An edge detection method based on a good point set genetic algorithm

In order to improve the convergence rate of genetic algorithms based on edge detection, a novel edge detection method based on a good point set genetic algorithm (GGA) was proposed. The proposed method designed the crossover operation with the theory of good point set in which the progeny inherits the common genes of the parents which represent its family so as to improve the convergence rate of the genetic algorithm. Furthermore, before the algorithm was used for edge detection, the feature space of the image grey level was transformed into the feature space of the fuzzy entropy. Dissimilarity enhancement processing next was applied to the image by using a fuzzy entropy theory to filter the non edge pixels so as to reduce the scale of the solution domain. This approach offered another efficient way to improve the convergence rate. Experimental results show the proposed algorithm performs very well in terms of convergence rate. The detected edge image is well localized, thin, and robustly resistant to noise.     

Image edge detection algorithm in fuzzy domain

An image edge detection algorithm in fuzzy domain is proposed, which combines adaptive fuzzy enhancement and multi direction fuzzy morphology to detect the edges of fuzzy image. The adaptive fuzzy enhancement method enhances the fuzzy image within blocks with sliding windows to avoid losses of the real edges resulting from enhancing with single threshold for the whole image and lead strong adaptive ability to image region variance. The multi direction fuzzy mathematical morphology operates on the enhanced fuzzy image with structure elements of multiple different directions to extract the real edges with directionality and restrain non directional noise. Experiments show the algorithm can detect fuzzy image edge effectively with strong antinoise ability.     

遗传算法的DV-Hop算法改进

DV-Hop算法中,平均每跳距离是影响定位精度的因素之一。针对平均每跳距离带来的定位误差,对锚节点和未知节点的平均每跳距离进行了改进和优化。首先引入遗传算法计算锚节点的平均每跳距离;然后利用跳数小于等于3的锚节点的平均每跳距离加权处理未知节点的平均每跳距离,减少平均每跳距离带来的误差。仿真结果表明,在不增加硬件开销的基础上,改进算法能够有效提高算法的定位精度,并且具有较好的稳定性。     

A frequency-domain image registration algorithm using the improved polar transform

The influence of applying different heat transfer models coupled different data processing methods on determining the ground thermal properties and borehole resistance is analyzed and studied in allusion to constant heating flux method of thermal response test. Results indicate that the calculated thermal properties and borehole resistance are different when applying line heat source model and cylindrical heat source model respectively; volume specific heat barely affects the unknown thermal conductivity, but affects the borehole resistance. Three-parameter estimation has good credibility in determination of thermal properties and borehole resistance. However, the stability of three-parameter estimation on the determination of thermal diffusivity is not good. Finally, the approach of three parameters estimation coupled the line heat source model and cylindrical heat source model is proposed to determine the thermal properties and borehole resistance based on the analysis of the minimum average error on the two heat transfer models.     

The image definition improved algorithm for hot continuous castingbillet surface defects inspection

In the hot continuous casting billet surface defect inspection system based on machine vision, acquiring a high signal-to-noise image is the key for successful inspection. To solve the disadvantages existing in current machine vision engineering, a new algorithm with improved image definition is presented based on both focus window and CCD target area illumination parameters. It selects a target object from series of hot continuous casting billet surface images, and then acquires the optimum articulation through focus window square gradient algorithm. By recognizing and calculating target’s area loss rate, target area parameter evaluation can be done. The global optimum image quality point is achieved. The algorithm is effective in selecting focus plane and shutter time during hot continuous casting surface imaging process and is of a good practical value. At the same time, the algorithm is useful for image collecting work in other machine vision engineering.     

An improved HEED clustering algorithm for Wireless Sensor Network

In wireless sensor network, routing protocols which based on clustering have the advantages of energy consumption, topology management and data fusion. The HEED protocol, which generates cluster heads based on distributed algorithm, drives up the rate of clustering and creates well distributed cluster heads. However, it does not consider the mobility of nodes in the network. When the distance between neighbor nodes has changed, the AMRP method which decides the node belongs to different cluster heads would cause problems such as high energy consumption, short lifetime of network and so on. Responding to these problems, the paper proposes the S HEED, a clustering algorithm based on stability, which chooses the stability as a parameter of nodes when choosing a cluster head. With S HEED algorithm, the high energy consumption problem among cluster nodes and cluster heads caused by the mobility is tackled. The simulation experiment demonstrates that the S HEED algorithm lower the energy consumption of cluster heads and prolongs the network lifetime.     

An improved localization algorithm based on RSSI for landslide monitoring

In order to overcome the existing problems of low automation, high cost and difficult to implement in the area of landslide monitoring, this paper presents a new method of RSSI (Received Signal Strength Indicator)based positioning technology without any one-off instruments to monitor landslide surface displacement. By adding weighted factors, the improved positioning algorithm can estimate the parameters of the path loss model dynamically and calculates the communication distance of network nodes in real-time, which can improve positioning precision and reduce the impact of environmental changes on it. The MATLAB experiments show that, compared with the traditional RSSI based localization algorithm using fixed pass loss model, the improved algorithm could significantly reduce the average error.     

An improved FCM algorithm and its application to EEG signal processing

Most of the popular EEG classifiers need to be supervised and their parameters have to be trained by a number of train data in advance.That’s the reason why they cannot be used in the real-time circumstances.In this paper,a new FCM unsupervised classification algorithm is proposed which is based on the density size of data dot and mahalanobis distance.Then,the algorithm is used to classify the EEG signals from the database of the second session of 2003 BCI competition.The EMD algorithm is used to decompose the EEG and extract the characteristic values,and then these values are classified by the proposed FCM algorithm.The experimental results show the algorithm’s feasibility and validity in the EEG classification field.     

无线传感器网络中一种改进的DV-Hop定位算法

针对DV-Hop算法在无线传感器网络节点分布不均匀时定位误差比较大的问题,提出了一种针对DV-Hop的改进定位算法。该改进算法主要是利用RSSI测量技术增加锚节点;在给定约束下引入“可能存在区域”这一概念,并以该可能存在区域的面积作为目标函数,对未知节点的位置利用非线性共轭梯度法进行逼近,从而使节点定位误差达到最小。通过仿真验证了节点通信半径和锚节点比例对定位误差的影响,结果表明,该改进算法将节点定位精度提高了5%~10%。     

An image segmentation method based on Chan-Vese model combined with threshold algorithm

Threshold segmentation is a basic grey-scale converting technology of image processing. We combine threshold segmentation with Chan-Vese model with an accompanying scale transformation to improve the segment speed and effect. Experimental results show that this program greatly enhances the convergent speed of the Chan-Vese model,and it focuses on changing the defects of more iterative times and low diffusion speed of Chan-Vese model on the border of the image when its grayscale changes slowly.     

An image encryption and compression algorithm based on chaos system and wavelet transform

An image encryption and compression algorithm based on chaos system and discrete wavelet transform (DWT) is studied in this paper.Firstly,four original secret images are transformed by DWT,and then the four low-frequency components are used to compose a two-dimensional coefficient matrix.The matrix is scrambled and encrypted by the chaos system,and then encrypted coefficient matrix is decomposed into four two-dimensional coefficient matrixes.Finally,an encrypted compressed image is obtained by the inverse DWT using the four decomposed two-dimensional coefficient matrices.Encryption and compression are realized at the same time in this algorithm which realizes the combination of chaos and wavelet transform,the experimental simulation and analysis show that the algorithm has good encryption and compression performance.     

An algorithm of image processing based on discrete wavelet transform compression and chaotic scrambling

An algorithm was proposed in view of the combination of image compression and encryption. We got the approximate part and three detail parts after transforming the image with discrete wavelet transform (DWT), and compressed the image by modifying the detail parts by a given threshold value based on human visual systems. And then, we encrypted the image by scrambling the approximate part because this part held mostly of the energy. Last, a compressed and encrypted image can be achieved after DWT. Simulation result shows a good effect on the combination of compression and encryption.     

Ultrasound B-mode image enhancement basedon improved histogram equalization

Abstract:The ultrasound B-mode image and the image enhancement are introcued. The cause of amalgamation for histogram equalization, logarithm and order histogram equalization is analyzed theoretically. An improved histogram equalization method is proposed to maintain the gray level. The experimental results with dummy ultrasound B-mode images demonstrate that the image enhancement performance of the proposed method is better than those of histogram equalization, logarithm and order histogram equalization.     

基于改进SVM分类器的动作识别方法

利用智能手机加速度传感器信号,提出一种改进的动作识别方法以降低传统动作识别方法的复杂程度,提高识别率。在特征提取时用盲选法,即用PCA(principal component analysis)进行特征值的降维和去除多维间的干扰,而所选特征没有对应的物理意义;并在分类识别中将遗传算法应用到SVM(support vector machine)分类器参数优化中。通过实验表明,该方法能够对日常的走路、站立、跑及上下楼等动作进行准确的识别。     

SA-PSO算法在CNN边缘提取模板设计中的应用

提出了一种用于边缘提取的细胞神经网络（CNN）模板的设计方法,该方法在基本粒子群算法的基础上引入模拟退火机制,形成模拟退火粒子群算法（SA-PSO）对模板参数值进行搜寻。在搜索过程中,用退火温度调节粒子的突跳概率,轮盘赌策略确定粒子的全局最优的替代值,这样能有效避免基本PSO算法容易陷入局部最优解的问题。同时,为了保证每轮搜寻产生的解均能使CNN网络稳定,用CNN反馈模板的研究结论对粒子群解空间进行约束。模拟实验表明,文章算法设计出的CNN模板有良好的边缘提取能力。     

An field programmable gate array implementation of an image encryption algorithm based on a discrete chaotic map

Software encryption cannot satisfy real time requirements for multimedia applications which usually involve large volumes of data. To address this problem, an field programmable gate array(FPGA) implementation of the Cyclone EP1C6 for a Kolmogorov chaotic map based image encryption algorithm MASK was proposed. The algorithm was composed of four basic parts: Mixture, key Add, S box and Kolmogorov chaotic map transforms. These parts specifically act on the image as follows: diffusion, applying secret keys, nonlinearity, and permutation. The correlation of adjacent pixels, UACI and the key space of the system subsequently were studied. The source occupation proportion of the hardware was calculated statistically and showed low occupation. Among the advantages of the proposed system are high security, fast encryption speed, and low hardware resources consumption. The proposed system is suitable for implementation in inexpensive FPGA.     

Job-Shop scheduling based on improved immune cloning algorithm

Parallel immune clone algorithm is proposed based on population coevolution theory and parallel computing affinity of individual at multiple compute nodes. Introducing the immune memory mechanism, the evolution processes of antibody population and memory units are conducted simultaneously, meanwhile, it improves mutual cooperation among antibodies, and ensures solution set approaching optimal solution from the inside of feasible region or infeasible region border. Clone proliferation, high frequency variation and operation of crossover operators increase the chance that better individuals gain affinity maturation by the operation of clone expansion, improve diversity of antibody population distribution, achieve the balance of optimization between depth and range, and ensure the convergence of the algorithm and the diversity of the search range. A computational study for a standard data set is carried out to test the validity of the algorithm, and the effect of algorithm parameters on the results is analyzed. The simulation results show that the global search capability, local search capability, algorithm stability and computing speed of the algorithm are all superior to conventional optimization algorithms such as normal immune clone optimization algorithm, genetic algorithm, etc.     

Adaptive image inpainting algorithm based on CDD model

An adaptive image inpainting algorithm based on CDD model is proposed. An adaptive coefficient is introduced to choose the right inpainting model for different curvatures. The coefficient adopts CDD model only for large curvatures,and use TV model for others. Thus the repair time of CDD model is greatly reduced. Another adaptive coefficient is introduced to choose the right diffusion way for different degrees of change. This coefficient adopts a more closing TV model in damage area edge which has large gradient,and use thermal diffusion equation in flat areas which has small gradient. Then better inpainting results can be achieved. Experiments show that the proposed algorithm has much faster inpainting speed and better inpainting results than CDD model.     

Fuzzy webpage text classification algorithm combined with improved NMF

An item-document weight matrix representing the web pages could be generated by constructing the vector space model. Since the efficiency of direct classification through the high-dimensional matrix is relatively low, a fuzzy webpage text classification algorithm combined with improved nonnegative matrix factorization (NMF) is presented. Firstly, the original high-dimensional data are mapped into the low-dimensional semantic space via an iterative normalized compression NMF(NCMF) to reduce the complexity of the problem. Secondly, in order to solve the problem of categorizing ambiguous words by using deterministic matrices, fuzzy logic is incorporated into the classification model, where the fuzzy categorization set of the document is constructed with the fuzzy membership degree between features and categories. Comparative experiment results demonstrate the proposed classification algorithm possesses higher accuracy and better time performance.