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.
Traffic sign recognition is difficult due to the low resolution of image, illumination variation and shape distortion. On the public dataset GTSRB, the state-of-the-art performance have been obtained by convolutional neural networks (CNNs), which learn discriminative features automatically to achieve high accuracy but suffer from high computation costs in both training and classification. In this...
Binarization of text in natural scene images is a challenging task due to the variations in color, size, and font of the text and the results are often affected by complex backgrounds, different lighting conditions, shadows and reflections. A robust solution to this problem can significantly enhance the accuracy of scene text recognition algorithms leading to a variety of applications such as scene...
Indirect immunofluorescence imaging is a fundamental technique used for detecting antinuclear antibodies in HEp-2 cells. This is particularly useful for the diagnosis of autoimmune diseases and other important pathological conditions involving the immune system. HEp-2 cells can be categorised into six groups: homogeneous, fine speckled, coarse speckled, nucleolar, cytoplasmic, and Centro mere cells,...
Complex networks refer to large-scale graphs with nontrivial connection patterns. The salient and interesting features that the complex network study offers in comparison to graph theory are the emphasis on the dynamical properties of the networks and the ability of inherently uncovering pattern formation of the vertices. In this paper, we present a hybrid data classification technique combining a...
Natural language dialogue is an important component of interaction between ordinary users and complex computer applications. Short Text Semantic Similarity algorithms have been developed to improve the efficiency of producing sophisticated dialogue systems. Such algorithms are currently unable to discriminate between different dialogue acts (assertions, questions, instructions etc.), requiring the...
Hybridization of neural networks and fuzzy sets has proved its efficiency in solving different pattern classification tasks, which led to the development of granular neural networks (GNNs). GNN works with the principles of granular computing and basically operates on granules of information. The present paper proposes an efficient multiple classifier system (MCS) framework with different guiding rules...
Image and pattern recognition have become a significant task in recent years when most mobile communication devices have integrated cameras. The bag-of-words (BOW) approach is commonly used in information retrieval algorithms, and although originally developed for text, it has been adapted also for visual search. In spite of the similarity, there are different challenges - less effective weighting...
In the last few years there has been growing interest in the use of functional Magnetic Resonance Imaging (fMRI) for brain mapping. To decode brain patterns in fMRI data, we need reliable and accurate classifiers. Towards this goal, we compared performance of eleven popular pattern recognition methods. Before performing pattern recognition, applying the dimensionality reduction methods can improve...
In this paper, we have presented a new and faster word retrieval approach, which is able to deal with heterogeneous document image collections. A certain amount of image features (statistical and Gabor Wavelet) are extracted, which inherently represent word's images. These features are used for generating hash table for fast retrieval of similar image from a very large image dataset. The decomposition...
Digital document categorization based on logo spotting and recognition has raised a great interest in the research community because logos in documents are sources of information for categorizing documents with low costs. In this paper, we present an approach to improve the result of our method for logo spotting and recognition based on key point matching and presented in our previous paper [7]. First,...
Nonnegative matrix factorization (NMF) has been a powerful tool for finding out parts-based, linear representations of nonnegative data samples. Nevertheless, NMF is an unsupervised algorithm, and it is not able to utilize the class label information. In this paper, the Nonnegative Matrix Factorization using Class Label Information (NMF-CLI) is proposed. It combines the class label information for...
Scale-invariant Feature Transform (SIFT) is an algorithm to find local features in images. SIFT uses Difference-of-Gaussian (DoG) to locate candidate keypoints and performs a detailed fit to locate keypoints, then orientations are added to keypoints and keypoint descriptor is generated for each keypoint. Iris recognition is one of the most reliable biometric authentications. In this paper, we propose...
Several studies for palmprint-based personal identification have focused on improving the performance of palmprint images captured under visible light. However, during the past few years, some researchers have considered multispectral images to improve the effect of these systems. Compared with color images, multispectral images provide additional information due to its variety of spectral bands....
Inhabitants daily activity form a pattern in their daily life which has important things in smart home. These patterns can be used to recognize the inhabitant activity that is useful to enhance the smart home services like energy efficiency service, where these patterns can be used as inhabitant behavior to reduce an unnecessary appliances or lightings usage based on the activities their conduct....
Myoelectric signal analysis provides insight into neural control during muscle contraction and it has been widely used to identify the intention of performing different movements for patients with disabilities. Previous studies have demonstrated that detailed neural control information could be extracted from high-density surface electromyography (EMG) signals. However, this imposes practical constraints...
Classification of imbalanced data is a challenging task in machine learning, as most classification approaches tend to bias towards the majority class, even though the minority class is often the one of greater importance. Consequently, methods that are capable of boosting the classification accuracy on the minority class are sought after. In this paper, we propose an improved ensemble approach for...
Base classifier's classification error and diversity are key factors in performance of ensemble methods. There is usually a trade-off between classification error and diversity in ensemble methods. Decreasing classification error of base classifiers usually makes them less diverse while increasing diversity, results in less accurate base classifiers. This paper proposes a new ensemble classifier generation...
Object recognition in real scenes is a central problem in computer vision. In this paper we propose a new approach for shape based recognition of objects in real scenes. This approach uses moment invariants for identification of shape features. Moment Invariants are functions of central moments. They are invariant against linear transformations such as rotation, translation and scaling. Therefore,...
A novel feature selection method based on weighted F-score and SVM is proposed for the problems which inter-class overlapping and consistency of the features are ignored in traditional F-score feature selection method. Firstly, overlapping weight and consistency weight are introduced. Secondly, F-score value of every feature is calculated. Thirdly, F-score values of the features are ordered from high...
In this paper, Persian handwritten digits reorganization by using zoning features and projection histogram for extracting feature vectors with 69-dimensions is presented. In classification stage, support vector machines (SVM) with three linear kernels, polynomial kernel and Gaussian kernel have been used as classifier. We tested our algorithm on the dataset that contained 8600 samples of Persian handwritten...
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.