background and then track them automatically throughout the video. It is insufficient to know a player's position on the image plane if we want to extract performance analysis of the player. Furthermore, image plane coordinates need to be transformed to real world coordinates representing the position...
A novel variable step size least mean squares (VSS-LMS) algorithm employing cross correlation between channel output and error signal has been proposed as a solution to disadvantage of slow convergence of LMS algorithm. The new algorithm resolves the conflict between the convergence rate and precise of the fixed step-size conventional LMS algorithm. Computer simulations have been performed to verify...
In this study, some solutions for out of vocabulary (OOV) word problem of automatic speech recognition (ASR) systems which are developed for agglutinative languages like Turkish, are examined and an improvement to this problem is proposed. It has been shown that using sub-word language models outperforms word based models by reducing the OOV word ratio in languages with complex morphology. In this...
A novel scene recognition method that utilizes local appearance descriptions together with geometrical invariants for multiview scene matching is presented in this paper. The rationale behind this effort is to complement the lowered discriminative capacity of local features, with invariant geometric descriptions. Presented method is evaluated by comparison with a prominent baseline method, which utilizes...
In this paper, we compare some of the existing joint state particle filtering algorithms for closely spaced target tracking problem. Both maximum a posteriori (MAP) and minimum mean square error (MMSE) estimation outputs of four different algorithms are compared. We also include comparison of a non-joint state particle filter and Kalman filter for a baseline. Simulation results show that claimed performance...
In this paper, we use contourlet transform for digital image manipulation detection. We extract contourlet and wavelet features and test these obtained features on a controlled image data set. Results show that contourlet based features gives better success rates than wavelet based ones.
We present an offline signature verification system based on a signature's local histogram features. Test signature is divided into zones using both the Cartesian and log polar coordinate systems and histogram of oriented gradients (HOG) is calculated for each zone. Verification is considered as a two-class classification problem and for this purpose, a user independent Support Vector Machine (SVM)...
In this paper, a receiver architecture with reduced complexity is proposed for spread spectrum type communication with M-ary quasi orthogonal signaling. The proposed structure comprises of the channel and code matched filtering (MF) concatenated with a reduced state maximum likelihood sequence estimation (MLSE) type processing at symbol rate. MLSE, which takes the interference caused by nonideal cross-...
In occluded areas conventional motion estimation techniques lead to high prediction errors. To reduce the prediction error, occlusion detection algorithms should be employed in motion estimation. This paper investigates the influence of the occlusion in a reversible video watermarking technique based on histogram modification of motion compensated prediction error and presents a new reversible video...
In this study, to compare the robustness and learning capability of the classifiers on imbalanced datasets, a cross validation method that generates class-imbalanced training sets is proposed. The method will also be used to evaluate the accuracies of methods developed for dealing with the class-imbalance problem. The proposed method is used to generate imbalanced datasets from three biomedical datasets...
In the color cognition process of a scene, there is no use of the atmosphere, surface reflectance and illuminant interaction. Therefore, the color perception is blind. The color perception in human brain is directly related to the response of retinal photodetector tissues. Are there only three detectors in the retina; Red, Green, Blue detectors; or are there many? Is spectral band clustering related...
Lattice reduction is a powerful method used in detection and precoding of wireless multiple input-multiple output (MIMO) systems. The basic idea is to consider the channel transfer matrix as a basis for the transmitted symbols. The channel transfer matrix is reduced to a more orthogonal matrix using lattice reduction algorithms. This in turn, improves the performance of conventional MIMO receivers...
Every year, more than ten thousand people die because of traffic accidents in Turkey and about two hundred thousand people are injured. After examining the traffic accident statics, 90% of the accident are caused by driver's mistakes. Drivers who are playing important role in the occurence of traffic accidents, must be aware of situtations of roads and risky areas on their routes during journey, not...
Most of the state-of-the-art reinforcement learning algorithms are based on Bellman equations and make use of fixed-point iteration methods to converge to suboptimal solutions. However, some of the recent approaches transform the reinforcement learning problem into an equivalent likelihood maximization problem with using appropriate graphical models. Hence, it allows the adoption of probabilistic...
The purpose of this study is to show the success of Abstract Feature Extraction Method in multi dimensional feature vectors studies. Author recognition study is taken as an application area and word root and 2 gram's are chosen as feature vectors. The success of the Abstract Feature Extraction method in classification is shown on both Turkish and English data sets by comparing with feature extraction...
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.