http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
이미지에서 기계 학습 기법을 활용한 특정 부품영역 탐지 기술 개발
Faisal Saeed,Anand Paul,Anand Kumar Balasubramaniam,김동인(Kim Dong-In),김대기(Kim Dae-gi),방종원(Bang Jong-Won),우진철(Woo jin-chael) 대한전자공학회 2018 대한전자공학회 학술대회 Vol.2018 No.11
With the growing pace in the industrial sector, the need of the smart environment is also increasing. While production of industrial products, quality always matters. Fault detection in the industrial images is very hot topic in era of current research. Faulty images mean the images of the products which have some fault like missing screw, misplaced labels etc. To detect fault in the images, we proposed a method. Our proposed method is based on deep neural networks which is using convolutional neural network for detection. We also used RoI concept to make detection faster and more accurate. We simulated our environment using python language. Our proposed model has almost 99%.