For the issue of over-segmentation in the watershed initial segmentation,this paper proposed a clustered cells segmen-tation method based on adaptive H-minima transform in watershed framework.Using corresponding candidate seeds as clustering initial centers,which were reserved seeds after noise seeds suppressed by different h value H-minima transform,this method first-ly produced some candidate segmentation results through modified K-means region merging algorithms.Then,it adaptively chose the optimal h value and produced the optional segmentation result for each clustered cells region using maximal average roundness of candidate segmentation results as optimization objective.Experiments on a variety of synthetic and real microscopic cell images show that the proposed method can efficiently restrain over-segmentation and decrease under-segmentation.This method yielded more accurate segmentation rate than the state-of-the-art watershed-based segmentation methods.

为了改善中央空调现有的全局控制策略,采用一种分区模型的局部控制策略。以广东省某购物广场中央空调节能改造项目作为研究背景,分析了购物广场内部结构特点和功能区域构成。将建筑中功能相似区域进行分区,找出各区域冷负荷规律,并根据不同区域冷负荷特点建立数学模型,"因地制宜"地制定控制策略,充分挖掘节能潜力。采取新老系统对比运行的方法,利用组态软件分别对电能数据进行采集、记录、查询和分析,验证了分区模型控制策略的可行性及节能效果。

The precise detection and counting of bars with high adhesion degree is a difficult issue.We propose the convex-hull peeling al-gorithm in the paper.It is to judge whether there are the bars with high adhesion degree in the image.If there are,then the edge contour cor-ners and part of central points on bars’end face are obtained first,and from the derived corners and central points the algorithm finds a set of point sets which can describe the end face contour of bars;then according to the point sets it finds the convex hull of end face contour of ex-ternal bars,so as to peel the external bars off to achieve the goal of precisely obtaining the central points of internal bars.If there are not, then the peak extraction method will be employed to detect the central points of all bars.Practice proves that the method can effectively en-hance the accuracy of recognition and counting on bars with high adhesion degree.

针对变水量空调温度控制的Fuzzy-PID复合控制器存在切换点选择困难和切换扰动的问题,设计了基于模糊规则切换的Fuzzy-PID复合控制器;在控制误差大时,采用模糊控制提高系统动态特性;在控制误差小时,采用PID控制提高系统的控制精度;为使控制器切换平滑,采用模糊规则进行切换,并对模糊规则的选取原则进行了分析,在Matlab/Simulink软件上进行了仿真;仿真结果表明,该控制器实现了平滑切换,且具有一定的抗干扰性。

The material thickness control of chain Grate to ensure the production of pellets is essential. For detection lag exists in the traditional process, we use a method based on a weighted average filter, designed a grate automatic gauge control system. The actual application shows that this method can effectively overcome the material thickness fluctuations original system problem exists, and achieved good control effect.

A kind of membership function, called as generalized linear membership function(GLMF), is designed in the paper, and the triangular and trapezoid ones are as its special cases. It is derived that the fuzzy-PID Controller with GLMF is equivalent to the sum of a nonlinear PID controller and a compensation value, based on the analytical structure of the controller. With the definition of fuzzy Lyapunov function, the stabilization condition is given to adjust the performance of the fuzzy system. Finally, the characters of the designed fuzzy system, derived by theoretical analysis, are manifested by the simulation results of several examples.

Projection Onto Convex Sets theory (POCS) and Scale Invariant Feature Transform (SIFT) algorithm were introduced for super-resolution restoration of moving blurred image. In order to achieve a better restored image, a POCS-SIFT based super-resolution image restoration algorithm was proposed, which incorporates POCS theory and SIFT algorithm. From experimental results, the improved restored images are obtained by POCS-SIFT hybrid algorithm.

The traditional two-dimensional Otsu can only divide the targets from the backgrounds. However, the targets are not all useful. So, a further process is needed. This paper proposes an optimized entropy function algorithm. The images are only regarded as the targets and backgrounds. Meanwhile, the weights can determine the proportion of the targets' and the backgrounds' entropy in the entire entropy function for selecting regions of interest (ROI), and then identify the ROIs from the targets which are divided by the method of two-dimensional Otsu by comparing the entropy function containing weights with the given threshold. Eventually, processing and analyzing the images obtained from the tar furnace combustion proved the feasibility, accuracy, and efficiency of the method proposed in this paper.

BoVW (Bag of Visual Words) Model has attracted much attention for many computer vision applications in which an image is represented by a histogram of visual words. Two of its critical steps are to construct a visual dictionary and to quantize each local feature to its nearest visual word in the dictionary. In this paper, we present the framework of a generalized BoVW (GBoVW) Model in which feature quantization can be replaced by sparse coding based feature encoding. We also propose to use spectral clustering to construct a visual dictionary to overcome the shortcomings of K-Means based clustering algorithms. Image retrieval experiments on ZuBud database indicate that GBoVW Model improves BoVW Model and the visual dictionary generated by spectral clustering achieves better performance than that by K-Means based clustering methods.

The ring cold trolley is an important part of the sintering ring cold machine, mainly include the table body, wheels, axle, sealing device, a blocking plate, heat insulation pad, and grate. the trolley has large volume ,overloading, large contact stress, and hard work environment. The trolley may happen wheels position shift, even fall . the paper have designed a device that is able to detect the running state of trolleys online for measuring the distance between the ring cold trolley wheels. We gain effective data derived from measuring data and effective data analysis,and according theoretical bearing repair cycle, calculate Correction coefficient a of repair cycle the trolley wheel bearings .

Aiming at the overlapping rebar on the conveyer band which was heterogeneous in shape and size,a design method of the online rebar section center recognition based on the gradient orientation-based fuzzy convolution kernel was presented.Firstly,according to the deformation degree from the standard circle edge,agradient orientation-based convolution kernel was defined.Secondly,rebar section centers were enhanced using the convolution between the rebar section gradient image and the gradient orientation-based fuzzy convolution kernel.Lastly,rebar section centers were recognized through three steps including the candidate points selection,the local peak suppressive and the distance detection.Experimental results show that this method can overcome the peak diffusion and decrease the error recognition and the missing recognition.Moreover,the recognition process can be finished in 8.3ms,which meets the real-time demand.

Research using image processing techniques to identify new burning point of industrial tube furnace.First, get the flame image through the design system, and then using the symmetric differencing to obtain each furnace burning point position, and finally the use of Clustering Algorithm to identify the new burning point. Through the experimental simulation show that this algorithm can avoid the complex background interference in the furnace, accurate and effective identify the new burning point.

Aim at the deficiency of the traditional fuzzy controller,the design of improved fuzzy controller with correction factor is designed in this paper.The controller adds self-turning correction factor and Intelligent integral module.Simulation result shows that the performance of controller is good,this method is applied to the liquid level control system,and had achieved good effect.

In order to decrease the design difficulty and improve the control performance,this paper designed a kind of PID-fuzzy controller with a weighted factor,and proposed a systematic design method of the parameters for the fuzzy controller on the basis of the conventional PID controller.Firstly,it proved the structure of the designed PID-fuzzy controller to be the combination of a global two dimensional multi-value delay and a local variable-structure PID controller.Secondly,it put forward the systematized design method for the PID-fuzzy controller on the basis of the steady state parameters of PID controller.Finally,it included the simulation results to demonstrate the effectiveness of the designed PID-fuzzy controller.

The paper proposes a method to realize the real-time and accurate counting of steel bars.Through using the method of processing every bar into a single pixel,the proposed scheme can avoid the influence of the counting by adhesion.Meanwhile this method makes the true shape of object section about steel bars counting unnecessary to consider.To effectively overcome the image blurring caused by the lighting,noise interference and the quick movement of the bar,the proposed scheme firstly proceeds image pre-processing of the original bar images,then uses corrosion and thinning algorithm to achieve the separation of the bar adhesion,and finally uses linear shrinkage and endpoint detection algorithm to achieve the correspondence between the single pixels and the original bar images respectively to realize the subsequent counting.Experiments demonstrate that the method can not only ensure the accuracy of automatic counting but also create conditions for the bar counts for packaging.

There are many problems about the Temperature and Humidity Controlling in Artificial Climate Chamber,not only its characteristics of larger lagging,no accurate mathematical model and uncertain interferences,but the coupled relation between temperature and humidity.It can’t get a good effect by using conventional PID controller or simple fuzzy controller.This paper proposes an intelligent control algorithm which contains fuzzy controller and PID controller.And at the same time,by the field examination in the artificial climate chamber in Inner Mongolia university college of biology,we prove the effectiveness of the control algorithm for the temperature and humidity control system.

Artificial climate chamber is a kind of experimental and scientific equipment that can simulate the natural environment. Temperature and humidity are the main control parameters. At present, at home and abroad , most of temperature and humidity control algorithms of the artificial climate chamber belong to single factor control, they all ignoring the coupling problem between temperature and humidity. This process cannot ensure the accuracy of the system, and it is easy to cause system oscillation. Thus, in this paper, we use an algorithm called the feed-forward decoupling to eliminate the coupling between the temperature and humidity through the way of feed-forward compensation, finally we design the temperature and humidity fuzzy controller respectively as the single factor control.

In this paper we proposed an improved watershed algorithm for the quasi-circle overlapping images of the bars' end face. According to the classical watershed algorithm, which often causes over-segmentation, the improved algorithm does a series of pretreatment with the original image, such as sobel filter. With the gradient operator and mathematical morphology method, we firstly obtain the smooth image of the forced local maximum marks. Then, on the basis of the quasi-circle characteristic of the target image, we proceed to maximize the erosion with circular structure in order to prevent under-segmentation. Finally, we use the watershed algorithm to segment the gray image based on distance transform. So we can separate the target from each other to achieve the accurate counting purpose. By using the proposed algorithm in the article, we obtain satisfactory segmentation results of the quasi-circle overlapping image of the bars' end face image.

A kind of control system of killing oxygen by adding aluminum process is described in this thesis. The prediction model Alcan amount is the core of the process. In this system, the signal separation and the rolling optimization method based on observational data sequence given oxygen Alcan hybrid model for online. The practical application has achieved good results.

The research on 3-D tracking and positioning based on C-arm is mainly completed by the prediction algorithm.This paper mainly introduces some popular prediction algorithms caused by respiration motion which can change the targets position irregularly. Meanwhile, this paper has made a summary and induction about the prediction algorithms. And we discuss the development trends as well.