Yazar "Altun, Halis" seçeneğine göre listele
Listeleniyor 1 - 10 / 10
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe An efficient color detection in RGB space using hierarchical neural network structure(2011) Altun, Halis; Sinekli, Recai; Tekbas, Ugur; Karakaya, Fuat; Peker, MuratColor detection is generally a primary stage in most of the image processing application, if the application is based on the color information, such as road sign detection, face detection, skin color detection, object detection and object tracking etc. As the performance of subsequent modules in an image processing application is adversely affected by the previous modules, the accuracy of color detection with a high performance inevitably becomes crucial in some applications. This paper introduces a method for an efficient color detection in RGB space using an ensemble of experts in hierarchical structure. In this structure, a set of experts is assigned to evaluate R, G, B components of a pixel and then constructs a degree of membership to the set of predefined class of colors for the given pixel. Then a master neural network constructs its final decision based on the membership probabilities provided by the set of experts. Qualitative and quantitative evaluations of the results show that the proposed hierarchical structure of neural networks is superior over the conventional neural network classifier in color detection. © 2011 IEEE.Öğe Boosting selection of speech related features to improve performance of multi-class SVMs in emotion detection(PERGAMON-ELSEVIER SCIENCE LTD, 2009) Altun, Halis; Polat, GoekhanThis paper deals with the strategies for feature selection and multi-class classification in the emotion detection problem. The aim is two-fold: to increase the effectiveness of four feature selection algorithms and to improve accuracy of multi-class Classifiers for emotion detection problem under different frameworks and strategies. Although, a large amount of research has been conducted to determine the most informative features in emotion detection, it is still an open problem to identify reliably discriminating features. As it is believed that highly informative features are more critical factor than classifier itself, recent Studies have been focused oil identifying the features that contribute more to the classification problem. In this paper, in order to improve the performance of multi-class SVMs in emotion detection, 58 features extracted from recorded speech samples are processed in two new frameworks to boost the feature selection algorithms. Evaluation of the final feature sets validates that the frameworks are able to select more informative Subset of the features in terms of class-separability. Also it is found that among four feature selection algorithms, a recently proposed one, LSBOUND, significantly outperforms the others. The accuracy rate obtained in the proposed framework is the highest achievement reported so far in the literature for the same dataset. (C) 2008 Elsevier Ltd. All rights reserved.Öğe Determining efficiency of speech feature groups in emotion detection(IEEE, 2007) Polat, Goekhan; Altun, HalisFeatures, extract from speech parameter are frequently used in emotion detection problem. Prosodic, MFCC, LPC and band energy feature groups are commonly used in literature to detect emotion in speech. The aim of the study is to examine the efficiency of these features groups in emotion detection problem using a SVM classifier.Öğe Evalutation of performance of KNN, MLP and RBF classifiers in emotion detection problem(IEEE, 2007) Polat, Goekhan; Altun, HalisEmotion Detection has gained increasing attention and become an active research area. The problem is solved with improved feature set with different number of feature groups, by employing different classifiers in order to achieve satisfactory recognition rate. In this study, speech related features are employed to evaluate the performance of different classifiers in emotion detection problem.Öğe Hardware implementation of a scale and rotation invariant object detection algorithm on FPGA for real-time applications(TUBITAK SCIENTIFIC & TECHNICAL RESEARCH COUNCIL TURKEY, 2016) Peker, Murat; Altun, Halis; Karakaya, FuatA hardware implementation of a computationally light, scale, and rotation invariant method for shape detection on FPGA is devised. The method is based on histogram of oriented gradients (HOG) and average magnitude difference function (AMDF). AMDF is used as a decision module that measures the similarity/dissimilarity between HOG vectors of an image in order to classify the object. In addition, a simulation environment implemented on MATLAB is developed in order to overcome the time-consuming and tedious process of hardware verification on the FPGA platform. The simulation environment provides specific tools to quickly implement the proposed methods. It is shown that the simulator is able to produce exactly the same results as those obtained from FPGA implementation. The results indicate that the proposed approach leads to a shape detection method that is computationally light, scale, and rotation invariant, and, therefore, suitable for real-time industrial and robotic vision applications.Öğe Implementation of HOG algorithm for Real Time Object Recognition Applications on FPGA based Embedded System(IEEE, 2009) Karakaya, Fuat; Altun, Halis; Cavuslu, Mehmet AliRecent years HOG algorithm has been used to recognize objects in images, with complex content, with a very high success rate. Hardware implementation of this algorithm is very important because of the fact that it can be used in many object recognition applications. In this work HOG algorithm is implemented on FPGA to recognize different geometrical figures with a very high success rate. Objects vertical and horizontal edges have been sharpened using edge detection algorithms to calculate magnitude and angle of the local gradients. Obtained result are used to construct the histograms of gradient orientation. It is observed that each constructed histogram have distinctive features for every object. Rule based classifiers has been used to implement a successful real time object recognition approach on embedded system.Öğe İnsan-bilgisayar etkileşimini geliştirmek için ses ve yüz görüntü işaretlerinden çok kipli biometrik özniteliklerin belirlenmesi ve etkin birleştirilmesi(2007) Altun, Halis; Polat, Ediz; Polat, Gökhan; Güneş, Turan[Abstract Not Available]Öğe New frameworks to boost feature selection algorithms in emotion detection for improved human-computer interaction(SPRINGER-VERLAG BERLIN, 2007) Altun, Halis; Polat, Goekhan; Mele, F; Santillo, S; Ramella, G; Ventriglia, FOne of the primary aims in human-computer interaction research is to develop an ability to recognize affective state of the user. Such ability is indispensable to have a more human-like nature in human-computer interaction. However, the researches in this direction are not mature and intensive efforts have only been witnessed recently. This work envisages the possibility of enhancing feature selection phase of emotion detection task to obtain robust parameters which will be determined from verbal information to achieve an improved affective human-computer interaction. As highly informative feature selection is believed to be a more critical factor than classifier itself, recent studies have increasingly focussed on determining features that contribute more to the classification problem. Two new frameworks for multi-class emotion detection problem are proposed in this paper, so as to boost the feature selection algorithms in a way that the selected features will be more informative in terms of class-separability. Evaluation of the selected final features is accomplished by multi-class classifiers. Results show that the proposed frameworks are successful in terms of attaining lower average cross-validation error.Öğe On the comparison of classifiers' performance in emotion classification: Critiques and Suggestions(IEEE, 2008) Altun, Halis; Polat, GoekhanIn literature there is a huge body of references available which compare various classifiers in a particular application. However, the reliability of such a comparison is only valid if the model parameters, performance criteria and training environment are chosen in a fair framework, as successful application of a classifier is dependent on the those parameters. In this study we attempt to answer the questions below in a emotion detection framework, using classifiers such as KNN, SVM, RBF and MLP: Is the success of a classifier enough to make the claim that a classifier is "the best one" in a particular classification task? How is it possible to carry out a fair comparison between classifiers?Öğe The Effect of Genetic Algorithm Parameters on the Solution of Plate Location Detection(IEEE, 2008) Peker, Murat; Altun, Halis; Karakaya, FuatIn this study, a new method based on genetic algorithm and neural networks for determining licence plate location is proposed. The effect of genetic algorithm parameters on the quality of solutions is investigated. The method is able to successfully locate a licence plate in avearge 40 msn, on the image of 768x288 size. This score is 200 times quicker compared to sequential search method. Futhermore the method is able to find multiple plates in an image.
