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.
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...
This paper presents a novel methodology of pattern analysis and enumeration to generate initial design-styled complex test patterns based on products from other more matured technology nodes in the beginning of a new technology development. With this methodology, the development of DRM (Design Rule Manual) and verification of process capability can be sped up significantly compared to the purely silicon...
Recently, the query on uncertain data attracts much attention and it is great significance for probabilistic reverse k neighbor query on uncertain data based on location-based services (LBS). However, the relevant research is less and immature. Probabilistic reverse k nearest neighbor (PRkNN) requests the query point of reverse k neighbor query and the probability is greater than the given threshold...
The purpose of this study is to propose an approach to recommend classification algorithms for real-world classification problems. First, the extension rhombus thinking mode is used to construct performance indicators of the classification algorithm. Second, an extension-based recommendation method about classification algorithm is proposed. Third, a recommendation system is designed to implement...
Vision-based video surveillance systems have gained increasing popularity. However, their functionality is substantially limited under nighttime conditions due to the poor visibility caused by improper illumination. Equipped on night vision cameras, ordinary infrared (IR) illuminators of fixed-intensity usually lead to the imaging problem of overexposure (or underexposure) when the object is too close...
It is true that Internet has not only expanded our horizons, but also triggered an unprecedented revolution of operating electronization against the traditional method after we entered the 21st century — also called the age of Internet. In the business area, many enterprises have already achieved the goal of electronic management, saved human resources as well as material consuming, and largely increased...
A video retrieval Algorithm based on video fingerprints and spatiotemporal information is proposed in this paper to solve the problem which is brought by the whole drift of brightness, interference of abnormal point and video re-editing. Firstly, the video fingerprints feature is extracted by frame segmentation. Then an improved direct timing algorithm is used to eliminate the interference of brightness...
Face recognition is a research hotspot in recent years. In order to improve recognition accuracy of face recognition, a feature selection method for face image based on Gabor feature and recursive feature elimination was proposed in this paper. Firstly, Gabor features were extracted from face image. Then, face image was divided into pieces and Gabor feature statistics of these pieces were linked in...
Mammogram analysis is known to provide early-stage diagnosis of breast cancer in reducing its morbidity and mortality. In this paper, we propose a scalable content-based image retrieval (CBIR) framework for digital mammograms. CBIR is of great significance for breast cancer diagnosis as it can provide doctors image-guided avenues to access relevant cases. Clinical decisions based on such cases offer...
With the emerging of digital convergence, lots of communication services are generated, and the quantity of data grows rapidly. We face the scalability issue to deal with call data records (CDRs) and so are the other telecom companies. This research uses police CDR query as an example with an intension to increase system execution efficiency and scalability and to reduce total cost by applying cloud...
Cloud Service is a major project that CHT currently initiated to promote. It aims to provide services to users anytime and anywhere. To achieve that, we need robust cloud technology. This paper takes FMS (Fraud Management System) as an example to depict the system migration process into the cloud service. We propose solutions to problems we encountered, software licensing issues, and other related...
In order to strengthen the comprehensive competitiveness under the global information environment, enterprises should integrate information resources within the companies, supply chain enterprises and other stakeholders. The core is to achieve information sharing and coordination. Through the analysis of new requirements of real time, sharing, interaction and diversity in enterprise information that...
Aiming at the software engineering practice of undergraduate, this paper proposes a software development practice platform. This platform effectively combines teaching management with software development process management, and realizes a complete lifecycle management of software engineering practice. As well, based on event ontology, this platform constructs a knowledge base of teaching resources...
Image-based building reconstruction is a hot point in computer vision and computer graphics, but few works have done on reconstruction from a single image because it is an ill-conditional problem and is very difficult to resolve. In this paper, we present an efficient method by matching contours between image and projection of 3D models. Our method simplifies the reconstruction process and avoids...
A novel word-based algorithm is presented to detect duplicate Picture in Picture (PiP) video sequences in this study. The conventional edge-based methods used to extract the PiP regions are not robust in the noise and blurring images. Bag of Words (BOW) model emphasizes words ambiguity and ignores spatial information. Without detecting the PiP regions and unlike the traditional word based approach,...
To help the biomedical scientist pre-confirm the disease-related genes, we considered these gene as a whole research set and analyzed the topological features of their interaction network. Two strategies had been proposed to construct the disease-related gene network from the OMIM database. Using these two constructed sets, we trained two support vector machine prediction models, the accuracy of which...
The paper outlines the weak point of ERP planning system, discuss the advantage at planning in APS, summarizes the relationship between ERP and APS. Analyzes the research on the integration of ERP and APS in domestic and international. On the basis of the summary and comparison of three different distributing technology, the paper proposed an integration model of ERP and APS based on CORBA static...
In the 21st century, lots of entity Retail Companies chooses online selling as a channel for their promotion. However, the technology based on catalogues to classify product information is no longer efficient for customer because they may get lost while they search information via catalogues. To solve this issue, online business agent appeared to try to fix this problem. This paper makes an attempt...
Most of the existing algorithms for mining frequent patterns could produce lots of projected databases and short patterns which could increase the time and memory cost of mining. In order to overcome such shortcoming, a fast and efficient algorithm named FBPM for mining frequent patterns in biological sequence is proposed. We first present the concept of primary pattern, and then use prefix tree for...
Breast cancer is the most common malignant disease in women. Mammographic mass retrieval system can help radiologists to improve the diagnostic accuracy by retrieving biopsy-proven masses which are similar with the diagnostic ones. However, although screening mammograms usually consists of two-view(MLO and CC) mammography of the same breast, most breast CAD systems incorporate with image retrieval...
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.