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.
This paper proposes a novel hybrid model that integrates the synergy of two superior classifiers for functional magnetic resonance imaging (fMRI) recognition, namely, convolutional neural networks (CNNs) and support vector machines (SVMs), both of which have proven results in the field of image recognition. In the proposed model, the CNN functions as a trainable feature extractor and the SVM functions...
This paper proposes a novel deep architecture to address multi-label image recognition, a fundamental and practical task towards general visual understanding. Current solutions for this task usually rely on an extra step of extracting hypothesis regions (i.e., region proposals), resulting in redundant computation and sub-optimal performance. In this work, we achieve the interpretable and contextualized...
Building recognition from images is a challenging task since pictures can be taken from different angles and under different illumination conditions. Most of the building recognition methods use local and global handcrafted image features and do not consider the rejection scenario, where the method have to be capable of identifying if a given image does not belong to any of the classes of interest...
Interest point detection is one of the key technologies in image processing and target recognition. This paper presents a new method for detecting interest points in digital images and computer vision problems based on complex network theory. We associate a directed and weighted complex network model to each image and then we propose three different algorithms to locate these key points based on three...
Bilinear convolutional neural networks (BCNN) model, the state-of-the-art in fine-grained image recognition, fails in distinguishing the categories with subtle visual differences. We design a novel BCNN model guided by user click data (C-BCNN) to improve the performance via capturing both the visual and semantical content in images. Specially, to deal with the heavy noise in large-scale click data,...
We propose AcFR, an active face recognition system that employs a convolutional neural network and acts consistently with human behaviors in common face recognition scenarios. AcFR comprises two main components—a recognition module and a controller module. The recognition module uses a pre-trained VGG-Face net to extract facial image features along with a nearest neighbor identity recognition algorithm...
Perceptual image of a product plays a significant role in decision making when users choose a product whose basic function is homogeneous nowadays. Designers try to design products that meet the all kinds of demands of users. However, a big gap between designers and users exists owning to the subjectivity of designers' experience. An objective model to recognize perceptual image of products is proposed...
Recognition and perception based mobile applications, such as image recognition, are on the rise. These applications recognize the user's surroundings and augment it with information and/or media. These applications are latency-sensitive. They have a soft-realtime nature - late results are potentially meaningless. On the one hand, given the compute-intensive nature of the tasks performed by such applications,...
In this paper, we propose a new video representation incorporating image based deep features and an efficient pooling strategy for the purpose of action recognition. The Convolutional Neural Network (CNN) based features have very recently emerged as the new state of the art for image classification. Several attempts have been made to extend such CNN models for videos by explicitly focusing on the...
The recent rapid and tremendous success of deep convolutional neural networks (CNN) on many challenging computer vision tasks largely derives from the accessibility of the well-annotated ImageNet and PASCAL VOC datasets. Nevertheless, unsupervised image categorization (i.e., without the ground-truth labeling) is much less investigated, yet critically important and difficult when annotations are extremely...
Most successful deep learning algorithms for action recognition extend models designed for image-based tasks such as object recognition to video. Such extensions are typically trained for actions on single video frames or very short clips, and then their predictions from sliding-windows over the video sequence are pooled for recognizing the action at the sequence level. Usually this pooling step uses...
This paper presents an image recognition technique based on discriminative models using features generated from separable lattice hidden Markov models (SL-HMMs). A major problem in image recognition is that the recognition performance is degraded by geometric variations such as that in position and size of the object to be recognized. SL-HMMs have been proposed to solve this problem. SL-HMMs are an...
The recognition images of cattle brand in an automatic way is a necessity to governmental organs responsible for this activity. To help this process, this work presents a method that consists in using Convolutional Neural Network for extracting of characteristics from images of cattle brand and Support Vector Machines for classification. This method consists of six stages: a) select database of images;...
In this paper, we propose a new local descriptor for action recognition in depth images. The proposed descriptor relies on surface normals in 4D space of depth, time, spatial coordinates and higher-order partial derivatives of depth values along spatial coordinates. In order to classify actions, we follow the traditional Bag-of-words (BoW) approach, and propose two encoding methods termed Multi-Scale...
Vehicle recognition has been an important topic in intelligent transportation. However, to recognize different vehicle models from a same make is difficult as there are many near-identical cars under different brand names. In this paper, we investigated fine-grained vehicle recognition via deep Convolutional Neural Network (CNN). Vehicle and the corresponding parts are localized with the help of Region-based...
The work presents an approach towards facial emotion recognition using face dataset consisting of four classes of emotions (happy, angry, neutral and sad) with different models of deep neural networks and compares their performance. We take the raw pixels values of all images in CMU face images dataset. The pixels values were represented by higher level concepts by feeding them into Restricted Boltz-mann...
Many crowd abnormal motion detection methods in video surveillance have been proposed in resent years. However, most of them are based on low semantic features, such gray value, velocity and gradient. Usually, low semantic features contain weak discriminative information of the scene. In addition, these methods often ignore important information in time and space dimension. In this work, a high semantic...
Modeling the emotional response of human observers to specific imagery is an important aspect of affective computing; it both furthers our understanding of the affective qualities of visual stimuli and paves the way for numerous applications. The emotional effect of colors and their combinations have been extensively studied by artists, as color is one of the essential means of conveying the artist's...
This paper presents a visual attention based convolutional neural network (CNN) to solve the image classification problem in the real complex world scene. The presented method can simulate the process of recognizing objects and find the area of interest which is related with the task. Compared with the CNN method in image classification, the model is proficient in fine-grained classification problem...
The computer vision research aims to enable computer to recognize images as easily as human. Human can segregate target from its surrounding environment, which is associated with human memory mechanism. However, it is not quite clear about how the visual images are stored and retrieved in the human brain. This paper attempts to introduce the REM (Retrieving Effective from Memory) model into image...
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.