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.
We propose a new pretreatment for pedestrian detection with convolutional networks. It is widely known that the phenomenon of overlapping feature distribution is common, which leads to overfitting problem. We present a method that divide one category that have overlapping distributed features into multi-subcategories. By this means smooth boundaries can be easily found to separate different subcategories,...
In order to obtain good welding quality, it is necessary to apply quality control because there are many influencing factors in the X-ray welding process. The key to realize welding quality control is to obtain the quality information. Automatic detection of weld defects (ADWD) is an important part of the welding quality assurance, while the extraction of weld region is the base of feature extraction...
The computational method of unconstrained optimization problem is an important research topic in the field of numerical computation. It is of great significance to solve the problem of unconstrained optimization. There are many ways that are applied to settle these questions, so we need to choose a method which owns much faster and less complex trait. Furthermore, in order to solve this rubs, this...
Color constancy is considered to be as the building block for computer vision applications, because color perception may vary based on type of illumination present in the scene. It's well known that human visual system has very efficient color constancy, so it was used as a source of inspiration for some color constancy algorithms. In this survey we present the most recent advances in color constancy...
Image segmentation plays a basic and important role in image processing, and its results are directly related to the ones of image analysis and understanding. Aiming at solving the problem of choosing the optimal threshold-weighted threshold of commonly used thread segmentation methods, this paper proposed the method of integrating genetic algorithm with OTSU method for image segmentation, and adopted...
The design uses AT89C51 series of high-speed microcontroller as the main control module, using a simple peripheral circuit to drive the 32 ∗ 16 dot matrix LED display. It consists of microcontroller, gating circuit, row and column driver circuit, display circuit. The design uses parallel transmission and dynamic scanning technology. Using the principle of LED display, this article elaborates LED dynamic...
Deep learning proposed by Hinton et al is a new learning algorithm of multi-layer neural network, and it is also a new study field in machine learning. This paper describes the structures and advantages to shallow learning of deep learning, and analyzes current popular learning algorithm in detail. Finally, this paper analyzes research directions and future prospects of deep learning.
This paper presents a distributed control method for traffic control at urban traffic network. This method is inspired from spontaneous synchronization. Synchronization is a prevalent phenomenon in nature that a group of objects spontaneously come into co-occurrence with a common rhythm by mutual interactions. The mechanism of synchronization allows controlling of complex processes by simple operations...
This paper presents a novel reflecting freeform surface component which adopts both artificial light and natural light as input, which component is a part of the NLIS (Natural Light Illumination System). The use of reflective elements significantly reduces the thickness of the structure; avoid high cost and installation restrictions. By this design, the illumination has 80.1% of uniformity and 83...
In this paper, we first analysis several solutions for investigation of digital-to-analog converters and also explain their problems. Second we build an embedded model which called TUP (Trace utility program). The model intends to demonstrate that XML combine with cache coherence can surmount upon quandary. Third we assumption the similar interact could also be proved in investigation of consistent...
This paper proposed a new face recognition method based on texture features of gray-level co-occurrence matrix (GLCM). The feature vector is constructed based on GLCM texture features using hybrid projection function in nonsubsampled contourlet transform domain. The experimental results on CMU PIE database demonstrate the efficacy of the new method.
The cyber-informatics method to local-area networks is defined not only by the visualization of RPCs, but also by the extensive need for redundancy. The study of voice-over-IP efficiency is poor and has bad real time capability. In order to accomplish this aim, this paper argues that through the foremost adaptive algorithm for the improvement of Markov models. Follows a Zipf-like distribution, methodology...
The simulation grid has become a very important research topic. In order to ensure the QoS of resource management, we present a control mechanism in simulation grid, which is based on the prediction methods. In the control mechanism, we first introduce our resource management module in simulation grid. Then, we propose a resource allocation algorithm. In order to justify the feasibility and the availability...
The traditional 2-D MLM is often used to protecting images' details, but the algorithm is weak when it is used to suppress image noise particularly image noise with rich details. In order to prove this problem, this paper proposes an improved 2-D MMF algorithm which the number of basic sub-windows is 6 while the number of basic sub-windows is 4 in the traditional 2-D MLM, make sure every pixel can...
This paper addresses the problem of recognize the structured road lane in color road scenes quickly and robustly for AGV (automatic guided vehicle) vision application. To avoid the complicated process and the large computational process time in the color space recognition, the lane recognition process is in the gray image combined with color information which acquired from the HSI color space. The...
An increasing number of real-time applications, related to multimedia, adaptive control and videoconference, require greater flexible scheduling than classical real-time systems permit. This paper proposes a novel approach that generates dynamically the upper bounds and the lower bounds of tasks to manage overload in a real-time system. And then we design a very simple stochastic heuristical algorithm...
The fuzzy c-means method (FCM) is an important research topic that has practical applications in many fields. However, the greatest disadvantage of this method is its sensitivity to initialized values including the number of clusters and cluster centroids. The main goal of this paper is to present an effective method for automatically determining the number of clusters and acquiring the corresponding...
The emerging service grids bring together various distributed application-level services to a 'market' for clients to request and enable the integration of services across distributed, heterogeneous, dynamic virtual organizations. However, there are a number of applications with the requirement of time constraints. We propose a real-time strategy in service grid architecture. We also extend the OGSI...
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.