딥러닝(Deep Learning) 기술은 이미지 데이터를 비롯하여 텍스트 데이터, 음성 데이터 등을 학습시켜 특성을 추출하고 인식하기 위한 여러 분야에 적용하고 연구되고 있다. 내부에 존재하는 블레이드는 본체와 분리가 불가능하고, 내부의 매우 불리한 환경속에서 검출이 이루어져야 한다. 기존의 영상 검출 방법은 상당한 시간이 요구되며, 기술자들의 개인적 능력과 경험에 의존하고 있다. 본 연구에서는 내부 블레이드의 표면 결함을 효율적으로 검출하고 자동화하기 위하여 Faster R-CNN 알고리즘을 학습시켜 검출 모델을 구축하였다.

A robot usually adopts ANN (artificial neural network)-based object detection and instance segmentation algorithms to recognize objects but creating datasets for these algorithms requires high labeling costs because the dataset should be manually labeled. In order to lower the labeling cost, a new scheme is proposed that can automatically generate a training images and label them for specific objects. This scheme uses an instance segmentation algorithm trained to give the masks of unknown objects, so that they can be obtained in a simple environment. The RGB images of objects can be obtained by using these masks, and it is necessary to label the classes of objects through a human supervision. After obtaining object images, they are synthesized with various background images to create new images. Labeling the synthesized images is performed automatically using the masks and previously input object classes. In addition, human intervention is further reduced by using the robot arm to collect object images. The experiments show that the performance of instance segmentation trained through the proposed method is equivalent to that of the real dataset and that the time required to generate the dataset can be significantly reduced.