To deal with poor robustness in strong noise environment, weak adaptability to complex mixed noise that appear in the existing unsupervised image segmentation models, an improved noise-robust image segmentation model based on One-class SVM (Support Vector Machine) method was proposed. Firstly, a data outlier detection mechanism was constructed based on One-class SVM. Secondly, an outlier degree was introduced into the energy function, so that more accurate image information could be obtained by the proposed model under multiple noise intensities and the failure of weight-descend mechanism in strong noise environment was avoided. Finally, the segmentation contour was driven to the target edge by minimizing the energy function. In noise image segmentation experiments, the proposed model could obtain ideal segmentation results with different types and intensities of noise. Under F₁-score metric, the proposed model is 0.2 to 0.3 higher than LCK (Local Correntropy-based K-means) model, and has better stability in strong noise environments. The segmentation convergence time of the proposed model is only slightly longer than that of LCK model by about 0.1 s. Experimental results show that the proposed model is more robust to probabilistic, extreme values and mixed noise without significantly increase of segmentation time, and can segment natural images with noise.

It is difficult to get correct segmentation results of the images with unknown intensity and distribution of noise, and the existing models are poor in robustness to complex noise environment. Thus, a noise adaptive algorithm for image segmentation was proposed based on local intensity difference. Firstly, Local Correntropy-based K-means (LCK) model and Region-based model via Local Similarity Factor (RLSF) model were analyzed to reduce the sensitivity to noise pixels. Secondly, a correction function based on local intensity statistical information was introduced to reduce the interference of samples to be away from local mean to segmentation results. Finally, the active contour energy function and iterative equation integrated with the correction function were deduced. Experimental results performed on synthetic, and real-world noisy images show that the proposed model is more robust with higher precision, recall and F-score in comparison with Local Binary Fitting (LBF) model, LCK model and RLSF model, and it can achieve good performance on the images with intensity inhomogeneity and noise.

Focusing on the issues of high cost, high susceptibility to damage and low prediction accuracy of soil moisture monitoring and forecasting system, the soil moisture monitoring based on non-fixed wireless sensor network and improved grey wolf algorithm optimization neural network was designed and implemented. In the proposed soil moisture monitoring system, non-fixed and plug-in sensor bluetooth network was used to collect moisture data, and high-precision multi-source location access fusion method was used for wide-area outdoor high-precision positioning. In terms of algorithms, focusing on the issue that Grey Wolf Optimizer (GWO) algorithm easily falls into local optima in its later iterations, an improved GWO algorithm based on rearward explorer mechanism was proposed. Firstly, according to the fitness value of the population, the explorer type was added to the original individual types of the algorithm. Secondly, the search period of population was divided into three parts: active exploration period, cycle exploration period and population regression period. Finally, the unique location updating strategy was used for the explorer during the different period, which made the algorithm more random in the early stage and keep updating in the middle and late stages, thus strengthening the local optimal avoidance ability of the algorithm. The algorithm was tested on the standard functions and applied to optimize the neural network prediction model of soil moisture system. Based on the datasets obtained from the experimental plot No. 2 in a city, the experimental results show that the relative error decreases by about 4 percentage points compared with the direct neural network prediction model, and decreases by about 1 to 2 percentage points compared with the traditional GWO algorithm and Particle Swarm Optimization (PSO). The proposed algorithm has smaller error, better local optimal avoidance ability, and improves the prediction quality of soil moisture.

Considering the LCD-Mura defect background reconstructed by current background suppression methods was vulnerable to introduced noise and target defects, a kind of defect image background modeling method based on Singular Value Decomposition (SVD) and maximum entropy was proposed. The singular value sequence was obtained by the SVD of the image pixel matrix. The correspondence between the image components and the singular values was derived by the matrix norm, and the entropy of each component of the image was calculated by the ratio of each component singular value, then effective singular values of background reconstruction was determined by the maximum entropy. Finally, the background was got by the matrix reconstruction, and the general method of evaluating the effect of background reconstruction was put forward. Compared with the three B spline curve fitting methods, the proposed method can improve the contrast of region Mura by 0.59 times at least and the line Mura contrast by 7.71 times at most; and compared with the Discrete Cosine Transform (DCT) method, it reduces the noise of the point Mura by 33.8 percent at least and the line Mura noise by 76.76 percent. The simulation results show that, the model has the advantages of low noise, low loss and high brightness, and can be used to construct the background information of the defect image more accurate.

Focusing on the issues that the effectiveness and efficiency of existing Adaptive Random Testing (ART) algorithms are not as good as Random Testing (RT) for point failure pattern, an improved ART algorithm based on the concept of crowding level of failure region, namely CLART, was proposed to improve the traditional ART algorithm: Fixed Sized Candidate Set (FSCS) and Restricted Random Testing (RRT), etc. Firstly, the main crowding level was estimated according to the input region to determine the local search region. Secondly, some Test Cases (TCs) were generated by traditional ART algorithms in the local region. Finally, if no failure was found, a new local region was re-selected and some TCs were generated again until the first failure was found. The simulation results show that the effectiveness of the proposed CLART algorithm is about 20% higher than that of FSCS algorithm, and the efficiency is about 60% higher than that of FSCS algorithm. The experimental results indicate that the CLART algorithm can quickly locate the concentrated failure regions by searching several regions one by one to improve the effectiveness and efficiency.

Body size parameters are important indicators to evaluate the growth status of sheep. How to achieve the measurement with non-stress instrument is an urgent and important problem that needs to be resolved in the breeding process of sheep. This paper introduced corresponding machine vision methods to measure the parameters. Sheep body in complex environment was detected by gray-based background subtraction method and chromaticity invariance principle. By virtue of grid method, the contour envelope of sheep body was extracted. After analyzing the contour sequence with D-P algorithm and Helen-Qin Jiushao formula, the point with maximum curvature in the contour was acquired. The point was chosen as the measurement point at the hip of sheep. Based on the above information, the other three measurment points were attained using four-point method and combing the spatial resolution, the body size parameters of sheep body were acquired. And the contactless measurement was achieved. The experimental results show that, the proposed method can effectively extract sheep body in complex environment; the measurement point at hip of sheep can be stably determined and the height of sheep can be stably attained. Due to the complexity of the ambient light, there still exits some problems when determining the shoulder points.

The security feature of DHAAD(Dynamic Home Agent Address Discovery) procedure was analyzed,and a solution was proposed to protect it.The solution authenticated the bi-directional DHAAD messages between mobile node and home Agent,and encrypted the home Agent address list in the message from home Agent to mobile node.The solution can protect the DHAAD procedure against Denial-of-Service attack and the theft of information on home link.Then the evaluation of the solution was given,and it was realized in the Mobile IPv6 demonstration network.

Data migration is a mapping between source database and target database. The formal process of data migration was addressed and several principal mappings among the process were analyzed. An XML-based mapping rule representation method was fully discussed. Furthermore, an approach which can be used to retrieve XML mapping rule skeleton by parsing table object creation DDL script was intorduced. Finally, the method was applied in practice.