基于极限学习机的焊点质量检测

焊点加工直接影响电子产品的可靠性,焊点的检测对产品质量的提高尤为重要。应用主成分分析与极限学习机对焊点质量进行检测。首先通过中值滤波和分水岭算法对焊点图像进行预处理,得到焊点轮廓及区域划分情况并用主成分分析法进行降维;然后采用200个隐含层网络节点、sigmoid响应函数的极限学习机算法对预处理结果进行分类。测试结果表明,极限学习机算法能够对焊点精确分类,与支持向量机、邻近算法、卷积神经网络相比,取得更高的检测准确率,检测时间更短。     

基于PCA和粒子群优化算法的焊点缺陷识别

针对生产线上的表面贴装技术(SMT）焊点图像的特点,提出了一种基于PCA和粒子群算法-误差反向传播（PSO-BP）神经网络的焊点缺陷识别方法。首先使用图像处理技术和CCD传感器对PCB焊点图像进行预处理,采用中值滤波、灰度图像增强、全局阈值法等方法,有效抑制噪声干扰并提高了图像对比度,提取出较好的图像特征。然后运用主成分分析法提取包含焊点86.6%特征信息的5个主成分,并输入到经粒子群算法改进后的BP神经网络。通过具体的实验分析,结果表明改进的BP神经网络具有较好的识别分类效果,能够对正常、多锡、少锡、漏焊四种不同类型的焊点进行识别,准确率达93.22%,算法可靠,在实际生产中能够有效的提高检测效率。     

基于图像处理的焊点缺陷识别方法的研究

针对生产线上的SMT（表面贴装技术）焊点图像的特点,研究基于图像处理的焊点缺陷识别算法,采用中值滤波、迭代阈值法、Sobel算子等一系列的图像预处理方法,有效抑制了噪声干扰,提高了图像的对比度,提取出较好的图像特征。采用径向基函数（RBF）神经网络对四种焊点缺陷进行识别。仿真结果表明,RBF神经网络很好地克服BP神经网络训练过程收敛依赖于初值和可能出现局部收敛的缺陷,具有较快的运算速度和较好的检测结果,基于图像处理的焊点识别方法是有效的。     

一种小波域内的BP神经网络图像压缩方法

通过时Mallat算法和提升小波变换的比较,并分析图像经过小波变换后系数的分布特点,提出了一种新的将提升小波变换和BP神经网络相结合的图像压缩方法.根据小波变换后图像的绝大部分能量都集中在小波变换的低频部分这一特性,利用BP神经网络,对不同的频带子图进行不同压缩比的压缩,从而得到高质量的重构图像.结果表明,该算法不仅有较高的压缩比,而且获得了质量较高的重构图像,对背景简单的图像压缩效果尤为明显.     

基于双树小波和神经网络的图像降噪与增强

为提高在图像降噪过程中对图像细节信息的保护能力,提出一种基于双树小波和神经网络的图像降噪与增强算法.通过Canny算子检测图像的边缘,通过shearlet变换将噪声图像分解为高频子带和低频子带;使用卷积网络保留边缘区域,通过两层剪切波滤波器组对非边缘区域进行降噪,通过神经网络对总体图像进行增强.实验结果表明,该算法可以实现较高的降噪性能,有效地提高图像的质量.     

基于神经网络与对比度的多聚焦图像融合技术

提出了一种基于小波对比度和神经网络的多聚焦图像融合算法。首先对各源图像进行小波变换，根据变换后系数计算出图像的小波对比度，选取源图像部分区域小波对比度作为前馈神经网络的训练样本，调整神经网络权重；然后用训练好的神经网络组合融合图像的小波系数，对组合后的系数进行一致性校验；最后对该系数进行小波逆变换，得到融合图像。实验结果表明，该算法能够较好地解决多聚焦图像融合问题，生成的融合图像效果优于传统图像融合方法。     

基于小波神经网络的医学图像分类方法

为了提高乳腺癌早期诊断的准确率,将小波理论与神经网络理论相结合提出改进的小波神经网络算法。将经过预处理的医学图像提取特征值,然后利用基于改进的小波神经网络算法的分类器对医学图像进行分类。通过实验表明此分类器具有较高的分类精度,是有效和可行的;与单独使用后向传播神经网络算法相比分类效果也得到了改善。     

基于神经网络的实用小波域零水印技术

提出一种基于神经网络的小波域零水印技术。不同于传统的水印算法,零水印技术对宿主图像进行离散小波变换,并在低频子带随机选择一些系数作为提取的特征,将其作为水印用于版权证明,以避免嵌入水印导致的图像变形。通过建立神经网络模型对所选特征系数进行管理、存储和检测,以提高算法的实用性。     

基于小波包变换与Wiener滤波的SMT焊点图像去噪技术

针对目前SMT(surface mount technology)焊点图像去噪效果不理想的问题,提出了一种基于小波包变换与wiener滤波的SMT焊点图像去噪新方法.利用小波包对图像进行分解,可以同时对SMT焊点图像的低频和高频部分进行多层分解,有利于保留图像信息,减少噪声对图像的影响.通过对图像的小波包系数的分析,对小波包树高频系数进行Wiener滤波,保留低频系数;然后进行小波包反变换,重构得到SMT焊点去噪后图像.实验表明,提出的方法不仅可以有效地去除SMT焊点图像的噪声,而且能很好地保留原图像的边缘信息,与传统方法相比,去噪性能和去噪声效果有一定的提高.     

异型冲压工件边缘检测算法研究

为了不断提高产品质量和生产效率,冲压工件缺陷自动在线检测技术在生产过程中显得日益重要。针对这一需求,提出了基于小波分解的神经网络和快速模糊算法相融合的异型冲压工件边缘检测算法。神经网络算法的引入,克服了快速模糊算法在图像边缘检测时高频信号得不到有效利用和检测速度较慢等问题。在提高算法效率的同时,增强了算法的适应性。与经典的边缘检测算法相比较,得到的处理图像更加清晰完整。     

Pattern classification of solder joint images using a correlation neural network

This paper presents a method of classifying solder joints on printed-circuit boards (PCB), using a neural-network approach. Inherently, the surface of the solder joints is curved, tiny and specularly reflective; it induces a difficulty of taking good images of the solder joints. The shapes of the solder joints tend to vary greatly with soldering conditions; solder joints, even when classified into the same soldering quality, have very different shapes. Furthermore, the position of the joints is not consistent within a registered solder pad on the PCB. Due to these aspects, it has been difficult to determine the visual features and classification criteria for automatic solder-joint inspection. In this research, the solder joints, imaged by using a circular, tiered illumination system of three colored lamps, are represented as red, green and blue colored patterns, showing their surface-slopes. Cross-correlation and auto-correlation of the colored patterns are used to classify the 3D shapes of the solder joints by their soldering qualities. To achieve this, a neural network is proposed, based on a functional link net, with two processing modules. The first preprocessing module is designed to implement the calculation of the correlations in functional terms. The subsequent, trainable module classifies the solder joints, based upon the capability learned from a human supervisor. The practical feasibility of the proposed method is demonstrated by testing numerous commercially manufactured PCBs.     

An efficient solder joint defects method for 3D point clouds with double-flow region attention network

In electronics mass-production, image-based methods are often used to detect the solder joint defects for achieving high-quality assurance with low labor costs. Recently, deep learning in 3D point clouds has shown an effective form of characterization for 3D objects. However, existing work rarely involves defect detection for PCBs based on 3D point clouds. In this paper, we propose a novel neural network named double-flow region attention network (DoubRAN) to detect defects of solder joints with 3D point clouds. On the one hand, a binocular lidar system is designed to efficiently capture 3D point clouds of solder joints. On the other hand, a fine-grained method named region attention network (RAN) is designed to detect defects, which attends on the region of interest directly by backpropagation without bounding box annotation. To evaluate the performance of our proposed network, we conduct extensive experiments on a unique dataset built by ourselves. The experimental results show that the region of interest extracted by RAN is consistent with the basis for human evaluation of solder joint quality. Besides, the defect detection results of DoubRAN meet factory requirements.     

Automated extraction of PCB components based on specularity using layered illumination

This paper investigates the methodologies for locating and identifying components on a printed circuit board (PCB) used for surface mount device inspection. It’s the foundation of other inspections, such as solder joint inspection, component type recognization and so on. The proposed scheme consists of two stages: solder joint extraction and protective coating extraction. This work uses automatic multilevel thresholding approach for detecting specular areas which contain solder joints. Some invalid specular areas, such as markings and via-holes are recognized and removed by comparing the colour distribution features of the target objects and the reference objects. A novel approach based on connection graph and the segmented gray-scale PCB images is developed to classify all recognized solder joints as several clusters. And then, the protective coating is extracted by the positions of the clustered solder joints. Experimental results show that the proposed method can recognize most of components effectively.     

An inspection and classification method for chip solder joints using color grads and Boolean rules

In order to improve the comprehensive performance of solder joints inspection in three aspects, i.e. high recognition rate, detailed classification of defect types and fast inspection speed, a new detection and classification algorithm of the chip solder joints based on color grads and Boolean rules is developed in this paper. Firstly, the region features, evaluation features and color grads’ features are defined and extracted based on the special solder joint image, which is acquired by a particular image acquisition system composed of a 3-CCD color digital camera and a 3-color (red, green, and blue) hemispherical LED array illumination. Secondly, the models of solder joint types are built based on extracted features and statistical characteristics of solder joint types. Thirdly, the detection and classification method is designed and presented using Boolean rules, then eight common solder joint types, including the acceptable solder joint, pseudo, no solder, lacked solder, excess solder, shifted, tombstone, and miss component, can be classified and detected by the proposed algorithm. Fourthly, the proposed algorithm is optimized to improve the inspection speed based on a parallel computing method. Finally, to evaluate the performance of the proposed method, 79 pieces of PCBs with defects were inspected by the commercial AOI system developed by the authors which integrates the proposed algorithm. Experiment and result analysis illustrates that the proposed method is better than other methods in three aspects, it can detect and classify properly all the eight common types of solder joints, its detailed classification, and high correct rate, which is up to 97.7%, are more useful to the quality control in the manufacturing process, and its inspection speed is faster, thus helping us to improve the efficiency of the manufacturing process.     

基于混合关节肢体模型的深度人体姿态估计方法

提出基于关节外观和关节间空间关系的模型与深层神经网络结构(DCNN)相结合的混合模型,解决人体姿态估计问题.首先,对人体构建图像模型以表示人体关节与肢体.然后,根据标注信息将图像分解为以关节为中心的若干图像块,作为训练输入数据.最后,得到一个可以解决多个分类的DCNN网络,用于人体姿态估计.文中方法对人体表示更灵活,有效提升关节点的检测率及正确检测的比率.     

Design and development of automatic visual inspection system for PCB manufacturing

Inspection of solder joints has been a critical process in the electronic manufacturing industry to reduce manufacturing cost, improve yield, and ensure product quality and reliability. This paper proposes two inspection modules for an automatic solder joint classification system. The “front-end” inspection system includes illumination normalisation, localisation and segmentation. The “back-end” inspection involves the classification of solder joints using the Log-Gabor filter and classifier fusion. Five different levels of solder quality with respect to the amount of solder paste have been defined. The Log-Gabor filter has been demonstrated to achieve high recognition rates and is resistant to misalignment. This proposed system does not need any special illumination system, and the images are acquired by an ordinary digital camera. This system could contribute to the development of automated non-contact, non-destructive and low cost solder joint quality inspection systems.     

Wavelet-based image interpolation using multilayer perceptrons

Changing the resolution of digital images and video is needed image processing systems. In this paper, we present nonlinear interpolation schemes for still image resolution enhancement. The proposed neural network interpolation method is based on wavelet reconstruction. With the wavelet decomposition, the image signals can be divided into several time–frequency portions. In this work, the wavelet decomposition signal is used to train the neural networks. The pixels in the low-resolution image are used as the input signal of the neural network to estimate all the wavelet sub-images of the corresponding high-resolution image. The image of increased resolution is finally produced by the synthesis procedure of wavelet transform. In the simulation, the proposed method obtains much better performance than other traditional methods. Moreover, the easy implementation and high flexibility of the proposed algorithm also make it applicable to various other related problems.     

A wavelet-based multi-dimensional temporal recurrent neural network for stencil printing performance prediction

The solder paste printing (SPP) is a critical procedure in a surface mount technology (SMT) based assembly line, which is one of the major attributes to the defect of the printed circuit boards (PCBs). The quality of SPP is influenced by multiple factors, such as the squeegee speed, pressure, the stencil separation speed, cleaning frequency, and cleaning profile. During printing, the printer environment is dynamically varying due to the physical change of solder paste, which can result in a dynamic variation of the relationships between the printing results and the influential factors. To reduce the printing defects, it is critical to understand such dynamic relationships. This research focuses on determining the printing performance during printing by implementing a wavelet filtering-based temporal recurrent neural network. To reduce the noise factor in the solder paste inspection (SPI) data, this research applies a three-dimensional dual-tree complex wavelet transformation for low-pass noise filtering and signal reconstruction. A recurrent neural network is utilized to model the performance prediction with low noise interference. Both printing sequence and process setting information are considered in the proposed recurrent network model. The proposed approach is validated using practical dataset and compared with other commonly used data mining approaches. The results show that the proposed wavelet-based multi-dimensional temporal recurrent neural network can effectively predict the printing process performance and can be a high potential approach in reducing the defects and controlling cleaning frequency. The proposed model is expected to advance the current research in the application of smart manufacturing in surface mount technology.