:::

【2020 Application Example】 "AI Embroidery Pattern Recognition System" effectively improves pattern recognition efficiency by 50 times!

Influenced by fast fashion, the OEM model of large variety in small quantities has become the development trend of the textile industry

"Fast fashion" features fast, cheap and fashionable. Taiwan has been affected by the rise of fast fashion in recent years. The OEM model of "wide variety in small quantities" has become the development trend of the textile industry. The primary goal of the textile industry is to understand how to receive purchase orders under this fashion trend.

Customer inquiries for new patterns can only be searched manually, which is time-consuming and inefficient.

Chairman Chen of a leading domestic textile company took over as the chairman of the "Taiwan Underwear Innovation Alliance" in 2018. He has engaged in the design and development of embroidery patterns for more than 40 years and has developed more than 30,000 embroidery patterns. Whenever international corporate customers request a price quotation for a new embroidery pattern, it takes about 2.5 hours of "manual search" to find 1 to 2 similar patterns for quotation. Therefore, the main bottleneck is how to quickly identify "embroidery patterns."

Cleaning and organizing raw data takes a lot of time

To build an AI model that can quickly identify and find similar embroidery patterns, a large amount of embroidery pattern data needs to be used for learning during the model development stage. Each embroidery pattern requires pre-processing, including watermark removal, border removal, and pattern standardization. It will take one full-time employee six months to complete image pre-processing. The textile company provided a total of 30,125 embroidery patterns for AI machine learning and identification. The data were annotated and divided into seven categories of patterns.

Improved AI accuracy through pattern recognition and learning

When a customer requests a price quotation for a new embroidery pattern, sales personnel can first upload the image to the system and check which important elements need to be identified, such as: style, shape, category, pattern, and size, and then select several satisfactory options from the many options recommended by AI. The results are sorted and stored according to "satisfaction," and recognition results and the user's score are stored in a cloud database. By recording the standards and key points of AI pattern recognition training, we can verify whether any images were left out and the reason why certain images were not selected.

In addition to finding similar patterns, another challenge of "embroidery pattern recognition" is "psychological level" cognition of human beings, including "different users' preferences" and "users' consideration of customers' preferences," both of which will affect selection results. The user's selection results, "satisfaction" scores, and "the operator's psychological level" preferences make the AI model more accurate.

The development of an "AI pattern recognition system" to assist manual work allows similar patterns and solutions to be found within 1 minute, significantly improving work efficiency by 50% and improving order-taking efficiency to cater to the fast fashion industry.

Schematic diagram of embroidery pattern AI recognition management system

▲Schematic diagram of embroidery pattern AI recognition management system

Schematic diagram of embroidery pattern AI recognition results

▲Schematic diagram of embroidery pattern AI recognition results

Establish the "Taiwan Textile Industry AI Pattern Recognition Service Center and Platform"

This "AI Embroidery Pattern Recognition System" project will work with more textile companies and resources in the future to establish a business model for the "Taiwan Textile Industry AI Pattern Recognition Service." Introducing this AI recognition system to the upstream and downstream of the industry chain will jointly improve the technological level, operational efficiency and international competitiveness of Taiwan's textile industry!

Recommend Cases

【導入案例】巨量遙測空間數據AI分析雲端服務平台 使衛星遙測影像順利落地應用
AI Analysis Cloud Service Platform for Remote Sensing Big Data Enables the Smooth Application of Satellite Remote Sensing Images

Although satellite remote sensing images can make all surface objects visible, it still requires a lot of time and manpower to be truly applied to the industry In order to effectively solve the problems that customers face in digesting huge amounts of image data and eliminate technical obstacles for cross-domain users to process satellite remote sensing images, ThinkTron has developed an "AI Analysis Cloud Service Platform for Remote Sensing Big Data" as a new beginning for cross-domain AI applications for spatial information In recent years, in response to the impact of industrial globalization, Taiwan's agriculture has continued to transition towards technology-based and higher quality, improving the yield and quality of crops by solving problems, such as microclimate impacts and pest and disease control The demand of agriculture on images has expanded endlessly to accurately grasp the growing environment of crops In the early years when UAVs unmanned aerial vehicles were not yet popular, manual field surveys were the most basic but most labor-intensive work With the emergence of UAV drones, aerial photography operations might not be difficult, but the range that can be photographed is limited Furthermore, surveying expertise is required to accurately capture spatial information At this time, the use of satellite remote sensing data may break away from the past imagination of using image data Taiwan Space Agency TASA ODC data warehouse services In the past ten years, with the breakthrough of modern satellite remote sensing application technology, Digital Earth has become a new trend in global data collection Countries have developed data cube image storage technology, and the development of smart agriculture has become one of the largest image users Determining planting distribution is the first step in understanding crop yields Free satellite remote sensing images, powerful data warehousing support, and the team's robust image recognition technology are important supports for accelerating agricultural transformation Using satellite remote sensing image data can accelerate the development of smart agriculture However, in the past, it was difficult to extract large-area crop distribution through satellite remote sensing images, not to mention the cost If you wanted to use free information, you had to visit all websites of international space agencies, look through the wide variety of satellite specifications, and carefully evaluate the sensor specifications, image resolution, and revisit cycle After finding suitable images, you had to look at them one by one to filter the ones you need Next is downloading dozens of images that are often several hundreds of Megabytes MB each, which might exceed the capacity of your computer Also, after overcoming image access and preparing data, you must then start to confirm the downloaded image products and which bands you want, because the image you see is not just an image file jpg or png, but rather complex multi-spectral information, attribute fields and coordinate information It takes a lot of effort just to confirm the correct information Facing GIS software packages with complex functions is the start of another trouble The complex image pre-processing process and the inflexible machine learning package greatly reduce the efficiency of analyzing data After finally getting the results of crop identification, you might find that the best time for using map information may have already passed The above-mentioned complex and time-consuming satellite image processing problems are precisely the pain points of the market ThinkTron expanded from traditional machine learning to modern deep learning applications, and developed an "AI Analysis Cloud Service Platform for Remote Sensing Big Data" under the GeoAI framework, breaking through the constraints of details in the spatial information for customers Differences between the process before and after introducing the AI analysis cloud service platform ThinkTron said that Taiwan's ODC Open Data Cube system has been completed and began providing services after years of efforts from the Taiwan Space Agency TASA, formally becoming aligned with international trends The powerful warehousing technology allows users to easily capture and use image data of a specific time and spatial range according to their needs The warehouse stores multiple satellite image resources from international space agencies, including the ESA's Sentinel-1 one image every 6 days, Sentinel-2 one image every 6 days, USGS's Landsat-7 one image every 16 days, Landsat-8 one image every 16 days, and the domestic Formosat-2 one image every day and Formosat-5 one image every 2 days ThinkTron develops satellite image recognition tools based on Python Breaking free from the limitations of GIS Geographic Information System software packages, ThinkTron integrated GDAL Geospatial Data Abstraction Library based on Python, and considered computing efficiency and parallel processing when developing all tools required for satellite image processing and image recognition modeling, including coordinate system and data format conversion, grid and vector data interaction, and data intra-difference and normalization All of the tools are designed with AI applications in mind, and some commonly used tools are packaged into an open source package under the name TronGisPy to benefit the technical community ThinkTron utilized the team's understanding of satellite remote sensing images and the collected tagged data crop distribution maps to preset the image recognition modeling process, the required training data specifications, and dataset definitions This is imported into the machine learning LightGBM or deep learning CNN framework that was completed in advance, and the entire training process to be performed in the Web GIS interface, providing users with partial flexibility to freely filter images, confirm spatial and temporal ranges, select models, and adjust hyperparameters In addition to the operation of training models, it also provides historical models to output identification results, and finally displays the identification results of crop distribution on the Web GIS map In fact, agriculture is not the only industry that needs satellite remote sensing applications AI applications of spatial information have also appeared in various fields as companies in different industries aim to enhance their global competitiveness For example, surveying and mapping companies that have a large amount of map data can use the AI analysis cloud service platform to store map data while also accelerating the efficiency of digital mapping Under the severe global climate change and the risk of strong earthquakes, there is a wide variety industrial insurance, agricultural insurance, financial insurance, or disaster insurance are all inseparable from spatial information The use of remote sensing image recognition to understand insurance targets has long been an international trend AI Analysis Cloud Service Architecture for Remote Sensing Big Data

【導入案例】維繫遊艇王國美譽 嘉信遊艇導入國內第一套FRP複材超音波智慧檢測
Maintaining the reputation of the “Kingdom of Yachts” - Kha Shing Enterprise introduces the first domestic FRP ultrasonic smart inspection of composite materials

The Kaohsiung-based Kha Shing Enterprise Co, Ltd was established over 40 years ago, and is Taiwan's largest customized yacht company with customers all over America, Europe, Asia, and Australia, earning Taiwan the reputation of the "Kingdom of Yachts" Current FRP hull inspection still relies on traditional methods, such as visual inspection and knocking sounds, which is time-consuming and labor-intensive Kha Shing has applied PAUT array ultrasonic inspection to hull FRP composite materials for the first time, and combined it with AI to interpret ultrasound images, develop complete intelligent solutions, and create emerging markets for inspection companies Kha Shing Enterprise Co, Ltd was formerly Kha Shing Wood Industry Co, Ltd, and was a factory specializing in wood import in Kaohsiung Linhai Industrial Park when it was first established It began to design, manufacture, and sell yachts in 1977 After the second-generation successor of the company, President Kung Chun-Hao entered the company, he made a breakthrough in the previous manufacturing model that relied mainly on the skills of master craftsmen, introduced digital manufacturing to accelerate shipbuilding, and began to make larger yachts, ranking in the top 20 manufacturers worldwide among manufacturers of large yachts over 24 feet It also set a record of delivering 94 yachts within one year, earning Taiwan the reputation of "Kingdom of Yachts" Defect detection ensures yacht quality, using AI to replace humans to achieve higher efficiency Defect detection is very important to ensuring yacht quality At present, the yacht industry still uses very traditional defect detection methods The hull structure is usually made by hand lay-up or the vacuum infusion process, using visual inspection or knocking and the frequency of the sound to determine defects It requires time-consuming manual inspection If there are any defects, they must be reworked and repaired, and a gel coat subsequently sprayed The hull must be constructed in sections to facilitate inspection For large yachts over 24 meters long, construction in sections is very time-consuming and labor-intensive To shorten the time of the yacht manufacturing process, Kha Shing Enterprise will first carry out the gel coating process for the hull, and then perform the hand lay-on process The hull manufacturing process has two types of composite material test specimen structures In terms of 54-foot yacht hulls, the hull contains gel coat, core material, fiber and resin, and the total thickness is about 32cmplusmn01cm, which is twice the total thickness of FRP hull without core material of about 16cmplusmn01cm Defects such as incomplete impregnation of glass fiber or residual air bubbles between glass fiber and resin occasionally occur during the manufacturing process The types of defects include insufficient resin, voids, and delamination Once defects occur, the supply of hull materials will be insufficient and yacht delivery will be delayed Schematic diagram of types of FRP hull In order to solve this problem, Kha Shing Enterprise has engaged in technical cooperated with the metal materials industry and the AI technology industry, combining the ultrasonic inspection expertise of the metal materials industry with AI technologies developed by the AI technology industry in recent years to help solve issues of Kha Shing Enterprise with defect detection The method uses PAUT on the composite material structure of yachts, conducts FRP ultrasonic evaluation to determine the thickness of the yacht hull and material properties, and evaluates the ultrasonic probe frequency applicable to the hull structure based on professional ultrasonic experience After testing, a frequency of 5MHz and a probe width of 45mm can successfully find the location and size of defects in the simulated defect test specimen The three parties jointly found defect detection solutions from array ultrasonic evaluation, AI technology model development, and actual application in yachts The image inspected is an ultrasound image The image displays different colors based on the ultrasonic feedback signal An AI model that automatically identifies defective parts is established through the YOLO algorithm If the amount of abnormal data collected is insufficient for training, the CNN-based Autoencoder algorithm is used to collect normal image data for training and construct an AI model for abnormality detection The object detection YOLO model is trained by inputting image data marked as having defects, while the abnormality detection model is trained by inputting image data without defects Simulated defective specimen corresponding to PAUT results Defect detection by and AI system can shorten the construction period by 15 months and speed up determination by 50 After the development of this AI system is completed, it will be validated on actual 54-foot yachts of Kha Shing Enterprise, and can effectively resolve issues with defects The application of AI technology in ultrasonic inspection for intelligent determination is expected to accelerate determination by approximately 50, and will also shortens the construction period by 15 months, effectively improving the speed and quality of the yacht manufacturing process As Taiwan develops larger and more refined yachts, it will create opportunities for industry optimization and transformation, as well as opportunities for the development of key technologies The application of an AI ultrasonic inspection solution for composite materials is the first of its kind in the yacht industry, and is expected to attract more yacht manufacturers with inspection needs The AI ultrasonic inspection solution for composite materials has three major competitive advantages 1 Professional inspection experience and digital database to facilitate process management and analysis 2 Automatic AI determination and identification quickly identifies defects and provides immediate feedback to process engineers 3 High-efficiency process inspection provides defect repair recommendations, reduces damage rate, and improves the strength and quality of composite materials The application of AI technology can optimize the yacht manufacturing process, reduce manual inspection, create added value through the application of AI in Taiwanrsquos yacht industry, increase international purchase orders, and allow Taiwan yachts to continue to enjoy a good reputation in the world Furthermore, this business model has also spread to fields of application related to composite materials, increasing cross-sector market usage It is estimated to contribute approximately NT14 to NT2 billion in economic benefits to Taiwan's equipment maintenance and non-destructive testing market

【解決方案】佐翼科技無人機導入高爾夫球場域 可節省一半人力
Droxo Tech Applies Drones in Golf Courses to Reduce Manpower by Half

For most golf courses, the operations and management is a headache "Golf courses are selling turf and need to be properly taken care of," a golf course manager bluntly pointed out Facing the market pain points of labor shortage, aging population and high cost, the use of AI drones for pesticide spraying and pest control will reduce labor costs by more than half and greatly improve the overall operational efficiency At noon in early summer, an AI drone is slowly taking off at the Taipei Golf Club in Taoyuan Its main task is to test AI drone fertilizing and pesticide spraying on the golf course In fact, drones of Droxo Tech, the company performing this task, are widely used for fertilization, pesticide spraying, and pest and disease control for rice, bananas, and tea trees For golf courses with turfs that often cover tens to hundreds of hectares, AI drones are needed to assist in turf maintenance Data collection, development of pesticide spraying AI models, and multispectral image analysis and testing will be carried out in the current stage In the future, large-scale technology implementation and verification will be carried out to set an example for applying drones to golf courses Using AI drones to fertilize and spray pesticides can reduce the manpower required by half The traditional way of maintaining the turf in golf courses is to carry spray buckets or drive spraying vehicles to spray areas one by one "Domestic golf courses began to plant ultra-dwarf Bermuda grass in 2001 This grass species prefers a cool climate and is not suitable for Taiwan's hot and humid weather" Droxo Techrsquos CEO further pointed out that to prevent turf from pests and diseases, pesticide spraying is necessary For an 18-hole golf course, it is equivalent to spraying pesticides once a week, and the T-ground and fairways are sprayed every two months For golf courses, spraying pesticides is time-consuming and labor-intensive It is important to note that large-scale spraying will increase the risk of personnel poisoning and increase the amount of pesticide used Benefits of applying agricultural drones to golf courses According to Droxo Techrsquos research, golf course pests include Spodoptera litura, which comes out at night to look for food, so pesticide spraying must be carried out in the evening According to the traditional method, pesticide spraying requires two vehicles and three personnel for a total of 45 hours If AI drones are used for fertilizing and pesticide spraying, it only takes one operator to spray 08 hectares of land in 20 minutes, saving about two-thirds of the manpower and reducing operating costs by about 30 Using AI drones to fertilize and spray pesticides on golf courses can reduce the manpower required by half In addition to the significant benefits of using agricultural drones for golf course turf maintenance, Droxo Tech also specially introduced AI multispectral image recognition for NDVI Normalized Difference Vegetation Index analysis "The so-called multispectral is to direct light with different wavelengths on the turf, and the reflected images are collected for analysis" Droxo Tech CEO Liu continued to explain that each plant absorbs light with different wavelengths, so multispectral imaging can determine the growth status of grass species At the same time, combined with AI image recognition, the distribution of pests and diseases can be accurately detected, and the amount of pesticide used is determined on this basis Cross-domain collaboration to build a multi-source turf image databasenbsp Using AI multispectral image recognition technology, Droxo Tech will collect visible light, multispectral, thermal images, and hyperspectral images to establish a multi-source turf image database to fully understand the growth cycle of Bermuda grass Droxo Tech has accumulated rich experience in agricultural AI drone pesticide spraying , but there are still many problems that need to be overcome to implement AI solutions in golf courses For example, it is necessary to establish a new pesticide spraying model and test flight methods, especially the application of multispectral image recognition PoC is not difficult, but actual implementation requires more test evidence, repeated inferences, and collaboration with plant experts This part must rely on the cross-domain integration of legal entities such as the Institute for Information Technology III, gathering more fields for verification, and creating a paradigm before it can be more widely adopted by golf courses There are not many international cases on the application of AI drones in golf courses During the verification process, it is not yet known whether it can be quickly copied to the next golf course However, Droxo Tech CEO Liu believes that through cross-domain collaboration, clearly defining the problems and listing them one by one, supply and demand parties can reach a consensus, propose solutions to each problem, and seek cooperation with internal and external resources Only then will we be able to gradually achieve the goal of making golf courses smarter and smoothly assist the industry with transformation Zuoyi Technology's CEO, Liu Junlin 「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」