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.
For face recognition systems, impostors can obtain legal identity authentication by presenting the printed images, the downloaded images or candid videos to the sensor. In this paper, an enhanced face local binary feature (ELBP) of a face map is extracted as a classification feature to identify whether the face map is a real face or a fake face. Compared with the dynamic or static methods proposed...
Classroom observations have been widely used in education over the past couple of decades to measure effective teaching practice. The traditional observation methods rely on human observers, which are short of scalability and objectivity. In this paper, we implement a kind of automatic behavior measurement system, which utilizes the Microsoft Kinect devices to record the students' performance in classroom...
Deep Convolutional Neural Networks (CNNs) achieve substantial improvements in face detection in the wild. Classical CNN-based face detection methods simply stack successive layers of filters where an input sample should pass through all layers before reaching a face/non-face decision. Inspired by the fact that for face detection, filters in deeper layers can discriminate between difficult face/non-face...
This paper aims to develop an effective flower classification approach using the technology of feature extraction. With this regard, a fused descriptor based on Pyramid Histogram of Visual Words (PHOW) is used to extract the color, texture and contour information of flower image. Secondly, Dictionary Learning and Locality-constrained Linear Coding (LLC) are operated on PHOW feature and then images...
Most existing weakly supervised localization (WSL) approaches learn detectors by finding positive bounding boxes based on features learned with image-level supervision. However, those features do not contain spatial location related information and usually provide poor-quality positive samples for training a detector. To overcome this issue, we propose a deep self-taught learning approach, which makes...
In this work we study the task of image annotation, of which the goal is to describe an image using a few tags. Instead of predicting the full list of tags, here we target for providing a short list of tags under a limited number (e.g., 3), to cover as much information as possible of the image. The tags in such a short list should be representative and diverse. It means they are required to be not...
Visual attention has been successfully applied in structural prediction tasks such as visual captioning and question answering. Existing visual attention models are generally spatial, i.e., the attention is modeled as spatial probabilities that re-weight the last conv-layer feature map of a CNN encoding an input image. However, we argue that such spatial attention does not necessarily conform to the...
Band selection is a very important hyperspectral image preprocessing before using data. A novel bands selection method for hyperspectral data based on convolutional neural network (CNN) is proposed in this paper. In this way, we use a custom one-dimensional CNN to train the hyperspectral data to obtain a well-trained model. After testing band combinations, we use the model to obtain the test precision...
In this paper, a face recognition method based on Convolution Neural Network (CNN) is presented. This network consists of three convolution layers, two pooling layers, two full-connected layers and one Softmax regression layer. Stochastic gradient descent algorithm is used to train the feature extractor and the classifier, which can extract the facial features and classify them automatically. The...
Physiological signals such as EEG and EOG have been successfully applied to detect driving fatigue in single modality. In this paper, we propose a multimodal approach by combining partial EEG and forehead EOG to enhance driving fatigue detection. We investigate the key brain area where we collect the EEG to combine with forehead EOG. Our experiment results demonstrate that the temporal EEG signals...
In this paper, a monocular vision measurement method based on rotating lens is proposed. A special optical lens is placed between the target and the camera, which causes light refraction during the measurement process. By analyzing images taken after different light refraction, the 3D coordinates of the target can be obtained. Using this method, 3D measurement of the full field can be completed with...
With the development of the Internet, e-commerce industry rises rapidly. Online shopping becomes more and more convenient and fast. However it is very difficult for consumers to find satisfied commodity because of abundant and mixed commodity. Especially when people purchase the items which they are not familiar with or consume in a strange place. The study of the recommended system is to figure out...
The very high resolution (VHR) images can be seen as multiview data. For better organizing and highlighting similarities and differences between the multiple views of data, a semisupervised multiview feature selection (SemiMFS) method is proposed in this paper, based on consensus and complementary principles. In SemiMFS, feature views are generated by decomposing features into multiple disjoint and...
It is difficult to obtain high-precision thermal geometric parameters of large hot forgings online because of the harsh measurement condition, the high-temperature and large-sized targets. To solve these problems, an online measurement method for thermal geometric parameters of hot forgings based on laser-aided multi-view stereo vision is proposed in this paper. The core content of the method is to...
In this paper, a monocular vision measurement method based on refraction of light is proposed. A flat glass board is placed between the target and the camera, which causes light refraction during the measurement process. By analyzing images taken before and after light refraction, the 3D coordinates of the target can be obtained. Using this method, only the thickness and refractive index of the glass...
Software defined radio (SDR) plays an important role in military and commerce because of its inherent flexibility. It also has great potential in home use, and it can be controlled by software installed on a personal computer or embedded system to achieve different purposes. In this paper, a novel method of dynamic gesture recognition based on support vector machine (SVM) and SDR is proposed. It is...
In view of the low precision and poor interaction in current traditional indoor navigation system of digital map, this paper puts forward an indoor guide strategy, which combines WiFi positioning technology with mobile AR technology. At the same time, the traditional natural feature extraction algorithm is improved by combining FASE with SURF. FAST-SURF can meet the requirement of robustness and real-time...
Brain-Computer Interfaces (BCIs) provide a way to communicate without movement and can offer significant clinical benefits. Electrical brain activity recorded using electroencephalography (EEG) can be automatically interpreted by supervised learning classifiers according to the descriptive features of the signal. This paper investigates the performance of novel feature extraction based on a signal...
In order to find the optimal feature subset for target recognition in foliage environment, a novel feature selection method based on quantum genetic algorithm (QGA) is proposed in this paper. The real data used to identify the targets were collected by ultra-wideband (UWB) radar system. Support vector machine (SVM) classifier is adopted to evaluate the proposed algorithm. The experimental results...
Pedestrian detection exhibits important application value in driver assistance systems, The detection performance often suffers from the various appearances of pedestrians, the illumination changes and complex background. Aiming at solving these challenges, in this paper, first, a new color moments feature is presented to describe the local similarity structure of pedestrians, which reduces the influence...
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.