Patents

::: Current Position: 🏠Homepage > Awards > Patents

Patents	Type	Certificate number
情緒模型之建立方法及以該情緒模型進行的情緒偵測方法	ROC (Taiwan)	I501093
疲勞駕駛警示裝置及疲勞駕駛警示方法	ROC (Taiwan)	I557002
嬰兒哭鬧含意判讀模型的建立方法及使用方法	ROC (Taiwan)	I571862
步態分析方法與系統	ROC (Taiwan)	I657800
LED發光元件之主動功因修正驅動系統	ROC (Taiwan)	I665935
口鼻異物遮蔽檢測方法及其系統	ROC (Taiwan)	I684959
臉部對稱性檢測方法及其系統	ROC (Taiwan)	I689285
一種聽音辨位拍照及後製智能剪裁之系統	ROC (Taiwan)	I691211
浮標定位監測方法及浮標定位監測系統	ROC (Taiwan)	I698656
主動式打火機聲源辨識系統	ROC (Taiwan)	I699543
應用於半特徵視覺式同步定位與建圖方法的半特徵視覺里程計	ROC (Taiwan)	I712993
姿態影像訊號與運動訊號之訊號匹配系統以及訊號匹配方法	ROC (Taiwan)	I722674
三維點雲資料處理法	ROC (Taiwan)	I731604
自由空間偵測系統及自由空間偵測方法	ROC (Taiwan)	I733449
非接觸式呼吸檢測方法及其系統	ROC (Taiwan)	I741708
嬰兒哭聲辨識修正方法及其系統	ROC (Taiwan)	I747392
光源光紋辨識系統及其方法	ROC (Taiwan)	I781410
金屬製品表面之文字辨識方法	ROC (Taiwan)	I786946
一種實體物件轉換點雲資訊之模型建置系統及其方法	ROC (Taiwan)	I805934
LED顯示器控制方法	ROC (Taiwan)	I777379
虛實整合建模系統及方法	ROC (Taiwan)	I794621
支援車聯網應用服務的行車監控系統	ROC (Taiwan)	M545723
心率檢測裝置	ROC (Taiwan)	M590433
一種實體物件轉換雲資訊之模型建置系統	ROC (Taiwan)	M608782
高光譜影像之自動化咖啡豆瑕疵檢測方法及其系統	ROC (Taiwan)	M624851
HEART RATE DETECTION METHOD AND DEVICE THEREOF	USA	US10,722,126B2
FACIAL STROKING DETECTION METHOD AND SYSTEM THEREOF	USA	US10,846,518B2
MOUTH AND NOSE OCCLUDED DETECTING METHOD AND SYSTEM THEREOF	USA	US10,891,845B2
INERTIAL POSITIONING NAVIGATION DEVICE A NOVEL DETECTION METHOD	USA	US10,533,874B2
LED PANEL CONTROLLING METHOD AND LED PANEL CONTROLLING SYSTEM	USA	US11,107,393B1
METHOD FOR PROCESSING THREE-DIMENSIONAL POINT CLOUD DATA	USA	US11,348,261B2
METHOD AND SYSTEM FOR CORRECTING INFANT CRYING IDENTIFICATION	USA	US11,380,348B2
NAVIGATION SYSTEM APPLYING AUGMENTED REALITY	USA	US9,953,461


Name of Technology	Character Recognition and Defect Detection of Metal
Developer of Technology	Department of Computer Science and Information Engineering Yi-Lung Lin, Associate Professor
Summary of Technology	Casting Since the metal surface is easy to reflect light, it is not easy to identify using traditional optical character detection. This technology is used to identify the characters of several English/number symbols on the control valve. The symbols include numbers 0 to 9 and English letters A to Z. The technology that has been used includes image preprocessing, deep convolution layer, time series layer, and connectionist temporal classification layer. Considering the field application, it is designed as a lightweight model running on the mobile phone, and a set of character optical detection systems that integrate computer vision. This technology reduces the identification time and improves the accuracy of identification, which is convenient for subsequent application in product inventory management and production history filing after production is completed. Technical characteristic: 1. Digital management of products traceability 2. Reducing the working hours for field personnel to input data 3. Increasing the efficiency of the assembly and shipping process 4. Improving the production history system


Name of Technology	Application of Hyperspectral Smart Agriculture in Food Safety Taking Eggs as Examples
Developer of Technology	Department of Computer Science and Information Engineering Shih-Yu Chen, Associate Professor
Summary of Technology	This technology uses Snapshot to take a hyperspectral image of egg defects and uses a line scan camera to take a picture of egg freshness. The obtained hyperspectral image is processed and trained using an AI depth learning algorithm. In terms of prediction speed, this technology can achieve real-time identification (3.23 ms/image), and the overall accuracy of the two classifications can reach more than 95%. Technical characteristic: 1. Non-invasive: Using the non-invasive hyperspectral camera 2. Real-time: Conducting real-time analysis by AI depth learning algorithm. Accuracy can reach more than 95% and the prediction time of one image only takes 3.23ms. 3. Economize manpower: Saving the manpower of traditional manual sections. 4. Increase production: Long-running


Name of Technology	AI-based Textile Defect Inspection
Developer of Technology	Department of Computer Science and Information Engineering Chien-Chou Lin, Professor
Summary of Technology	Generative adversarial network model is first built and defect identification/location network is used to find the location of defects. The degree of automation of textile defect detection technology is significantly upgraded. An algorithm is designed to improve the accuracy of identification. The defects are located in the images and the corresponding locations of the textile and defects are recorded in real time for later examination and review. This technique is also useful in ensuring the areas of textile with defects are avoided during the cutting process. An identification accuracy of higher than 95% is achieved.


Name of Technology	Industry 4.0 Connected Intelligent Ball Screw
Developer of Technology	Department of Computer Science and Information Engineering Ching-Lung Chang, Professor
Summary of Technology	The performance of ball screws can be effectively monitored by integrating the hybrid sensor for vibration and temperature with algorithm. The user is able to monitor the condition of each work station in real time on remote web pages. Based on the results, timely maintenance can be arranged to avoid unexpected shutdown. Other benefits include high equipment availability and energy efficiency. Intelligent ball screw diagnosis: Vibration alert – Warning signals are triggered as abnormal vibration occurs in order to ensure the normal operation of the ball screws. The incident records are logged as well. Lifetime pre-diagnosis – The online pre-diagnosis enables ball screw health monitoring, facilitates maintenance arrangement and avoids emergency shutdown. Intelligent lubrication – The automatic lubrication ensures worker safety and avoids shutdown of ball screws caused by insufficient lubrication. This condition-based lubrication approach is cost effective and environmentally friendly.


Name of Technology	Agricultural Land Survey Aiot Application and Vehicle Integrated System
Developer of Technology	Bachelor Program in Interdisciplinary Studies Wang Szu-Hong, Project-Appointed Assistant Professor


Name of Technology	Vehicle Surround View Display System with Free Viewing Function (AVM)
Developer of Technology	Department of Electronic Engineering Ching-Lung Su, Associate Professor
Summary of Technology	4 optical wide-angle fisheye lenses are used to provide a panoramic view of the vehicle, showing high-resolution images of the entire vehicle from above and at any angle of view. When parking and reversing, obstacles around the vehicle can be inspected without blind spot, improving safety and protection.


Name of Technology	Indoors Gait Positioning System (Indoors GPS)
Developer of Technology	Department of Computer Science and Information Engineering Wen-Fong Wang, Associate Professor
Summary of Technology	The indoors GPS applies the cell-phone built-in sensors (accelerometer, magnetometer, gyroscope, etc.) with dead reckoning algorithms to locate users, who stay in a complex indoors separated space. This novel idea has been developed in a cell-phone user APP. This app has the functions of service initialization, indoor navigation, check-in, and more.


Name of Technology	Mowing robot
Developer of Technology	Department of Computer Science and Information Engineering Ching-Lung Chang, Professor
Summary of Technology	Embedded platform, combined with RTK-GPS, 9-axis sensor and the Kalman filter, PID control, ultrasonic sensing, image recognition and other technologies. Create a mowing robot with precise autonomous mowing and obstacle avoidance capability. Relevant technologies can be transferred to achieve automatic mowing and save manpower. It can be applied to lawn finishing in campus, parks, homes, etc.
Video


Name of Technology	Intelligent Trash Can Featuring Patrolling and Surveillance
Developer of Technology	Department of Electrical Engineering Chian-C. Ho, Associate Professor
Summary of Technology	Traditional trash cans are usually installed in the out-of-the-way dead corners so that people are often littering the trash anywhere because of urgency or inconvenience. This work “Intelligent Trash Can Featuring Patrolling and Surveillance” can collect the trach proactively from people so as to improve the effectiveness and efficiency of cleaning service. On the other hand, traditional security surveillance cameras are usually installed on the ceiling corners or crossways so that there are still many dead spaces and security loopholes to be monitored. This work can patrol and inspect proactively so as to improve the effectiveness and efficiency of surveillance service.

Patents

Intelligent Recognition Industry Service Research Center

No. 123, Section 3, University Road, Douliu City, Yunlin County (3F-AI304/AI305,Dream Hub Building) Tel: 05-5342601 ext. 2776-2780 05-5524539

© 2020 IRIS YunTech All Rights Reserved

No. 123, Section 3, University Road, Douliu City, Yunlin County (3F-AI304/AI305,Dream Hub Building)
Tel: 05-5342601 ext. 2776-2780　05-5524539