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.
The intent of the image classification process is to objectively categorize an image visual contents into semantic meanings. The classification process is a challenging task due to the difficulty associated with extracting and identifying relevant shape information. In this paper, we introduce a new fusion algorithm that combines the strengths of deep learning and mid-level image descriptors. Our...
Right Whales can be recognized by the callosities pattern on their heads. They are an endangered species with an estimated 450 whales remaining. Marine biologists regularly perform manual recognition of the whales while monitoring the population but the process is slow and time consuming. Deep learning methods achieved state-of-the-art results on several visual recognition tasks. However, training...
Histopathology image classification can provide automated support towards cancer diagnosis. In this paper, we present a transfer learning-based approach for histopathology image classification. We first represent the image feature by Fisher Vector (FV) encoding of local features that are extracted using the Convolutional Neural Network (CNN) model pretrained on ImageNet. Next, to better transfer the...
Tongue coating nature inspection is an essential part in the tongue diagnosis of Traditional Chinese Medicine (TCM). However, it has been depending on doctors' visual judgment. Although many researches have been done in this field, the issue remains challenging. The approaches are limited to image processing or shallow neural networks. In this paper, we propose to computerize tongue coating nature...
In recent years, deep learning has been used in image classification, object tracking, pose estimation, text detection and recognition, visual saliency detection, action recognition and scene labeling. Auto Encoder, sparse coding, Restricted Boltzmann Machine, Deep Belief Networks and Convolutional neural networks is commonly used models in deep learning. Among different type of models, Convolutional...
A novel Hierarchical Structured Dictionary Learning (HSDL) algorithm is proposed in this paper. It aims to learn classs-pecific dictionaries for all classes simultaneously in a hierarchical structure. A discriminative term based on Fisher discrimination criterion is jointly considered for both the classs-pecific dictionaries in the lower level and the shared dictionaries in the upper level to enhance...
Non-cosmic, non-Gaussian disturbances known as “glitches”, show up in gravitational-wave data of the Advanced Laser Interferometer Gravitational-wave Observatory, or aLIGO. In this paper, we propose a deep multi-view convolutional neural network to classify glitches automatically. The primary purpose of classifying glitches is to understand their characteristics and origin, which facilitates their...
Hierarchical dictionary learning seeks multiple dictionaries at different image scales to capture complementary coherent characteristics. We propose a method to learn a hierarchy of two overcomplete synthesis dictionaries with an image classification goal. The classification objective in some sense regularizes the joint optimization of the hierarchical dictionaries and injects refinement feedback...
Environmental sound classification (ESC) is usually conducted based on handcrafted features such as the log-mel feature. Meanwhile, end-to-end classification systems perform feature extraction jointly with classification and have achieved success particularly in image classification. In the same manner, if environmental sounds could be directly learned from the raw waveforms, we would be able to extract...
In Mexico a great number of diseases spread by the mosquitos Aedes has been reported. There are some regions on the country that this number is alarming. The spread of this disease becomes a public health problem and the government is worried about this situation and applied some methods for reducing the infection rate. One of principal methods relies on the localization of the mosquito's larvae and...
Domain adaptation aims to deal with a kind of problem, in which the distribution of training scenarios and testing scenarios are different. Traditional solutions consider this problem in the point of the distribution matching. For the problem of domain adaptation of image classification, this paper proposes a new collaborative representation from the view of image representation. First, all source...
Sparse representation, which represents the test sample as a linear combination of the whole training samples, achieved great success in face recognition. It can obtain a good performance if there exist enough training samples. However, the number of face images of a subject is usually limited in real face recognition systems. In this paper, in order to obtain more representations of a face, we propose...
Because of the challenge of collecting labelled training data, zero-shot learning (ZSL) which transfers semantic knowledge represented by category attributes from seen classes to recognize unseen classes has received a lot of attention recently. Existing methods assume that the source attributes are completely correct in zero-shot learning. However, the source attributes in practice may contain noise...
Hereby in this paper, we are interested to extraction methods and classification in case of image classification and recognition application. We expose the performance of training models on varying classifier algorithms on Caltech 101 images categories. For feature extraction functions we evaluate the use of the classical SURF technique against global color feature extraction. The purpose of our work...
Classification of massive multidimensional data requires high computational power and memory resources. In this paper the problem of parallel implementation of the ensemble composed of classifiers operating with multi-dimensional patterns is discussed. The member classifiers of the ensemble operate in the orthogonal subspaces obtained with the Higher-Order Singular Value Decomposition (HOSVD) of the...
Regarding texture features, Local-based methods such as Local Binary Pattern (LBP) and its variants are computationally efficient high-performing but sensitive to noise, and suffering global structure information loss. By contrast, filter-based counterparts, the Scattering Transform for instance, are tolerant to noise and translation but often lack of small local structure information. In this paper...
In this paper we propose to face the problem of event detection from single images, by exploiting both background information often containing revealing contextual clues and details, which are salient for recognizing the event. Such details are visual objects critical to understand the underlying event depicted in the image and were recently defined in the literature as “event-saliency”. Adopting...
This work shows how to improve hyperspectral image classification through using both a deep representation and contextual information. To implement this objective, this work proposes a new Conditional Random Field (CRF) model (named DBN-CRF) with potentials defined over deep features produced by the Deep Belief Networks (DBNs). The newly formulated DBN-CRF model takes advantage of strength of the...
Hierarchical decomposition enables increased number of classes in a classification problem. Class similarities guide the creation of a family of course to fine classifiers which solve categorical problems more effectively than a single flat classifier. High accuracies require precise configurations for each of the family of classifiers. This paper proposes a method to adaptively select the configuration...
The main objective of the spatial image classification is to extract information classes from a multiband raster spatial image. The network structure and number of inputs are the key factors in deciding the performance and accuracy of the traditional pixel based image classification techniques like Support Vector Machines (SVM), Artificial Neural Networks (ANN), Fuzzy logic, Decision Trees (DT) and...
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.