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...
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...
In order to solve performance reduction of space-time adaptive processing caused by interfering targets mixing in clutter training samples, a robust training samples detection method based on prior knowledge and sparse recovery is proposed. Firstly, the object region in unit to be detected is locked. Then the sparse complete base is got by discretizing the whole Angle-Doppler plane. After that, hollow...
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...
Recent research endeavors have shown the potential of using feed-forward convolutional neural networks to accomplish fast style transfer for images. In this work, we take one step further to explore the possibility of exploiting a feed-forward network to perform style transfer for videos and simultaneously maintain temporal consistency among stylized video frames. Our feed-forward network is trained...
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...
An efficient recognition framework requires both good feature representation and effective classification methods. This paper proposes such a framework based on a spatial Scale Invariant Feature Transform (SIFT) combined with a logistic regression classifier. The performance of the proposed framework is compared to that of state-of-the-art methods based on the Histogram of Orientation Gradients, SIFT...
In this paper, a novel kernel low rank representation (KLRR) method for hyperspectral image classification is proposed. Firstly, we extract the global structure characteristics information of the hyperspectral image based on low rank representation (LRR), then use it as a prior to constrain the recovery coefficient matrix. In order to further improve the classification efficiency and deal with the...
Deep learning has become increasingly popular in both academic and industrial areas in the past years. Various domains including pattern recognition, computer vision, and natural language processing have witnessed the great power of deep networks. However, current studies on deep learning mainly focus on data sets with balanced class labels, while its performance on imbalanced data is not well examined...
In ear recognition problems, sparse representation based classification (SRC) has shown good performance. The dictionary used for sparse coding plays a key role in SRC. Traditional SRC methods mostly use the holistic features of the training samples to construct the dictionary for identification. But this will bring heavy computational load because of the large dimensionality of the dictionary. Therefore,...
We propose a two-stage detector that can not only detect and localize hands, but also provide fine-detailed information in the bounding box of hand in an efficient fashion. In the first stage, hand bounding box proposals are generated from a pixel-level hand probability map. Next, each hand proposal is evaluated by a Multi-task Convolutional Neural Network to filter out false positives and obtain...
This paper presents a novel application of software radio (e.g., Sora) for hand gesture recognition by using long training symbols. The type of gesture performed between the transmitter and receiver can have significant effects on the received wireless signals (e.g., IEEE 802.11a). Since all wireless signal processing functions could be done completely in software, we can easily capture the two long...
Research of the neural network language model in NLP is reviewed. In this paper, the neural network language models are classified into early shallow language models and deep neural network models based on deep learning. This paper emphatically introduces progress of the deep neural network language models, and summarizes the status of deep neural network research's development. Finally, the existing...
This paper introduces a novel tree induction algorithm called sequential Random Forest (sRF) to improve the detection accuracy of a standard Random Forest classifier. Observations have shown that the overall performance of a forest is strongly influenced by the number of training samples. The main idea is to sequentially adapt the number of training samples per class so that each tree better complements...
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...
With the development of economy, science and technology of China, the number of the international students studying science and technology in China has been increasing significantly over the past decade. In our teaching practice, we have introduced a research-oriented teaching/learning curriculum in the undergraduate program for the international students majoring in telecommunications engineering,...
Recent years have witnessed the growing popularity of hashing in large-scale vision problems. It has been shown that the hashing quality could be boosted by leveraging supervised information into hash function learning. However, the existing supervised methods either lack adequate performance or often incur cumbersome model training. In this paper, we propose a novel kernel-based supervised hashing...
Natural scene recognition and classification have received considerable attention in the computer vision community due to its challenging nature. Significant intra-class variations have largely limited the accuracy of scene categorization tasks: a holistic representation forces matching in strict spatial confinement; whereas a bag of features representation ignores the order or spatial layout of the...
Under the condition of modern information technology, various universities in China have been exploring how to reform the teaching content, teaching method, teaching means and teaching mode on higher mathematics. In recent years, according to the talent training goal of our university, we have carried out a series of beneficial exploration and practice such as updating the corresponding teaching content...
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.