• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• pp.143-148
• /
• 2003

본 논문에서는 통계적 방법에 기초한 사과 선별시스템을 이용하여 사과의 색깔을 식별하고자 한다. 이를 위해 T-검정을 이용하여 에지를 검출하였고 검출된 에지로부터 체인코드를 이용하여 사과 영상의 경계선과 환상대 영역을 구하였다. 우리는 주어진 사과영상의 환상대 영역으로부터 R, G, B 채널상에서 히스토그램과 평균 명암값을 구하여 색깔 판정용 표준사과로부터 얻은 기준값들과 비교함으로서 사과의 색깔을 식별하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.758-760
• /
• 2022

본 연구는 머신러닝의 한 종류인 YOLOv5를 이용하여 기존 육안 선별작업을 자동화 하는 기계를 설계하는 것이다. 본 연구에서는 영상촬영과 선별작업을 진행하는 컨베이어 기구와 선별 프로그램을 제작하고, 모든 표면을 검사해 사과의 품질을 3단계로 구별하는 작업을 진행하였다. 결과적으로 투입된 사과의 품질을 성공적으로 분류 하였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.1
• /
• pp.208-213
• /
• 2021

There is a lack of studies comparing the internal quality of fruit with its external quality. However, issues of internal quality of fruit such as internal browning are important. We propose a method of classifying normal apples and internally browned apples using a near-infrared (NIR) non-destructive system. Specifically, we found the optimal wavelength and characteristics of the spectra for determining the internal browning of Fuji apples. The NIR spectra of apples were obtained in the wavelength range of 470-1150 nm. A group of normal apples and a group of internally browned apples were identified using principal component analysis (PCA), and a partial least squares regression (PLSR) analysis was performed to develop and evaluate the discriminant model. The PCA analysis revealed a clear difference between the normal and internally browned apples. From the PLSR, the correlation coefficient of the predictive model without pretreatment was determined to be 0.902 with an RMSE value of 0.157. The correlation coefficient of the predictive model with pretreatment was 0.906 with an RMSE value of 0.154. The results show that this model is suitable for classifying normal and internally browned apples and that it can be applied for the sorting and evaluation of agricultural products for internal and external defects.

• Smart Media Journal
• /
• v.11 no.4
• /
• pp.46-55
• /
• 2022

It is very important to first detect and remove defective fruits with scratches or bruised areas in the automatic fruit quality screening system. This paper proposes a method of detecting defective areas in fruits using the latest artificial intelligence technology, the Yolo V4 deep learning model in order to overcome the limitations of the method of detecting fruit's defective areas using the existing image processing techniques. In this study, a total of 2,400 defective fruits, including 1,000 defective apples and 1,400 defective fruits with scratch or decayed areas, were learned using the Yolo V4 deep learning model and experiments were conducted to detect defective areas. As a result of the performance test, the precision of apples is 0.80, recall is 0.76, IoU is 69.92% and mAP is 65.27%. The precision of pears is 0.86, recall is 0.81, IoU is 70.54% and mAP is 68.75%. The method proposed in this study can dramatically improve the performance of the existing automatic fruit quality screening system by accurately selecting fruits with defective areas in real time rather than using the existing image processing techniques.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.9-16
• /
• 2023

Recently, a convolutional neural network (CNN) based system is being developed to overcome the limitations of human resources in the apple quality classification of farmhouse. However, since convolutional neural networks receive only images of the same size, preprocessing such as sampling may be required, and in the case of oversampling, information loss of the original image such as image quality degradation and blurring occurs. In this paper, in order to minimize the above problem, to generate a image patch based graph of an original image and propose a random walk-based positional encoding method to apply the graph transformer model. The above method continuously learns the position embedding information of patches which don't have a positional information based on the random walk algorithm, and finds the optimal graph structure by aggregating useful node information through the self-attention technique of graph transformer model. Therefore, it is robust and shows good performance even in a new graph structure of random node order and an arbitrary graph structure according to the location of an object in an image. As a result, when experimented with 5 apple quality datasets, the learning accuracy was higher than other GNN models by a minimum of 1.3% to a maximum of 4.7%, and the number of parameters was 3.59M, which was about 15% less than the 23.52M of the ResNet18 model. Therefore, it shows fast reasoning speed according to the reduction of the amount of computation and proves the effect.