Earticle

Grading the fruit by using machine vision system, it is hoped by the computer to recognize and understand the image automatically, in order to achieve this objective, the key step is to capture the suitable fruit images so that fruit image information can be effectively decomposed. Therefore, the final result of decomposition is to get some of the characteristics of each image with its own motifs, such as borders, shape and so on. By using these primitives, you can match a certain pattern, so as to determine the quality of the fruit. In this paper, it takes the overview of the finite element segmentation as a starting point, combined with the interpretation of the numerical algorithm and FCM algorithm functional convergence of the sequence, relying on Mumford-Shah function model to investigate the generation of fruit image finite element model.

본 연구에서는 지도학습 기반 분할기법을 이용하여 단층 촬영된 단방향 복합재료의 유한요소모델링을 실시하였다. 우선, 단방향 복합재료의 형상 정보를 얻기 위해 Micro-CT 스캔을 수행하여 단방향 복합재료의 순수 체적(raw volume)을 획득하였고 여기에 몇 개의 단면을 선택하여 재료의 마이크로 구조인 섬유의 형상을 라벨링하였다. 이후 재료의 단면 이미지와 라벨링한 이미지를 각각 입출력으로 U-net 모델을 훈련시켰다. 이를 사용하여 선택되지 않은 단층촬영 이미지를 섬유형상을 구분하는 분할을 수행하였고 이렇게 생성된 3차원 정보를 이용해서 유한요소모델을 생성하였다. 최종적으로 단방향 복합재료 시편과 유한요소모델의 섬유체적비를 비교하여 제안된 방법의 적절성을 확인하였다.

In this study, finite element modeling of unidirectional composite materials of the computed tomography (CT) was conducted using a supervised learning-based segmentation technique. Firstly, Micro-CT scan was performed to obtain the raw volume of unidirectional composite materials, providing microstructure information. From the CT volume images, actual microstructure of the cross-section of unidirectional composite materials was extracted by the labeling process. Then, a U-net deep learning model was trained with a small number of raw images as inputs and their labeled images as outputs to generate a segmentation model. Subsequently, most of remaining images were input to the trained U-net deep learning model to segment all raw volume for identifying complex microstructure, which was used for the generation of finite element model. Finally, the fiber volume fraction of the finite element model was compared with that of experimentally measured volume to validate the appropriateness of the proposed method.