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.
Compared to image representation based on low-level local descriptors, deep neural activations of Convolutional Neural Networks (CNNs) are richer in mid-level representation, but poorer in geometric invariance properties. In this paper, we present a straightforward framework for better image representation by combining the two approaches. To take advantages of both representations, we extract a fair...
Gene selection prior to classification has been an important topic in bioinformatics, since last decade. Small sample size and high dimensionality in microarray data pose great challenges for performing efficient classification. In this paper we propose efficient hybrid method (GT-kernelPLS) with a combination of wrapper like technique coalitional game theory and kernel partial least square (kernelPLS)...
A key development in the design of visual object recognition systems is the combination of multiple features. In recent years, various popular optimization based feature combination methods have been proposed in the literatures. However, those methods obtain tiny performance improvement at the cost of enormous computation consumption. In this paper, we propose an improved averaging combination (IAC)...
Human action recognition is widely recognized as a challenging task due to the difficulty of effectively characterizing human action in a complex scene. Recent studies have shown that the dense-trajectory-based methods can achieve state-of-the-art recognition results on some challenging datasets. However, in these methods, each dense trajectory is often represented as a vector of coordinates, consequently...
In this paper we introduce a new video description framework that replaces traditional Bag-of-Words with a combination of Fisher Kernels (FK) and Vector of Locally Aggregated Descriptors (VLAD). The main contributions are: (i) a fast algorithm to densely extract global frame features, easier and faster to compute than spatio-temporal local features; (ii) replacing the traditional k-means based vocabulary...
Mobile image retrieval and pairwise matching applications pose a unique set of challenges. As communicating large amount of data could take tens of seconds over a slow wireless link, MPEG defined the CDVS standard to transfer over the network only the data essential to the matching, and not the entire image. However, the extraction of salient image features is a very time consuming process, and it...
Convolutional Neural Network (CNN) is efficient in learning hierarchical features from large image datasets, but its model complexity and large memory foot prints are preventing it from being deployed to devices without a server back-end support. Modern CNNs are always trained on GPUs or even GPU clusters with high speed computation capability due to the immense size of the network. A device based...
Hand posture recognition is an extremely active research topic in Computer Vision and Robotics, with many applications ranging from automatic sign language recognition to human-system interaction. Recently, a new descriptor for object representation based on the kernel method (KDES) has been proposed. While this descriptor has been shown to be efficient for hand posture representation, across-the-board...
Action recognition is a challenging task due to intra-class motion variation caused by diverse style and duration in performed action videos. Previous works on action recognition task are more focused on hand-crafted features, treat different sources of information independently, and simply combine them before classification. In this paper we study action recognition from depth sequences captured...
We present a novel audiovisual emotion recognition solution using multimodal information fusion based on entropy estimation. Considering the limitations of existing methods, we propose a new dual-level fusion framework which consists of feature level fusion module based on kernel entropy component analysis and score level fusion module based on maximum correntropy criterion. In our system, audio and...
A method based on Interval Type-2 Fuzzy Logic Systems (IT2FLSs) for combination of different Support Vector Machines (SVMs) in order to bearing fault detection is the main argument of this paper. For this purpose, an experimental setup has been provided to collect data samples of stator current phase a of the induction motor using healthy and defective bearing. The defective bearing has an inner race...
Blood vessel extraction from retinal fundus images is an important task in developing the computer-aided diagnostic system for ophthalmologists. In this paper we have presented an algorithm for extraction of blood vessels of retinal fundus images and comparison of different moment invariants used for the extraction of features for the vessel pixels. The algorithm uses neural networks for distinguishing...
Autism is a neuro-developmental disorder that retards the normal cognitive development of an affected person. It is prevalent in children below the age of five and is generally identified through the symptoms exhibited by them while they interact with the environment. This work focuses on the extraction of texture features for autistic and control subjects and validation is done using the neural classifiers,...
Diagnosis of disease is done by physical examination of patient by physician. For internal observation physician requires help of sonography, MRI, pathological tests reports etc. In Ayurveda Nadi-Pariksha (pulse examination) is used for making the diagnosis. It uses pulse signal sensed at radial artery on wrist below the thumb for diagnosis manually. The pulse signal contains very useful information...
To alleviate the loads of tracking web log file by human effort, machine learning methods are now commonly used to analyze log data and to identify the pattern of malicious activities. Traditional kernel based techniques, like the neural network and the support vector machine (SVM), typically can deliver higher prediction accuracy. However, the user of a kernel based techniques normally cannot get...
Classification of digital images into photographs and various kinds of non-photographic images has not been sufficiently studied but has many applications such as retrieval of real scene photographs from web sites and image databases. In this paper, we show that the combination of Bag of Visual Words of SURF features and histograms of LBPs for HSV and Luminance components (SURF+LBP(HSVL)) is simple,...
The continuous proliferation of more complex and various security threats leads to the conclusion that new solutions are required. Intrusion Detection Systems can be a pertinent solution because they can deal with the large data volumes of logs gathered from the multitude of systems and can even identify new types of attacks if based on anomaly detection. In this paper we propose an IDS model which...
In this paper, we present an efficient semantic segmentation framework for indoor scenes operating on 3D point clouds. We use the results of a Random Forest Classifier to initialize the unary potentials of a densely interconnected Conditional Random Field, for which we learn the parameters for the pairwise potentials from training data. These potentials capture and model common spatial relations between...
As robots continue to create long-term maps, the amount of information that they need to handle increases over time. In terms of place recognition, this implies that the number of images being considered may increase until exceeding the computational resources of the robot. In this paper we consider a scenario where, given multiple independent large maps, possibly from different cities or locations,...
Automatic classification of tropical wood species is becoming more important especially for timber exporting countries due to the considerable economic challenge as a result of fraudulent labelling of timber species at the custom checkpoints. Hence, a reliable automated wood species recognition system is needed to inspect the wood species labelling at the checkpoints. A tropical wood species classification...
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.