基于机器视觉的柔性包装袋喷码缺陷检测研究

目的 针对传统喷码检测方法计算量大、字符区域定位不显著、识别准确率较低等不足,提出一种基于机器视觉的柔性包装袋喷码缺陷检测方法。方法 以柔性包装袋上喷码图像为研究对象,以滤波抑噪、阈值处理等技术对图像进行预处理,运用YOLO-V3网络模型对字符区域进行定位,并采用阈值和非极大值抑制算法提高喷码区域定位的显著性,通过改进AlexNet网络结构、运用多特征融合运算等方法,获取更为丰富的图像卷积特征,实现字符串的整体识别,从而提高喷码缺陷识别的准确率。结果 将YOLO-V3联合改进AlexNet的检测方法与传统喷码检测方法进行对比,结果表明,所设计喷码缺陷检测方法的分类准确率达到99.39%。结论 基于机器视觉的柔性包装袋喷码缺陷检测方法在模型计算量、字符区域定位显著性和字符识别准确率都有一定的优势,并有效解决了字符串整体识别的问题。     

食品包装日期喷码检测系统设计

目的为了提高食品包装过程中喷码检测的准确度,基于机器视觉提出一种喷码缺陷检测方法。方法分析自动喷码系统结构和工艺流程,包括搬运机械手、传送装置、喷码装置、检测装置等。以扫码检测为重点研究对象,利用机器视觉采集图像,通过图像处理算法实现喷码缺陷检测,包括模板匹配算法和垂直投影方法。同时给出缺陷检测流程,主要由图像分割、字符校正和分割、字符分割、缺陷检测等步骤组成。结果实验结果表明,所述喷码检测方法的识别成功率可以达到99%,识别成功率较高。结论该方法能够有效处理漏印等喷码缺陷,可以代替人工实现食品包装的自动化分拣。     

基于比例特征的区域分割算法在药板缺陷检测中的研究

目的 为解决铝塑泡罩药板图像ROI区域定位慢、精度差等问题,本文提出一种基于比例特征的泡罩区域分割算法,该算法可以快速定位并分割泡罩ROI区域,结合图像相关性特征算法对铝塑泡罩药板进行缺陷检测。方法 首先通过工业相机采集药品包装生产线上的药板原始图像,接着使用Blob分析从原始图片中分离出铝塑泡罩主体部分,然后通过仿射变换将图像放置在中心区域,并使用比例特征分割算法对泡罩区域进行分割,最后通过金字塔加速的NCC算法完成缺陷检测。结果 实验结果表明,基于比例特征分割后的图像平均NCC匹配时间为9 ms,在缺陷样本占比20%的实验中误检率为0.167%,漏检率为0.556%。结论 通过比例特征分割出精准的泡罩ROI区域结合改进的NCC算法,在拥有较高准确率的同时大幅减少了缺陷检测时图像匹配的时间,能较好地完成铝塑泡罩药板的缺陷检测任务。     

基于多对象匹配与融合字符特征的印刷质量检验方法

目的 为了增强字符配准对字符位姿变化的鲁棒性和识别能力,以及印刷质量检验精度和缺陷类型分析对不同字符产品的自适应性,提出一种基于多对象匹配与融合字符特征的印刷质量检验方法。方法 采用多张合格字符样品图像进行模板构建;借助多对象匹配来配准多个待检验的字符,消除字符位姿的变化对字符配准的影响;进行逐像素的比对,检验字符区域的质量;利用灰度阈值分割以及Sobel边缘检测,将字符区域分成3个待检验的局部特征区域：边缘、前景、后景;进而获取边缘完整性,前景面积和灰度,背景面积和灰度这些显著的字符特征,由多张字符样品训练每个特征的自适应的合格范围;将其组合,形成融合字符特征,分析缺陷的类型。结果 测试数据表明,针对不同种类、不同精度要求的字符产品,所提方法对于字符质量的判断准确率达到100%,对缺陷类型的分类准确率保持在84.2%以上。结论 所提字符质量检验方法拥有良好的鲁棒性与自适应性,在包装、印刷等行业具备较高的应用价值。     

多参数数显仪表的自动识别方法研究

为提高数显仪表的识别精度和速度,提出一种针对多参数数显仪表的自动识别方法,并以电焊机的电流和电压作为算法验证。对于数显表显示的字符3和7,由于这两个字符的宽度原因,传统的穿线法会导致较高的错误识别率,因此提出一种用倾斜直线代替传统的竖直直线的改进方法。由于数显仪表的字符颜色种类繁多,利用V通道(HSV色彩空间)特征解决各种颜色数显的识别,并且减少计算量、提高定位精度。通过分析字符的特征,利用字符右侧边界的高度信息快速确定小数点位。实验结果表明该算法能够以较高精度实时识别电焊机上的多参数字符和小数点。静态识别率为99%,平均识别时间7.2 ms/张,相机动态识别率为98.4%,平均识别时间为8.5 ms/张。     

基于特征检测的数字仪表数码快速识别算法

为对数显类仪表的显示数据进行自动识别与监测,提高该类仪表的自动化水平,需要研究仪表数码快速识别算法。该文提出一种基于特征提取的数字仪表数码快速直接识别算法。将图像进行预处理后,对数显屏幕进行定位。通过列切实现单个数码字符切割,对单个数码字符进行七段特征检测和五线相交检测,实现对正体数码和斜体数码的快速直接识别。实验表明,算法基本可以满足各种仪表数码的识别需求,识别速度快、准度高。     

基于卷积神经网络的模糊车牌自动识别

目前,清晰的车牌识别算法已经成熟,但是对于人眼不能识别的模糊车牌,传统车牌识别算法的识别率较低或者根本无法识别。鉴于此,提出了一种基于卷积神经网络的车牌字符识别算法。制作了含9 720幅模糊字符样本集,用8 748幅样本对卷积神经网络进行训练,测试样本时,先对模糊车牌字符进行盲分割等预处理,再调用训练好的卷积神经网络对盲分割后的字符进行识别。实验结果表明:该算法对训练集的准确识别率约为99.17%,对测试集的准确识别率约为93.32%,这说明该算法对模糊车牌的识别具有鲁棒性,能应用于各种场景。     

一种基于结构特征的票据印刷号码识别方法

目的为保证含有号码印刷错误的票据不流入社会,研究一种新的用于票据印刷在线检测系统的号码识别方案。方法提出一种基于结构特征的票据号码识别方法。先对票据图像进行采集、灰度化、二值化、去噪、倾斜校正、字符定位、单字符分割及归一化等一系列预处理。建立一种基于结构特征的号码识别分类器,再根据票据中每个号码的结构特征值,对号码进行分类识别。结果实验结果表明,利用文中提出的结构特征方法,票据号码识别率达到99%以上。结论经过对大量实际发票号码的识别测试实验,该方法有较强的抗干扰性,识别算法速度快、精度高。     

基于机器视觉的燃气表表观缺陷自动检测方法

针对膜式燃气表表观缺陷用普通拍照难以高精、高效检测的难题,提出了一种基于机器视觉的燃气表表观缺陷自动检测方法。依据均值滤波算法去除图像中噪声后,基于Otsu自适应分割方法精准分割缺陷与背景区域,在此基础上,采用连通域算法对缺陷轮廓进行提取。实验结果表明,该方法针对划痕、孔洞、表皮剥落等缺陷的检测精度达100%,检测速度为0.42f/s以内,可以有效解决当前燃气表缺陷检测技术效率低、成本高的难题。     

基于神经网络的玻璃缺陷声学检测方法

描述了一种通过声学信号检测玻璃制品缺陷的方法。在实现步骤上,首先采集了不同缺陷类型的玻璃瓶敲击声,然后经过频谱变换及小波包变换,将敲击信号映射至不同的变换域中,并在每个变换域中提取信号的特征,从而将样本的缺陷信息对应为统计特征和物理特征,并采用基于互信息量的特征选择算法对特征空间进行降维;降维后的特征子集作为后向传播神经网络的输入参数,再由该神经网络实现对玻璃缺陷的自动化检测。结果表明,在已有实验样本数据下,该缺陷检测算法能准确高效地检测出存在缺陷的样本,识别结果的F-值稳定在95%左右。     

Automatic defect inspection system of colour filters using Taguchi-based neural network

A coloured filter is a critical part of an LCD panel, especially to present a high quality colour display. At present, the defect detection of colour filters is conducted by manual inspection in the final product stage. However, poor detection efficiency and subjective judgment of manual inspection undermine accuracy. Therefore, this study applied image processing technology and the neural network to detect surface defects of colour filters in order to prevent losses arising from incorrect detection, lower production costs, and effectively improve yield. A back-propagation neural network (BPNN) classifier was selected to train the features. The results showed that the proposed method can be successfully applied in defect detection of colour filters to reduce artificial detection errors. In addition, the Taguchi method was used with BPNN to save time searching optimal learning parameters by the trial and error method, which achieves faster convergence, smaller convergent errors and better recognition rate. The results proved that the root-mean-square error (RMSE) of the Taguchi-based BPNN at final convergence is 0.000254, and recognition rate reaches 94%. Therefore, the proposed method has good effects in detecting the micro defects of a colour filter panel.     

基于机器视觉的编织袋表面缺陷检测系统设计与实现

目的 针对编织袋生产中表面缺陷检测效率和精度低等问题,应用机器视觉技术于编织袋表面缺陷检测,进而提高编织袋的生产效率。方法 基于机器视觉设计编织袋表面缺陷检测系统:首先为了降低背景灰度变化对缺陷检测的影响,研究一种同时具有噪声滤除与图像增强功能的预处理算法;其次选取二维最大熵值法对预处理后的编织袋图进行分割,并采用改进遗传算法对它进行优化以增强算法的收敛速度和效果;然后利用特征提取结合形态学处理的方法实现了编织袋表面缺陷的识别与分类;最后应用连通域进行分析,对分类出的缺陷进行统计与定位以获取缺陷的尺寸以及位置信息。结果 采集了200个编织袋缺陷样本,采用文中编织袋表面缺陷检测系统对编织袋样本进行缺陷识别,平均识别准确率为94.0%,处理一幅编织袋图像的时间约为600 ms。结论 该系统具有较高的识别效率和正确率,可实现编织袋表面缺陷的快速检测,满足工业生产的需求。     

An Elevator Button Recognition Method Combining YOLOv5 and OCR

Fast recognition of elevator buttons is a key step for service robots to ride elevators automatically. Although there are some studies in this field, none of them can achieve real-time application due to problems such as recognition speed and algorithm complexity. Elevator button recognition is a comprehensive problem. Not only does it need to detect the position of multiple buttons at the same time, but also needs to accurately identify the characters on each button. The latest version 5 of you only look once algorithm (YOLOv5) has the fastest reasoning speed and can be used for detecting multiple objects in real-time. The advantages of YOLOv5 make it an ideal choice for detecting the position of multiple buttons in an elevator, but it’s not good at specific word recognition. Optical character recognition (OCR) is a well-known technique for character recognition. This paper innovatively improved the YOLOv5 network, integrated OCR technology, and applied them to the elevator button recognition process. First, we changed the detection scale in the YOLOv5 network and only maintained the detection scales of 40 * 40 and 80 * 80, thus improving the overall object detection speed. Then, we put a modified OCR branch after the YOLOv5 network to identify the numbers on the buttons. Finally, we verified this method on different datasets and compared it with other typical methods. The results show that the average recall and precision of this method are 81.2% and 92.4%. Compared with others, the accuracy of this method has reached a very high level, but the recognition speed has reached 0.056 s, which is far higher than other methods.     

一种针对畸变印刷品字符校正的多项式自寻优改进方法

目的针对畸变印刷品字符校正过程中无畸变先验知识、传统方法效率低且精度差的问题,提出一种以多项式自寻优改进算法为核心的字符校正方法。方法将待测字符区域视为小篇幅图像,通过初次校正确定畸变区域,以待测图像与标准图像的最小差分结果为优化目标,利用菌群算法在畸变区域中进行校正控制点的自寻优运算,从而建立校正函数对字符畸变区域进行校正,并通过Matlab仿真加以实现。结果该方法平均校正精度低于0.6像素,运行时间低于0.12 s,达到了对畸变字符快速准确校正的目的。结论该自寻优改进方法克服了人工操作的弊端,对畸变字符进行了有效校正,有助于提高后续缺陷检测的精度和效率。     

自然场景图像的字符识别方法

目的基于大津算法(Otsu算法)对图像进行分割,利用光学字符识别方法对自然场景图像中的英文字符进行识别。方法首先用分块Otsu算法对图像进行初步的二值化,然后通过对二值化结果的分析,把原始的输入图片分割成单个字符的子图,再对各子图重新用Otsu算法进行二值化,最后对最终得到的二值化结果进行识别,再结合之前得到的每幅图的字符数量信息和词典信息,对识别结果进行修正,得到最终的识别结果。结果在ICDAR2013数据集上测试文中算法,单词正确识别率为46.03%,总编辑距离为474.5。结论文中提出的以Otsu为基础的分块识别算法,能够更好地分割复杂背景图像的背景和文本,同时结合词典信息对识别结果进行了修正,改善了识别效果。     

The algorithm of accelerated cracks detection and extracting skeleton by direction chain code in concrete surface image

Due to concrete surface roughness, uneven illumination, shadows, complex background and other disruptive factors, the traditional image processing-based concrete crack detection method cannot accurately detect concrete cracks, especially unclear ones and some tiny ones. The crack detection method based on the percolation model, which fully considered the low brightness and slenderness of the cracks, can accurately detect unclear and tiny cracks. But this method is time-consuming, and in some cases, it may cause fractures on the detected cracks. In order to solve these problems, this paper proposed an improved algorithm of image crack inspection based on the percolation model, which can reduce processing time through reducing the number of percolated pixels. To reconnect the fractured cracks, this method extracts the skeleton of cracks first by using an algorithm of skeleton extraction based on direction chain code. Then this paper proposed a region extension-based algorithm to reconnect part of the fractured cracks. Experimental results showed that this algorithm can significantly accelerate crack detection and maintain high detection precision.     

粉状炸药自动包装工艺的改进研究

目的 针对印刷品表面缺陷检测中计算实时性差、缺陷类型识别率不高等问题,提出一种改进灰度共生矩阵(GLCM)的印刷品表面缺陷检测方法。方法 首先对主流的缺陷检测流程进行优化设计,通过对图像进行预处理和差分操作,判断待测印刷品表面是否存在形状缺陷;然后针对传统灰度共生矩阵的特征提取维度高、信息易丢失、旋转不变性差等问题,设计一种综合考虑效率和实时性的缺陷区域特征参数提取算法;最后结合得到的特征参量,通过基于支持向量机的分类器完成不同形状缺陷的分类识别。结果 实验结果表明,文中所设计的改进算法所提取的特征参量更能精确表征缺陷区域的特征,同时,特征参数的提取时间和缺陷分类识别率等指标均比传统检测方法更有优势。结论 在保证计算实时性的前提下,文中所设计的检测方法能有效完成印刷品表面缺陷区域的纹理特征识别能力,具有较高的分类识别率。     

Text Detection and Recognition for Natural Scene Images Using Deep Convolutional Neural Networks

Words are the most indispensable information in human life. It is very important to analyze and understand the meaning of words. Compared with the general visual elements, the text conveys rich and high-level moral information, which enables the computer to better understand the semantic content of the text. With the rapid development of computer technology, great achievements have been made in text information detection and recognition. However, when dealing with text characters in natural scene images, there are still some limitations in the detection and recognition of natural scene images. Because natural scene image has more interference and complexity than text, these factors make the detection and recognition of natural scene image text face many challenges. To solve this problem, a new text detection and recognition method based on depth convolution neural network is proposed for natural scene image in this paper. In text detection, this method obtains high-level visual features from the bottom pixels by ResNet network, and extracts the context features from character sequences by BLSTM layer, then introduce to the idea of faster R-CNN vertical anchor point to find the bounding box of the detected text, which effectively improves the effect of text object detection. In addition, in text recognition task, DenseNet model is used to construct character recognition based on Kares. Finally, the output of Softmax is used to classify each character. Our method can replace the artificially defined features with automatic learning and context-based features. It improves the efficiency and accuracy of recognition, and realizes text detection and recognition of natural scene images. And on the PAC2018 competition platform, the experimental results have achieved good results.