基于机器视觉的轮胎表面缺陷检测系统的研究与应用

在传统的轮胎表面缺陷依靠人工检测,存在劳动强度高、受人的主观影响大以及效率低下的问题。针对这一现象,研究了一种基于机器视觉的轮胎表面缺陷3D检测系统。该系统依靠机器视觉系统获取检测轮胎的表面图像,然后创建3D模型、判定缺陷类型,最终实现实时自动预警,为轮胎生产商提供一种自动化检测方案。系统集成了先进的技术、软件和工具,配套的信息管控系统可以对轮胎型号和生产数据进行采集、存储、分析,以便在生产过程中实现更高效、更可靠的质量控制,具有较高的实际应用推广价值。     

平面设计中视觉与触觉的审美构建

目的探索视觉与触觉在平面设计中的多元化呈现及应用路径。方法立足于平面设计中的审美与功能的双向视角,从视觉与触觉对平面设计的艺术潜力与价值进行挖掘,总结两者在平面设计中必须遵循的秩序性、冲击感和功能性三大原则,并在此基础上深度探寻应用领域,总结两者共同作用下的平面设计在合理构图、色彩搭配、材质升级、强化交互等方面的创新与突破,展示其中的典型案例,总结更高层面的审美价值的表达与创作。结论良好的触觉感知及视觉冲击在平面设计的发展壮大过程中发挥着重要作用,在有效提升平面设计水平的基础上,深度挖掘出平面设计本身的情趣,最大限度地满足了人们的审美需求,也找到了彼此融合与发展的共促路径。     

Image Super-Resolution Based on Generative Adversarial Networks: A Brief Review

Single image super resolution (SISR) is an important research content in the field of computer vision and image processing. With the rapid development of deep neural networks, different image super-resolution models have emerged. Compared to some traditional SISR methods, deep learning-based methods can complete the superresolution tasks through a single image. In addition, compared with the SISR methods using traditional convolutional neural networks, SISR based on generative adversarial networks (GAN) has achieved the most advanced visual performance. In this review, we first explore the challenges faced by SISR and introduce some common datasets and evaluation metrics. Then, we review the improved network structures and loss functions of GAN-based perceptual SISR. Subsequently, the advantages and disadvantages of different networks are analyzed by multiple comparative experiments. Finally, we summarize the paper and look forward to the future development trends of GAN-based perceptual SISR.     

Transforming Hand Drawn Wireframes into Front-End Code with Deep Learning

The way towards generating a website front end involves a designer settling on an idea for what kind of layout they want the website to have, then proceeding to plan and implement each aspect one by one until they have converted what they initially laid out into its Html front end form, this process can take a considerable time, especially considering the first draft of the design is traditionally never the final one. This process can take up a large amount of resource real estate, and as we have laid out in this paper, by using a Model consisting of various Neural Networks trained on a custom dataset. It can be automated into assisting designers, allowing them to focus on the other more complicated parts of the system they are designing by quickly generating what would rather be straightforward busywork. Over the past 20 years, the boom in how much the internet is used and the sheer volume of pages on it demands a high level of work and time to create them. For the efficiency of the process, we proposed a multi-model-based architecture on image captioning, consisting of Convolutional neural network (CNN) and Long short-term memory (LSTM) models. Our proposed approach trained on our custom-made database can be automated into assisting designers, allowing them to focus on the other more complicated part of the system. We trained our model in several batches over a custom-made dataset consisting of over 6300 files and were finally able to achieve a Bilingual Evaluation Understudy (BLEU) score for a batch of 50 hand-drawn images at 87.86%     

High quality 3D reconstruction based on fusion of polarization imaging and binocular stereo vision

Polarization imaging can retrieve inaccurate objects’ 3D shapes with fine textures, whereas coarse but accurate depths can be provided by binocular stereo vision. To take full advantage of these two complementary techniques, we investigate a novel 3D reconstruction method based on the fusion of polarization imaging and binocular stereo vision for high quality 3D reconstruction. We first generate the polarization surface by correcting the azimuth angle errors on the basis of registered binocular depth, to solve the azimuthal ambiguity in the polarization imaging. Then we propose a joint 3D reconstruction model for depth fusion, including a data fitting term and a robust low-rank matrix factorization constraint. The former is to transfer textures from the polarization surface to the fused depth by assuming their relationship linear, whereas the latter is to utilize the low-frequency part of binocular depth to improve the accuracy of the fused depth considering the influences of missing-entries and outliers. To solve the optimization problem in the proposed model, we adopt an efficient solution based on the alternating direction method of multipliers. Extensive experiments have been conducted to demonstrate the efficiency of the proposed method in comparison with state-of-the-art methods and to exhibit its wide application prospects in 3D reconstruction.     

A tutorial on the segmentation of metallographic images: Taxonomy,new MetalDAM dataset,deep learning-based ensemble model,experimental analysis and challenges

Image segmentation is an important issue in many industrial processes, with high potential to enhance the manufacturing process derived from raw material imaging. For example, metal phases contained in microstructures yield information on the physical properties of the steel. Existing prior literature has been devoted to develop specific computer vision techniques able to tackle a single problem involving a particular type of metallographic image. However, the field lacks a comprehensive tutorial on the different types of techniques, methodologies, their generalizations and the algorithms that can be applied in each scenario. This paper aims to fill this gap. First, the typologies of computer vision techniques to perform the segmentation of metallographic images are reviewed and categorized in a taxonomy. Second, the potential utilization of pixel similarity is discussed by introducing novel deep learning-based ensemble techniques that exploit this information. Third, a thorough comparison of the reviewed techniques is carried out in two openly available real-world datasets, one of them being a newly published dataset directly provided by ArcelorMittal, which opens up the discussion on the strengths and weaknesses of each technique and the appropriate application framework for each one. Finally, the open challenges in the topic are discussed, aiming to provide guidance in future research to cover the existing gaps.     

Efficient Identification of water conveyance tunnels siltation based on ensemble deep learning

The inspection of water conveyance tunnels plays an important role in water diversion projects. Siltation is an essential factor threatening the safety of water conveyance tunnels. Accurate and efficient identification of such siltation can reduce risks and enhance safety and reliability of these projects. The remotely operated vehicle (ROV) can detect such siltation. However, it needs to improve its intelligent recognition of image data it obtains. This paper introduces the idea of ensemble deep learning. Based on the VGG16 network, a compact convolutional neural network (CNN) is designed as a primary learner, called Silt-net, which is used to identify the siltation images. At the same time, the fully-connected network is applied as the meta-learner, and stacking ensemble learning is combined with the outputs of the primary classifiers to obtain satisfactory classification results. Finally, several evaluation metrics are used to measure the performance of the proposed method. The experimental results on the siltation dataset show that the classification accuracy of the proposed method reaches 97.2%, which is far better than the accuracy of other classifiers. Furthermore, the proposed method can weigh the accuracy and model complexity on a platform with limited computing resources.     

快速反求测量系统标定方法研究

提出一种基于结构光三维视觉测量的方法,利用结构光特征解决了三维视觉测量中存在的图像匹配困难的问题,使三维数据的测量更加方便、快捷。最后利用平面网格模板对测量系统的参数进行了标定,通过实验,此系统得到了验证。     

如何确定球窝铣刀的直径

球窝铣刀是加工工件球窝的,其原理是:机床主轴带动工件回转的同时,铣刀与主轴轴线成40°回转并能前后进给,通过切削就完成了球窝的精加工。这样选择球窝铣刀的直径是非常重要的。     

散状物料输送机称重的图像处理方法初步研究

散状物料实时称重系统依据计算机视觉理论,对摄像机模型进行标定,获得摄像机内外参数,利用数字图像处理技术获得目标图像的边缘,根据获得的边缘数据和特征点的匹配推算出目标物体点距离参考面的深度;由深度数据求得所测物料的重量。通过采用照相图片处理实验证明了方法的可行性。