Fujitsu Develops AI for Image Inspection to Detect Abnormalities in Product Appearance with World-Leading Precision in Key Benchmark
TOKYO, Mar 29, 2021 - (JCN Newswire) - Fujitsu Laboratories today announced the successful development of an AI technology for image inspection that enables highly precise detection of a wide variety of external abnormalities on manufactured goods, including scratches and production errors. The technology leverages an AI model trained on images of products with simulated abnormalities, without having to prepare training data that uses actual images of defective products pulled from the inspection process of a production line.
|Fig 1. Outline of the development technology|
|Fig 2. Comparison with the prior art|
This technology is capable of correctly detecting abnormalities like frayed threads and defective wiring patterns in products that vary individually, even if they appear normal, such as carpets with different wool or color, or printed circuit boards with different wiring shapes depending on the part. The developed technology successfully achieved world leading accuracy (1) in a benchmark using public data (2) collected from external images of various manufactured goods.
Fujitsu verified the effectiveness of this technology during the inspection process at the Nagano Plant of Fujitsu Interconnect Technologies Limited, a factory that manufactures electronic equipment, and confirmed its effectiveness in reducing man-hours required for inspecting printed circuit boards by 25%. The technology ultimately offers the potential to help reduce the workload of workers at manufacturing plants and improve productivity, while helping to introduce new working styles for frontline staff.
Background & Challenges
At the site of the inspection process, the inspector determines whether the product is defective based on features such as its approximate shape, detailed structure, and texture. For example, approximate shape is considered important in a shape distortion test, and texture is considered important in a condition or pattern test. Furthermore, even if the product appears normal, if there are individual variations in elements like coating, color, and wiring shape, these characteristics are examined for each item, and the inspection is conducted while distinguishing whether individual differences or abnormalities fall within the acceptable range. Therefore, when training AI to conduct quality control tasks, it is necessary to be able to capture a wide variety of features that occur on an individual basis in a normal image. However, the typical method of training an AI model using weighted and summed indices for each characteristic has led to a tendency to focus on only one characteristic, and it has proven difficult to create a model that fully grasps all the characteristics.
About the Newly Developed Technology
With this technology, the AI restores the normal image from which the abnormality has been removed when an abnormality is detected, and detects the abnormal part by capturing the difference between the image to be inspected and the restored normal image. Fujitsu has developed a method to train an AI model so that a normal image without a variety of anomalies such as shape, size, and color can be restored by artificially adding the simulated abnormalities to a normal image prepared for training. The improved ability to restore normal images has made it possible to detect abnormal areas with high accuracy without preparing images containing abnormalities as training data. During training, Fujitsu compares the normal image with the image restored by AI, evaluates the degree of training of each feature such as approximate shape, detailed structure, and texture, and control the size, color, and number of abnormalities to be added so that AI preferentially learns features not captured. For example, if the AI is not able to correctly restore the approximate shape, it trains with abnormal images with a few small abnormalities that do not affect the normal appearance. Also, if the details and texture are slightly different, the AI trains with many abnormal images that are large enough to obscure the details or add a conspicuous pattern. In this way, by evaluating the state of AI restoration and training on weak areas where AI cannot restore features, it became possible to restore normal images that captured all features.
In addition, Fujitsu has developed a new technology that generates materials of various shapes, sizes, and colors from a library of images of more than 5000 kinds of artificial objects, and adds abnormalities by probabilistically changing the number of abnormalities and the position to which they are added.
The developed technology achieved world leading accuracy, with an AUROC (3) score exceeding 98% in a class of products that have variations in their normal appearance, such as carpets with different fur patterns and colors on an individual basis and printed circuit boards with different wiring shapes on different parts. In addition, there is no variation in individual products such as screws and nuts, and in products where non-defective products have a uniform appearance, accuracy equivalent to that of conventional technologies (4) was also successfully maintained.
The real-world effectiveness of this technology was verified during the inspection process at the Nagano Plant of Fujitsu Interconnect Technologies, a manufacturer of electronic equipment. The technology succeeded in reducing man-hours required for inspecting printed circuit boards by 25%.
In the future, Fujitsu will further develop this and other related technologies to support Fujitsu's portfolio of AI technologies, "FUJITSU Human Centric AI Zinrai," and aims to apply this new approach to Fujitsu's manufacturing brand "COLMINA," which delivers digital transformation (DX) for the manufacturing industry.
(1) world leading accuracy:
The accuracy was achieved for AUROC in comparison with the technologies listed in the benchmark ranking of anomaly detection technology using MVTec AD in the target class with variations in normal appearance. Company data as of March 29, 2021.
(2) benchmark using public data:
MVTec Anomaly Detection Dataset offered by MVTec.
Area Under the ROC Curve. A measure of the performance of a model that detects abnormalities. With a maximum score of 100%, the higher the score on the index, the better the model's performance.
(4) conventional technology:
Technology listed in the benchmark ranking of anomaly detection technology using MVTec AD
Fujitsu is the leading Japanese information and communication technology (ICT) company offering a full range of technology products, solutions and services. Approximately 130,000 Fujitsu people support customers in more than 100 countries. We use our experience and the power of ICT to shape the future of society with our customers. Fujitsu Limited (TSE:6702) reported consolidated revenues of 3.9 trillion yen (US$35 billion) for the fiscal year ended March 31, 2020. For more information, please see www.fujitsu.com.
About Fujitsu Laboratories
Founded in 1968 as a wholly owned subsidiary of Fujitsu Limited, Fujitsu Laboratories Ltd. is one of the premier research centers in the world. With a global network of laboratories in Japan, China, the United States and Europe, the organization conducts a wide range of basic and applied research in the areas of Next-generation Services, Computer Servers, Networks, Electronic Devices and Advanced Materials. For more information, please see: http://www.fujitsu.com/jp/group/labs/en/.
Source: Fujitsu Ltd
Sectors: Cloud & Enterprise, Artificial Intel [AI]
Copyright ©2021 JCN Newswire. All rights reserved. A division of Japan Corporate News Network.
More Latest Release >>
Eisai and Merck & Co., Inc., Kenilworth, N.J., U.S.A. Receive Priority Review From FDA for LENVIMA (lenvatinib) Plus KEYTRUDA (pembrolizumab) Applications
May 07, 2021 11:08 JST
Showa Denko and Infineon Technologies Conclude Supply Contract and Development Agreement
May 06, 2021 17:30 JST
NEC Develops Neuroscience-inspired AI Technology for Time Series Analysis
May 06, 2021 14:13 JST
NEC Contributes to Development of Artificial DNA Aptamer that Binds to the Novel Coronavirus (SARS-CoV-2)
May 06, 2021 11:27 JST
Synopsis 2021: Hot Trends - Join the Summit 1-5 June
May 04, 2021 09:00 JST
Hard-Fought Hypercar Win for Toyota Gazoo Racing
May 03, 2021 04:25 JST
Komatsu, NTT DOCOMO, Sony Semiconductor Solutions and Nomura Research Institute to Launch "EARTHBRAIN"
Apr 30, 2021 16:35 JST
Toyota Developing Hydrogen Engine Technologies Through Motorsports
Apr 30, 2021 14:20 JST
Toyota Global Sales and Production Secures 90 Percent Level Year-on-Year in FY2021
Apr 28, 2021 16:46 JST
RESONA and Eisai Enter Into Business Alliance Aiming to Support People Living with Dementia and to Prevent Dementia in Saitama Prefecture, Japan
Apr 28, 2021 12:33 JST
NEC recognized in Gartner Magic Quadrant for 5G Network Infrastructure for Communications Service Providers as a Visionary
Apr 28, 2021 11:05 JST
LEXUS DESIGN AWARD 2021 Grand Prix Winner Announced
Apr 27, 2021 17:38 JST
AEON GLOBAL SCM and Toyota Starts to Consider Collaboration on Logistics Improvement and Carbon Neutrality Initiatives
Apr 27, 2021 16:15 JST
Suzuki, Subaru, Daihatsu, Toyota and Mazda Reach Agreement on Joint Development of Technical Specifications for Next-generation Vehicle Communications Devices
Apr 27, 2021 14:35 JST
MHIEC Supplies Incinerators for First Waste-to-Energy Plant in Xiaogan, Hubei Province, China
Apr 27, 2021 11:22 JST
Woven Planet Holdings, a Subsidiary of Toyota, Announces Acquisition of Lyft's Level 5 Division to Accelerate Software Innovation for Automated Driving Mobility
Apr 27, 2021 09:00 JST
Mitsubishi Heavy Industries Partner in Newly Established Hamburg Hydrogen Network to 'Make Hamburg Greener'
Apr 26, 2021 17:27 JST
NTT and Fujitsu Embark on Strategic Alliance to Drive "Realization of Sustainable Digital Society"
Apr 26, 2021 14:05 JST
AD ECU and OTA Unit Adopted in New Model Legend Capable of Over-the-Air (OTA) Vehicle Control Software Updating
Apr 26, 2021 11:35 JST
Honda to be Title Sponsor of the 2021 FIA Formula One Japanese Grand Prix
Apr 26, 2021 10:16 JST