A robust approach for extracting template from images with relatively poor quality is presented in this paper. The approach combines fast Fourier transformation algorithm and weighted normalized cross correlation algo...
详细信息
A robust approach for extracting template from images with relatively poor quality is presented in this paper. The approach combines fast Fourier transformation algorithm and weighted normalized cross correlation algorithm to deal with images taken under weak template. Basically, it consists of three steps: 1) searching candidate template from the target image using prefabricated template, and 2) determining the count of template matching area and adjusting the candidate template by using neighborhood growth method, and 3) evaluating the optimal template among the candidate templates. A set of experiments has been performed and the results shows that the proposed approach can obtain templates accurately and robustly.
In image matching algorithm, how to ensure that best match's accuracy of the premise and how to reduce the computing time in the image matching process are the challenge problems. So the search strategy to find th...
详细信息
Robot path planning is a NP problem;traditional optimization methods are not very effective to solve it. Traditional genetic algorithm trapped into the local minimum easily. Therefore, based on a simple genetic algori...
详细信息
Minimizing energy dissipation and maximizing network lifetime are among the central concerns when designing applications and protocols for sensor networks. Clustering has been proven to be energy-efficient in sensor n...
详细信息
Minimizing energy dissipation and maximizing network lifetime are among the central concerns when designing applications and protocols for sensor networks. Clustering has been proven to be energy-efficient in sensor networks since data routing and relaying are only operated by cluster heads. Besides, cluster heads can process, filter and aggregate data sent by cluster members, thus reducing network load and alleviating the bandwidth. This paper proposes an improved clustering algorithm named EDC (energy-efficient, dual-pathed, clustering) aiming at avoiding temporary failure of sensor node after cluster head died in the cluster-based WSN. This algorithm set a backup path for every ordinary sensor node which can still transmit data when the cluster head has broken down. And this algorithm can also reduce the communication overhead of network re-clustering efficiently. The results of simulation experiment on the platform OMNeT++ indicate that the network lifetime of the new scheme are much better than other algorithms.
According to the complexity and nonlinear interaction between influencing factors of gas explosion in coal mine, this paper analyzed the main influencing factors of coal mine gas explosion accident with Grey Relationa...
详细信息
According to the complexity and nonlinear interaction between influencing factors of gas explosion in coal mine, this paper analyzed the main influencing factors of coal mine gas explosion accident with Grey Relational Analysis, and built the risk assessment index system of coal mine gas explosion based on four factors of “man-machine-environment- management”. This paper built the multi-criterion and multi-level network calculation model for the index system and got the weight sets by using Analytic Network Process. Multi-level fuzzy comprehensive evaluation determined the risk of gas explosion level. A coal mine in the South, for example, its gas explosion risk assessment, results showed that the method could find the main key risk factors and deal effectively the complex influence relationship among them, and provide an important reference to coal mine gas accident risk control and management.
Traditional Ad Hoc network routing protocols are mainly based on the condition "Shortest Path", and possibly form many congestion nodes to cause routing instability and re-routing. To this point, this paper ...
详细信息
Traditional Ad Hoc network routing protocols are mainly based on the condition "Shortest Path", and possibly form many congestion nodes to cause routing instability and re-routing. To this point, this paper proposed a new bio-inspired adaptive routing protocol (ATAR) based on a mathematic model ARAS which is originally a model for its host Escherichia coli cells to adapt to changes in the availability of a nutrient. In this paper, queue buffer of routing node and hop count of feedback are defined as a new metric, fitness, which represents the comprehensive factor of congestion level and the length of routing path. We map the fitness of neighbors of routing node to the cell volume growth speed in the improved ARAS model, and calculate the state values of neighbors with the model. Then, the routing node selects the next hop according to the maximum. Using this method, we can adaptive to choose a leisurely node as the next hop with shorter path.
Traditional evolutionary algorithm trapped into the local minimum easily. Therefore, based on a simple evolutionary algorithm and combine the base ideology of orthogonal test then applied it to the population initiali...
详细信息
This paper presents the age-group classification based on facial images. We perform age-group classification by dividing ages into five age groups according to the incremental regulation of age. Features are extracted...
详细信息
This paper presents the age-group classification based on facial images. We perform age-group classification by dividing ages into five age groups according to the incremental regulation of age. Features are extracted from face images through Active Appearance Model (AAM), which describe the shape and gray value variation of face images. Principle Component Analysis (PCA) is adopted to reduce the dimensions and Support Vector Machine (SVM) classifier with Gaussian Radian Basis Function (RBF) kernel is trained. Experimental results demonstrate that AAM can improve the performance of age estimation.
Optimization problems arise in many real-world applications. Cultural Algorithms are a class of computational models derived from observing the cultural evolution process in nature, compared with genetic algorithm the...
详细信息
Embedded hardware design is important in real world applications, but with the increase of the hardware scale the traditional methods can not design them well. Cultural Algorithms are a class of computational models d...
详细信息
暂无评论