:::

【2020 Solutions】 Anomaly Detection Solves the Problem of Insufficient Defect Images

E-Hui Technology collaborates with the Institute for Information Industry to create an anomaly detection system

In closed production lines where anomaly data is hard to collect, the biggest problem with AI image recognition is the paucity of training data and its rarity, making implementation very challenging. E-Hui Technology, in collaboration with the Service Creation Institute of the Institute for Information Industry, has developed unsupervised learning technology, wherein the computer does not need to label specific items to recognize during its learning process. It classifies based on the characteristics of the data. For instance, in manufacturing, where defect detection is critical, the system first learns from the predominantly normal products on the production line. When a few defective items are mixed in, the machine uses classification rules to screen out the defective items. Similarly, if a consumer credit card transaction suddenly shows completely unusual characteristics that do not match typical patterns and habits, the machine autonomously detects this anomaly. Due to its distinctiveness, this technology is applicable to unique sectors.

Using unsupervised deep learning algorithms for developing AI anomaly detection technology eliminates the need for collecting and labeling anomaly data, reducing the introduction period to 1-2 months. The target market is traditional industries such as chemical and steel, which find it difficult to gather anomaly data. This technology has a high tolerance for image quality, requiring only regular surveillance footage from the production line to train the model. It can detect various types of anomalies and has a simple and fast implementation process. The system includes components for image acquisition, training mechanisms, edge real-time computing hosts, and cloud inspection services, forming a complete anomaly detection solution that can be integrated with factory patrols, apps, and other reporting mechanisms.

Anomaly Detection System

 

Anomaly Detection System-2

「Translated content is generated by ChatGPT and is for reference only. Translation date:2024-05-19」

Recommend Cases

【解決方案】客廳化身為健身房 Uniigym矢志成為健身界的Netflix
Living Room as a Gym: Uniigym Aims to be the Netflix of Fitness

Afflicted by the pandemic, most people choose to stay at home However, for those who enjoy exercising, missing a day at the gym can feel uncomfortable With Uniigym's 'AR Fitness x Uniigym' app, users have access to nearly 1,000 diverse exercise classes With a dedicated AI coach, users can exercise anytime they wish, while also tracking their fitness journey, and understanding their condition completely To encourage public fitness and fight the pandemic together, Uniigym has also collaborated with Chunghwa Telecom, offering free access to the 'AR Fitness x Uniigym' app for 30 days starting from now until the end of June, contributing to the public health effort Founded in 2019 by CEO Yu-Chieh Lin, Uniigym was conceived from the monotony and limited options of gym venues like fitness centers and school gyms, and low interaction with trainers The company aims to make exercising as fun as gaming through technological solutions, starting with their first product—an intelligent dynamic projection system that has gained favor in the fitness market Uniigym continuously innovates fitness products creating a comprehensive platform for sports health Uniigym is dedicated to creating an immersive fitness course platform starting from offline venues to an online platform, thereby achieving a full spectrum of fitness content and increasing data traffic for enhanced monetization capabilities Over three years, Uniigym has continued to develop new products So far, they have reached the third generation of products In addition to the Uniicube, a dynamic projection fitness system, there's also Uniihome, which turns living rooms into gyms through set-top boxes provided by Taiwan Broadband Communications and cable television provider Kbro Furthermore, the third generation, Uniicell, allows users to exercise anywhere anytime with mobile devices and 5G networks Next, Uniigym plans to launch the fourth generation, Uniicare, targeting businesses and government employees with camera and heart-rate devices to gather health data and offer health management solutions Features of the AR Fitness x Uniigym App "Uniigym is a combination of Netflix and Nintendo, aiming to become the Netflix of the fitness world" By lowering the barriers to exercise through Uniigym's diverse workout classes and fostering a national habit of exercise, marketing director Shu-Wei Wang explained the company's strong ambition and its ongoing progress towards these goals Since the launch of the AR Fitness x Uniigym app in collaboration with Chunghwa Telecom in November 2021, the app has seen over 20,000 downloads in less than half a year, featuring nearly 1,000 multi-category classes including aerobics, fat-burning, body sculpting, strength training, yoga, boxing, and popular dance Built-in latest AI posture algorithm for real-time monitoring of exercise state The AR Fitness x Uniigym APP features six key functionalities, consisting of One Celebrity fitness courses, featuring a hundred top instructors, pick and practice anytime without appointment Two AI real-time motion matching that captures 20 skeletal points of the body through the phone's camera, accurately comparing movements and providing instant feedback Three AR fitness trainer, accompanying you in any environment, personally guiding the workouts, making the fitness experience more engaging Four Gesture remote control interface, allowing you to remotely access various features, making operations easier Five Supports screen casting, syncing the phone with TVs and screens to enhance immersive exercise experiences Six Self-data tracking, fully recording fitness progress including exercise hours, calories burned, and training programs AR动滋动 x Uniigym Rise to Exercise, Safeguard Health TAIWAN SAFE Event Introduction Most importantly, the system platform integrates the latest AI posture algorithm, comparing user movements and skeletal points with those of the fitness trainer during exercise, combined with heart-rate belts to display changes in heart rate on the screen during exercise By employing technology in exercise, it not only protects users during training but also helps in logging physical energy consumption, effectively enhancing exercise efficiency and preventing exercise injuries Uniigym is deeply rooted in Taiwan and expanding to international markets In fact, Uniigym's products are iteratively evolved according to different user groups The second generation product, Uniihome, turns living rooms into gyms in collaboration with the television system platforms, Taiwan Broadband Communications and Kbro, featuring set-top boxes with a menu of 1,700 classes, each lasting 3-5 minutes suitable for all family members ranging from grandparents to children, providing a freely selectable fitness menu for different groups AR Fitness x Uniigym App Product Experience Scenario Illustration In the post-pandemic era, exercising at home has become a trend Uniigym's interactive sensor-based fitness courses offer consumers a convenient, economical way to exercise anytime, anywhere It eliminates the need for purchasing fitness equipment or spending on expensive courses, as users can enjoy personal guidance from an AI coach directly through their smartphones, enhancing their willingness and frequency of exercise, playing an essential role in promoting a healthier lifestyle for all Uniigym provides a combination of online and offline AI cloud-based interactive sensor technology services, matched with home settings and various types of exercise spaces, to offer consumers an entry-level threshold to enjoy professional and entertaining fitness experiences anytime, anywhere This innovative business model has attracted investments from renowned Taiwanese listed companies such as, Nan Yih Textile and Taishin International Bank, and also partnerships with notable international sports enterprises like Decathlon Besides deep-rooting in the Taiwanese market, Uniigym is also actively expanding into international markets including Singapore, Thailand, and China This year 2022, Uniigym plans to launch its products with the Singaporean telecom group Singtel, allowing Chinese-speaking users and a broad international audience to enjoy new interactive sensor-based fitness courses In the future, Uniigym will also introduce home-based health management solutions for corporate and government employees, where employee health data is collected during exercise through cameras or heart rate devices, analyzed, integrated, and linked with health and medical data to achieve preventive medical goals Uniigym founder and CEO, Yu-Chieh Lin「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【解決方案】讓硬碟裡的音樂重生 愛飛媒平運用AI為影像找到最佳拍檔
Rebirth the music on the hard drive. Aifei Matchmaking uses AI to find the best partner for the image.

A young girl, alone in Los Angeles, USA, is looking for a dream, a dream that allows the music creator to find her soulmate again with the music she buried deep in the hard drive Li Zihui, the founder of iFeiMedia, has a background in science and engineering, but she has a strong gene for musicians In order to help global musicians create music and find the "best partner" who can successfully match them, she founded iFeiMedia Ping Company provides a one-stop AI video and music matching platform AV Mapping to help video creators quickly find copyrighted original music One-stop AI image music matching solution to find innovative business opportunities for music creators Generally speaking, in the past, video creators had to work on video music, including composing lyrics, music, and finding copyrights It usually took two weeks Through the AV Mapping video and music matching platform, it can be instantly matched to a suitable video in 10 seconds Music, musicians can also remarket their creations to gain profit sharing, creating a win-win situation This new, decentralized operating model is also favored by the descendants of the late Taiwanese music master Li Taixiang On the platform, you can relive a time when music creation was free to fly Li Zihui has practiced piano since she was a child, participated in choirs and wind bands, and composed her own music Although she studied science and engineering in college - the Department of Surveying and Spatial Information at Cheng Kung University, she joined the imaging team to work on soundtracks from her junior year , and went to the Applied Music Department of Nanyit University to audit After graduating from college, Li Zihui decided to obey the voice in her heart and become a music dreamer Aifei Matching provides a one-stop AI image and music matching solution Aifei Matching provides a one-stop AI image and music matching solution, which mainly uses artificial intelligence image recognition and music analysis Image creators can search and match suitable music by themselves on the platform, and use the system to It can shorten the duration of the soundtrack from 8 hours to a few seconds, a significant reduction of nearly 2,000 times Li Zihui said that in addition to creating suitable soundtracks, traditional video scoring projects also require a lot of time and cost in communication and search, including subsequent post-production processing such as arrangement and recording, and music licensing, which are even more time-consuming and labor-intensive With the assistance of AI, creators can focus all their efforts on creation without worrying about finding suitable music or having their music copyright stolen Integrated virtual and real marketing, from transaction to contract signing with one click At present, AifeiMeiping's music database has a total of 60,000 tracks in more than 60 categories, covering music from Europe, America, Asia and other parts of the world, including pop, EDM, rock, Irish music, etc The original decentralized concept of iFlyMediaPing further protects the rights and interests of musicians Musicians on the platform can set their own prices and track the transaction process, achieving open, transparent and decentralized features There are currently more than 7,000 video and music creators on the platform Music creators who successfully trade on the platform can share profits of more than 40, up to 50 The two parties transact and complete the contract on the platform, and the procedure is very simple AVMapping has a total of 14 AI models, making it easy to find speed dating music Li Zihui said that the AI image music matching solution has a total of 14 AI models The method is to disassemble all elements, conduct music analysis through image recognition and text recognition, and then use machine learning algorithms to train extensively The characteristics of images and music are listed, which can quickly match the soundtrack that suits the image situation, atmosphere, and rhythm In addition to online matchmaking transactions, Aifei Matchmaking also holds physical concert events, inviting music and video creators to participate The content of the event revolves around the display of AI video soundtracks, and a video directed by the director is used on-site to allow music creators to participate PK soundtrack or take out a demonstration video and let AI match it It only takes 10 seconds The images and music matched by AI are very accurate in terms of mood and atmosphere, which amazed the participants Three years of research and development won the Red Dot Design Award, using technology to support the development of music and art Aifei MatchPing spent three years of research and development, and the platform was officially launched in August 2021 In January 2022, it participated in the CES event in Las Vegas, USA, which attracted great attention from reporters present and received more than 100 awards in total media reports, the number of uses in a month has exceeded 1,000 times, attracting 7,000 video and music creators to join the matchmaking platform According to statistics, in the initial stage, the proportion of matchmaking transactions between the United States and Taiwan is evenly divided Li Zihui said that the licensing methods of traditional music are very complex, including types of works, types of copyright property rights, etc To obtain authorization for a song, one must go through a songwriting agency, a collective management group, a production company, a record company, or even a composer , lyricists, it is very cumbersome, and musicians may not necessarily get profit sharing Through the AI image music matching platform, all transaction contracts are completed online, music creators can gain profits, and their creative enthusiasm is constantly stimulated Three steps to help video creators easily complete the soundtrack work It is worth mentioning that NFT Non-fungible token, also known as non-fungible token is currently very popular in the art and cultural market What is the possibility of introducing it into the field of video and music Li Zihui said that the current transaction fees gas fees of Ethereum remain high, and coupled with the conclusions she obtained from attending many gatherings in Los Angeles, the acceptance of NFT is still in the process of brewing However, Aifei Matching is still optimistic about the future of NFT Trend, in the foreseeable future, relevant technologies will still be introduced into the AV Mapping platform to provide more diversified trading methods In order to rapidly expand overseas markets, Li Zihui continues to seek funding from international strategic investors in San Francisco At the same time, due to the appropriate control of the epidemic in Los Angeles, the industry is gradually recovering, and Li Zihui also participates in many offline creative gatherings Aifei Media hopes to become a bridge connecting images and music, introduce well-known user cases in the international market, and let more creators see the power of the platform Aifei Media Ping also frequently reports good news After winning the DSA Digital Advertising Singularity Silver Award and the AWE Female Entrepreneurship Best Potential Award co-organized by the American Institute in Taiwan and META, the one-stop AI video and music matchmaking company founded by Li Zihui The platform AV Mapping also won the Best of the best in the Design Concept of the German Red Dot Award in 2020 We hope to continue to be based on technology and nourished by art Support music creators to create better works Li Zihui, the founder of Aifei Matchping, has won many international awards and is a female entrepreneur with great potential「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【解決方案】AI電眼取代人眼 慧演智能運用AI幫製造業做品管
Using AI vision to replace human vision, Claireye Intelligence uses AI to help the manufacturing industry with quality control

In response to customer demand on a wide variety of products in small quantities in the manufacturing industry, there is an urgent need to find AI solutions from the cloud to terminals Claireye Intelligence provides a solution that integrates software and hardware - BailAI image inspection solution to assist traditional manufacturing industries in improving process efficiency and product quality, thereby achieving the initial goal of transformation After the government declared 2017 to be Taiwan's "First Year of AI," AI startups have sprung up in Taiwan Established in 2018, Claireye Intelligence targets smart manufacturing and provides a platform for AI image analysis and process optimization, using the power of deep learning to detect product defects and abnormalities in the assembly process It assists companies in building infrastructure from terminals to the cloud, which enables automated monitoring of factory production to improve process efficiency and quality Focusing on AI image inspection based on its familiarity with the production line quality control process Shirley Liu, founder and CEO of Claireye Intelligence, is a young entrepreneur She entered the manufacturing industry after graduating from college and held a quality control position in the plastic injection process of hard disk parts "She was already on the production line at the time, and is familiar with the production line process of production machinery" She later switched career paths to marketing and planning, and then worked as an AI product manager When the time came, Shirley Liu decided to start a business, focusing on AI image recognition in the manufacturing industry "The difficulty for enterprises is the lack of an AI development team Even if an enterprise has an AI team, development projects will take a lot of time, at least 6-12 months" said Shirley Liu, who is well versed in the market's pain points The problem that needs to be solved by platforms is to provide services that allow traditional manufacturing industries to build their own AI models without needing employees with a programming background, and to remotely assist production lines with troubleshooting and subsequent system maintenance, helping companies save development time and labor costs BailAI image inspection platform usage scenarios Facing the large number of competitors that provide AI image recognition in the market, what are the technical advantages of Claireye Intelligence Shirley Liu said that many companies currently have AOI equipment, but the bottleneck in the application of AOI is that it can only be used for defect inspection in fast production of large quantities, and parameters need to be adjusted after each inspection or production Based on her understanding of the industry, most SMEs are limited by their financial resources due to AOI equipment often costing over NT1 million, but they also want to use automated inspection This is where Claireye Intelligence comes in Shirley Liu went on to say that it is impossible for traditional manufacturing industries to maintain a technical team that includes AI engineers, data engineers, cloud architects, and terminal architects Claireye Intelligence specializes in software and hardware integration Enterprises can use the BailAI image inspection platform to easily solve inspection problems on the production line In other words, customers only need to provide images or samples for Claireye Intelligence to carry out model training, model deployment, and system integration, and they can easily use AI technology to optimize and monitor production line processes Participated in the AI New Talent Selection and achieved a recognition rate of over 90 in assembly behavioral image recognition For example, a certain connector manufacturer only has 1-2 AI engineers in its technical team The main problem that needs to be solved is that most operators are on the production line, while quality control and senior managers are not on site, and the company wants to understand the actual situation of the production line through remote monitoring Claireye Intelligence uses industrial cameras to capture production line images, and transmits AI image analysis to the remote end Supervisors and quality control personnel can observe if there are any errors in the production line assembly, such as whether the connectors and lines are connected properly, through the monitor Claireye Intelligence's AI image inspection operates on Microsoft's Azure cloud platform, and also utilizes terminal equipment, such as NVIDIA's edge computing equipment placed around the inspection station, to assist traditional manufacturing industries with improving production line efficiency and detecting problems early through an integrated solution from the cloud to terminals Claireye Intelligencersquos customers currently include aviation, electronic peripherals, connectors, and metal industries Assembly process solution for human behavior recognition in assembly lines achieves an accuracy of over 90 In order to demonstrate the depth of technology, Claireye Intelligence participated in the 2021 AI New Talents Selection of the Industrial Development Bureau, Ministry of Economic Affairs, and provided Lite-On Technology with the "assembly process solution for human behavior recognition in assembly lines" The solution determines effective working hours and ineffective working hours of operators on the production line through cameras and AI image recognition It recognizes hand posture and position through images to determine the operator's assembly behavior, achieving an accuracy of over 90 Shirley Liu added that the assembly process of electronic components is complex, mostly carried out manually, and cannot be replaced by robotic arms Claireye Intelligence used cameras to film the assembly process of operators at Lite-On's assembly station The algorithm is then trained and corrected based on the video, and the final trained model can directly determine whether there are any errors in the assembly process to improve the overall process Project development time is expected to be shortened to 1 month by using the BailAI image inspection platform Since its establishment more than three years ago, Claireye Intelligence has accumulated a considerable amount of project experience and hopes to commercialize the project experience Shirley Liu pointed out that the trial version of BailAI image inspection will be completed this year 2022 Customers can choose industrial cameras or video cameras based on the detail of the object being inspected It can even use X-rays to capture images, and then the images are automatically marked by the platform Claireye Intelligence will provide customers with AI application models suitable for the field Inferences can also be made in the cloud or terminals for launch in the manufacturing industry The metals industry, metal casings of industrial computers, connectors, electronic peripherals, and mechanical parts can all use the platform for defect detection and object identification Claireye Intelligence will continue to improve its technical capabilities, accumulate customer experience to complete commercialization, and also accelerate the implementation of AI inspection applications In the mid-term, it will build terminal and cloud infrastructure and shorten the development time of enterprise AI projects from 6-12 months to 1 month, reducing usage time and lowering the threshold for enterprises The long-term goal is to target the Southeast Asian market where Taiwanese businesses are gathered, expand software and hardware integrated AI solutions to overseas markets, and expand the scale of operations