Search results

The purpose of this paper is to review the progress of machine vision as it applies to automated assembly applications.

A series of technological developments is described: 3D vision, smart cameras, near infrared (NIR) imaging and LED illumination. Associated with each are relevant assembly applications.

Advances in multi‐core processors are facilitating the development of 3D image processing algorithms for robot guidance and product inspection, which in turn enable the automation of skilful and labour‐intensive tasks. Machine vision products are becoming more capable, yet simpler to use. NIR imaging is useful for inspecting semiconductors and bottle filling. Advances in LED lighting address difficult inspection tasks at the macro and microscopic levels.

The paper recognises the emergence of 3D machine vision as a new tool in assembly automation. Updates engineers on other relevant machine vision advances.

This paper aims to design an automatic inspection system for the characters on tire molds, which involves a vision-based inspection method for the characters on tire molds.

An automatic inspection equipment is designed according to the features of the tire mold. To implement the inspection task, the corresponding image processing methods are designed, including image preprocessing, image mosaic, image locating and character inspection. Image preprocessing mainly contains fitting the contours of the acquired tire mold images and those of the computer aided design (CAD) as the arcs of two circles and polar transformation of the acquired images and the CAD. Then, the authors propose a novel framework to locate the acquired images into the corresponding mosaicked tire mold image. Finally, a character inspection scheme is proposed by combining an support-vector-machine-based character recognition method and a string matching approach. At the stages of image locating and character inspection, image mosaic is simultaneously used to label the defects in the mosaicked tire mold image, which is based on histograms-of-gradients features.

The experimental results indicate that the designed automatic inspection system can inspect the characters on the tire mold with a high accuracy at a reasonable time consumption.

The designed automatic inspection system can detect the carving faults for the characters on the tire molds, which are the cases that the characters are wrongly added, deleted or modified on the tire mold.

To the best of the authors’ knowledge, this is the first automatic vision-based inspection system for the characters on tire molds. An inspection equipment is designed and many novel image processing methods are proposed to implement the inspection task. The designed system can be widely applied in the industry.

Lubricating oil leakage is a common issue in thermal power plant operation sites, requiring prompt equipment maintenance. The real-time detection of leakage occurrences could avoid disruptive consequences caused by the lack of timely maintenance. Currently, inspection operations are mostly carried out manually, resulting in time-consuming processes prone to health and safety hazards. To overcome such issues, this paper proposes a machine vision-based inspection system aimed at automating the oil leakage detection for improving the maintenance procedures.

The approach aims at developing a novel modular-structured automatic inspection system. The image acquisition module collects digital images along a predefined inspection path using a dual-light (i.e. ultraviolet and blue light) illumination system, deploying the fluorescence of the lubricating oil while suppressing unwanted background noise. The image processing module is designed to detect the oil leakage within the digital images minimizing detection errors. A case study is reported to validate the industrial suitability of the proposed inspection system.

On-site experimental results demonstrate the capabilities to complete the automatic inspection procedures of the tested industrial equipment by achieving an oil leakage detection accuracy up to 99.13%.

The proposed inspection system can be adopted in industrial context to detect lubricant leakage ensuring the equipment and the operators safety.

The proposed inspection system adopts a computer vision approach, which deploys the combination of two separate sources of light, to boost the detection capabilities, enabling the application for a variety of particularly hard-to-inspect industrial contexts.

Many industrial applications could benefit from line imaging‐based edge sensors rather than full‐scale vision systems, a leading specialist argues.

Recently great interest has developed for a high speed, flexible machine vision system which can accurately determine solder paste and component placement for both process verification and quality control inspection. Present SMT inspection systems must cope with the unpredictable appearance of components and backgrounds and are often used only to determine presence and absence. This paper describes a new approach which combines greyscale data with a three‐dimensional map of the board under test. Originally this method was proposed as a robust technique for locating components in low contrast greyscale images. However, experience working with manufacturers and developers of placement equipment has shown that emerging SMT inspection requirements indicate the importance of three‐dimensional information. In addition to the detection of components and measurement of orientation, examples are shown of solder paste volume measurements, lead co‐planarity, and tombstone effect detection.

This work aims to develop a web platform for inspecting roof structures for technical assistance supported by drones and artificial intelligence. The tools used were HTML, CSS and JavaScript languages; Firebase software for infrastructure; and Custom Vision for image processing.

This study adopted the design science research approach, and the main stages for the development of the web platform include (1) creation and validation of the roof inspection checklist, (2) validation of the use of Custom Vision as an image recognition tool, and (3) development of the web platform.

The results of automatic recognition showed a percentage of 77.08% accuracy in identifying pathologies in roof images obtained by drones for technical assistance.

This study contributed to developing a drone-integrated roof platform for visual data collection and artificial intelligence for automatic recognition of pathologies, enabling greater efficiency and agility in the collection, processing and analysis of results to guarantee the durability of the building.

Film is an important recording medium in industry. How to ensure film quality is a problem, because the film is produced in a dark room. Aims to focus on this.

An inspection system based on machine vision is presented which could assure illumination and imaging at 940 nm which is safe for film.

An objective evaluation is given using an image processing method and satisfactory results are obtained. Now, the inspection system is used by the biggest film company in China.

This work focuses on an important issue in film production.

Inspection is an activity that controls the outgoing product quality and involves search, detection and measurement or diagnosis. Traditionally, inspection tasks have been allocated to humans. Attempts to automate industrial inspection in order to eliminate errors and alleviate monotony have faced difficulties due to technological limitations and/or prohibitive implementation costs. An occasional compromise is partial automation (hybrid inspection). Reviews published research in manual, hybrid and automated inspection to understand the current research status.

Geometric errors are common in metallic bent tubular parts. Thus, tubes should be inspected and fixed before welding with the joints first. After welding, the relative position of the joints is also necessary to be inspected to judge whether the tube can be assembled reliably. Therefore, the inspection plays an important role in the tube’s assembly. The purpose of this paper is to propose a multi-vision-based system designed to inspect the tube and the relative position of the joints.

For the tube inspection, the small cylinders are taken as the primitives to reconstruct the tube using the multi- vision-based system. Then, any geometric error in the tube can be inspected by comparing the reconstructed models and designed ones. For joints’ inspection, authors designed an adapter with marked points, by which the system can calculate the relative position of the joints.

The reconstruction idea can recognise the line and arc segments of a tube automatically and resolve the textureless deficiency of the tube’s surface. The joints’ inspection method is simple in operation, and any kinds of joints can be inspected by designing the structure of the adapters accordingly.

By experimental verification, the inspection precision of the proposed system was 0.17 mm; the inspection time was within 2 min. Thus, the system developed can inspect a tube effectively and automatically. Moreover, authors can determine how the springback of the arcs behaves, allowing in-process springback prediction and compensation, which can reduce geometric errors in the tubes given the present bending machine accuracy.

According to a recent study by Active‐Media Research, USA, total sales in advanced vision systems, including vision‐guided mobile devices/robots are expected to soar from US $665 million in the year 2000 to more than US $17 billion by 2005. The key technologies contributing to this massive growth include major advancements in vision imaging science and control, integrated with increasingly “machine intelligent” and robust industrial robotics. This article gives an overview of key machine vision advancements, and demonstrates some advanced vision application examples.