Laser image spot processing for sea oil film thickness measurement

The method of extracting the center coordinate of the light spot using the improved Gaussian fitting is presented to measure the thickness of oil film on water surface with differential laser trigonometry. The image of the light spot from the upper and lower surfaces of the oil film under measurement is extracted by the entropic threshold, and the center coordinate of the light spot is obtained by Gaussian fitting of the ascending edge and descending edge data of the light spot image extracted. Experimental measurement is carried out to verify the performance of the method. The range of the measurement is 0.1–10?mm and the maximum deviation between the nominal value and the measured value is less than?±23?μm for block gauges. The research results show that the algorithm presented in this paper is successful and feasible.     

图像处理中的绝缘子缺陷检测方法

目前国内外生产上钢化玻璃绝缘子的缺陷检测均采用传统的人工肉眼检测方法,难以满足大规模、自动化生产的需要.为此,结合基于形态学的特征检测和基于BP神经网络的缺陷分类检测,提出一种基于图像处理的玻璃件缺陷检测方法.实验结果证明了该方法的有效性.     

含废机油混装乳化炸药可行性研究

为研究废机油用于制备混装乳化炸药的可行性,采用正交实验的方法制备乳化基质,利用偏光显微镜和扫描电镜记录新制、自然储存和高、低温循环乳化基质的微观形态,并分析了废机油对乳化炸药成乳性、储存性能和爆炸能力的影响。结果表明:废机油和乳化剂在油相中的含量会影响乳化基质的成乳性,废机油与成乳性指数的相关性指数为-0.697,废机油和乳化剂的比值与成乳性指数的相关性指数为-0.674。说明废机油比例越高,废机油与乳化剂的比值越高,越难形成乳化基质。成乳后含废机油乳化基质的储存性与废机油在油相中的含量没有明显的直接关系,含废机油混装乳化炸药爆速与不含废机油混装乳化炸药接近,含废机油乳化炸药可以满足工程爆破对乳化炸药的性能要求。     

含废机油混装乳化炸药可行性研究

为研究废机油用于制备混装乳化炸药的可行性,采用正交实验的方法制备乳化基质,利用偏光显微镜和扫描电镜记录新制、自然储存和高、低温循环乳化基质的微观形态,并分析了废机油对乳化炸药成乳性、储存性能和爆炸能力的影响。结果表明:废机油和乳化剂在油相中的含量会影响乳化基质的成乳性,废机油与成乳性指数的相关性指数为-0.697,废机油和乳化剂的比值与成乳性指数的相关性指数为-0.674。说明废机油比例越高,废机油与乳化剂的比值越高,越难形成乳化基质。成乳后含废机油乳化基质的储存性与废机油在油相中的含量没有明显的直接关系,含废机油混装乳化炸药爆速与不含废机油混装乳化炸药接近,含废机油乳化炸药可以满足工程爆破对乳化炸药的性能要求。     

Adhesion status of platelets under flow conditions by digital image processing

Abstract

The kinetics and distribution of platelet deposition on protein‐coated surfaces were studied in an in vitro flow system. When fluorescence‐labeled platelets in whole blood flow through a flow chamber that is composed of a glass plate, platelets will deposit onto the protein‐coated surface in a time‐and location‐dependent manner. A combination of fluorescence video microscopy and a digital image processing system allowed us to systematically study thrombosis kinetics under various flow conditions, with different biomaterials and forms of blood.

In this paper, the image processing and pattern recognition techniques have been developed to quantify adhered platelets from numerous video frames. The dynamic adhesion status (newly attached, staying, detached) has been calculated automatically by software developed on an IBM/PC/386. These morphometric parameters as a function of flow rate and type of biomaterials can be determined experimentally.     

LIP多重微区域分解算法扩展数字图像动态范围

CCD/CMOS 图像传感器的饱和电流和背景噪音使得一次曝光很难超过 60-80dB 的动态范围。用 LIP(Logarithmic image processing)模式将图像转换为灰色调函数,再将基于 LIP 模式的非线性多重微区域图像分解算法进行改进,可以适应不同亮度的单幅图像处理,提高了可分辨信息量和图像对比度,同时抑止了噪声。质量评价显示,该算法能将 MOS 等级四的源图像提高到等级一。     

图像处理在自动焊接中的应用和展望

图像处理技术在自动焊接领域的应用已引起国内外学者的广泛重视。通过图像传感技术获取焊接熔池直观丰富的图像信息，使用高效的图像处理算法，提取焊接熔池的特征信息，用以实现自动焊接过程质量实时传感与控制。本文综合论述了图像处理技术在自动焊接中的应用原理、数字图像的采集方法、数字图像的特征信息定义、广义数字图像处理技术及其对自动化焊接理论研究和实践应用的推动作用。通过总结图像处理技术的研究和应用现状，综合分析了图像处理技术在现代焊接技术中发展和应用的前景。     

图像处理技术在板料激光弯曲中的应用

为了提高激光弯曲过程数值模拟结果的验证精度,用图像处理技术对铝合金板料AA6056进行了激光弯曲变形过程的实时测量.自行设计了硬件测量系统和软件的测试系统,使用MV21300UM CCD拍摄板料上测量点在激光照射过程中的动态变化过程,通过软件测试系统中实时采集软件记录动态变化过程、图像处理软件进行图像处理,得到了测量点动态变化的实测曲线.实测曲线表明,板料厚度对激光弯曲过程的位移变化影响较大,板料越薄,边界效应越明显,使得位移的变化曲线越易出现突变.实验结果证明该实测方案是可靠有效的.     

深度学习在材料显微图像分析中的应用与挑战

材料的组织结构主要受成分和制备加工工艺的影响,是决定材料性能的关键因素,在材料研发的全周期内具有重要作用。材料组织结构以非结构化图像数据的形式呈现,利用人工经验性的手段进行分析和信息抽取,遗漏了大量的材料学信息和隐含知识。深度学习技术的发展和应用,为材料显微图像中信息的精准、快速、自动获取提供了重要的研究手段。本文从图像处理、图像分析和图像理解3个方面概述了材料显微图像处理与信息挖掘的主要研究内容和关键技术,详细介绍了深度学习在图像分析中的图像识别、图像分割和图像生成3个任务中的研究进展,讨论了深度学习在材料显微图像分析和信息挖掘中的发展方向和挑战。     

Speed estimation of vehicles approaching an intersection: a digital image processing method

Abstract

Most severe car accidents that occur in urban environments involve side impacts at street intersections, even at those regulated with traffic lights. Hence, it is very common to implement a small delay since one road changes to red until the other road changes to green. This delay is intended to avoid accidents in which a vehicle decides to go through the intersection after the sequence green–yellow–red is started, underestimating the time required to overtake the intersection. A better approach is to adjust the delay dynamically, depending on the speed of the vehicles approaching to the intersection. Using the dynamic approach, it is possible to improve traffic flow by reducing unnecessary delays, and to improve safety by applying longer delays when needed. This paper proposes a speed estimation method based on digital image processing of pictures taken with wireless cameras installed on top of existing traffic lights. The algorithm finds a vehicle in two consecutive images (either in day or night condition) and computes its speed by correlation. When a traffic light turns red, the systems estimates the speed of the cars approaching and decides to change the other road to green immediately, or to wait until it is safe to do so. The system was tested with real traffic flow at a street located in the city of Talavera de la Reina, Spain, with vehicles at different speeds. The image processing method proved to be accurate for this application, and adding the advantage of low cost equipment and easy installation results in a very attractive solution.     

流媒体与图像处理的多工位燃气表检定系统

针对当今国内市场上已有的钟罩式气体流量标准检定装置在小量程检定时存在的检定效率低,时间浪费的问题,该系统提出了一种基于流媒体(DirectShow)与数字图像处理技术的多工位燃气表检定方法,可有效地提高检定效率,使原有的检定系统装置更加完善,自动化的程度更高,使之能在工业上更加广泛的应用.     

Introducing a simple method to determine aggregate gradation of hot mix asphalt using image processing

The aggregate gradation is one of the most important parameters in the mechanical properties of hot mix asphalt (HMA). Thus, determining the aggregate gradation is a very significant subject in civil engineering. Usually, to estimate the aggregate gradation, it is required to separate the aggregate from the bitumen, and this operation can be time-consuming and even dangerous related to chemical solvents. Moreover, several computer-based methods have been established to model the internal structure of HMA in two- and three-dimensional methods and can be applied to determine the aggregate gradation, but these methods need special and expensive equipment. Therefore, in this study, a simple approach is introduced to quickly and easily determine the aggregate gradation of HMA from the prepared cross-section images of cylindrical samples using numerical and image-processing techniques such as fitting equation and colour space system. The obtained results indicate that the introduced method can detect the aggregate gradation with high accuracy and can be used as a satisfactory alternative to other expensive methods.     

基于Otsu阈值法与形态学自适应修正的舌像分割方法

为了从原始舌图像中精确分割出舌体以实现中医舌诊的客观化,提出了一种基于Otsu阈值法与形态学自适应修正的舌像分割方法。该方法提取原始舌像的RGB色彩空间与HSV色彩空间中G、B、V通道的信息,运用Otsu阈值法对舌像进行二值化,基于先验知识对目标区域进行聚类,采用形态学运算方法,利用舌体当量直径自适应选取结构元素的大小,对聚类结果进行开启运算修正得到舌像分割结果。基于200幅不同形态、不同舌色类别原始舌像的实验结果表明,该方法能稳定精确地分割出舌体,与传统的Otsu方法及灰度投影-Otsu方法相比,准确率有了很大的提升。     

基于数字图像处理的光切法槽深测量方法研究

在窄浅槽的深度测量方面，常用的测量方法受到很多的限制。对不锈钢管的电火花加工（EDM）的刻槽深度测量，提出了一种在光切法基础上采用电荷藕合器件图像传感器（CCD）获得不锈钢管表面和刻槽底部的图像，运用数字图像处理技术对图像进一步处理的刻槽深度测量方法。介绍了光切法的原理，并详细介绍了对所获得的数字图像进行处理的步骤。实际应用表明，该方法有较高的测量精度。     

火灾探测中动态火焰的数字图像处理

通过模拟火灾实验,利用移动的CCD摄像头实现图像的动态获取与传输.重点研究火焰图像的阈值处理、边缘检测、链码提取等图像处理算法,并且运用Matlab语言编程处理实验图像,计算出火焰图像的面积、周长、圆形度等特征值,从而总结得出火灾发生时具有火焰面积增大、边缘抖动等特征,获得了早期火灾探测的重要判据.     

Three-dimensional atomic imaging of Y and (B12)13 clusters in YB56 by HREM and crystallographic image processing

The three-dimensional atomic image of YB₅₆ was obtained by inverse Fourier transformation of three-dimensional phases and amplitudes in three high-resolution images along [100], [110] and [111] of YB₅₆ crystals. After crystallographic image processing, the image directly showed the three-dimensional potential map of the crystal, which showed (B₁₂)₁₃ clusters and Y atom positions. The present method would be useful for three-dimensional structure analysis in nanoscale regions.     

Pattern recognition,image processing and computer vision in fifth generation computer systems

It is well-known that one of the goals of research for the last two decades or so in pattern recognition and its sub-areas, such as processing, analysis and understanding of image, speech and natural language, and computer vision techniques etc., has always been to develop fundamental techniques for flexible interactive intelligent man-machine interfaces for computers. In this paper, the author tries to argue that for the evolution of fifth generation computer systems (FGCS) as defined by Japanese scientists, some of the things required are realisation and implementation of the advances in pattern recognition and its sub-areas, not only to achieve the man-machine interface with a natural mode of communication, but also for the realisation of the basic mechanisms of inference, association and learning, which are inherent both in pattern recognition and in the core functions of FGCS. The next generation computers will be knowledge-based systems, which form a subdomain of artificial intelligence (a1) techniques, and soa1 provides the essential link between pattern recognition domains and different application systems. No attempt is made to discuss other essential conceptual building blocks, such as software engineering, computer architecture and very large scale integration technology unless these become very relevant in the discussions of concerned topics of the paper. A section on limitations of perception, learning and knowledge for computing machines is also included. This work was funded by the Knowledge-based Computer Systems Project of the Department of Electronics, Government of India.     

超滤法处理油田含油污水膜清洗方法的研究

采用聚砜共混中空纤维超滤膜对油田含油污水进行处理,探讨了不同清洗剂和不同清洗方法对膜通量的恢复效果。试验表明,使用表面活性剂和异戊醇混合溶液为清洗剂,采用负压抽洗和反压冲洗同时进行的方法,可使膜通量恢复率达到９０％以上。     

Principle and realization method of tunnel deformation detection based on image recognition and data transmission technology

To detect the deformation of the tunnel structure based on image sensor networks is the advanced study and application of spatial sensor technology. For the vertical settlement of metro tunnel caused by internal and external stress after its long period operation, the overall scheme and measuring principle of a tunnel deformation detection system is introduced. The image data acquisition and processing of detection target are achieved by the cooperative work of image sensor, ARM embedded system. RS485 communication achieves the data transmission between ARM memory and Host Computer. The database system in station platform analyses the detection data and obtain the deformation state of tunnel inner wall, which makes it possible to early-warn the tunnel deformation and take preventive measures in time.