• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.873-876
• /
• 2020

매실의 병충해 이미지를 Tensorflow hub에서 제공하는 Resnet50모델에 Transfer Learning기법을 이용하여 학습시키고, 학습된 모델을 Flask를 이용하여 연동시킨다. 이렇게 완성된 웹앱은 사용자가 매실의 이미지를 업로드 하면, 어떤 병충해를 가지고 있는 지 알려주며, 사용자는 얻은 결과를 통해 육안으로 구분하기 어려운 병충해의 정보를 얻어 매실이 손상이 가는 것을 예방할 수 있다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.656-659
• /
• 2020

초해상화 딥러닝 기법은 학습 시 수렴하기까지 최소 수백 번의 에폭을 필요로 하며 오랜 시간이 걸린다. 최근, 영상 인식용 딥러닝 모델에서는 학습 수렴 속도를 향상시키기 위해 픽셀, 채널간 불필요한 상호연관 정보를 제거하는 Deconvolution 기술이 제안되었다. 본 논문에서는 최초로 Deconvolution 기술을 초해상화 딥러닝 방법에 적용하여 학습 수렴 속도 증가를 시도했다. 영상 인식 딥러닝 기법과 다르게 초해상화 딥러닝 기법은 이미지 특성 추출 부분과 이미지 복원 부분의 정보를 보존하는 것이 중요하기 때문에, EDSR을 Baseline 모델로 사용하여 양쪽 끝의 레이어는 기존의 Convolution 연산을 그대로 유지하고, 중간 레이어의 ResBlock 내의 Convolution 연산만 Deconvolution 연산으로 바꿔서 구성하였다. 초해상화 벤치마크 데이터셋을 사용한 실험 결과, 수렴속도가 빨라지지 않는 결과를 도출했다. 본 논문에서는 Deconvolution 기술이 Baseline 모델의 성능을 개선하지 못하는 이유를 초해상화 분야에서 기본적으로 적용되는 Residual Learning 기법 때문으로 분석했다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.327-329
• /
• 2022

본 논문에서는 AI Hub의 개방 데이터인 '유형별 두피 이미지'를 사용하여 두피 상태에 대한 신경망을 학습한다. 이 두피 상태에는 6가지 상태가 있는데, 각각의 상태들에 대한 평가를 양호(0)부터 심각(3)까지 분류하여 학습한 신경망 모델로 실제 어플리케이션으로 구현하여 사람들의 두피 사진을 찍어서 두피 상태를 진단한다. 이 과정에서 기존 개방 데이터에서 사용했던 값 비싼 두피 진단기를 사용하는 것이 아닌 값싸게 구할 수 있는 스마트폰용 현미경을 사용하여 좀 더 효율적으로 두피 상태를 진단 할 수 있는 어플리케이션을 만들었다. 몇백만 원 상당의 비싼 두피 진단기로 촬영한 사진과 비교하였을 시 평균적으로 65%의 정확도를 보여주고 있으며 데이터가 많은 유형은 77%의 정확도까지도 보여주었다.

• Journal of Bio-Environment Control
• /
• v.31 no.3
• /
• pp.255-260
• /
• 2022

This study aimed to develop a service model that uses a deep learning algorithm for detecting diseases and pests in strawberries through image data. In addition, the pest detection performance of deep learning models was further improved by proposing segmented image data sets specialized in disease and pest symptoms. The CNN-based YOLO deep learning model was selected to enhance the existing R-CNN-based model's slow learning speed and inference speed. A general image data set and a proposed segmented image dataset was prepared to train the pest and disease detection model. When the deep learning model was trained with the general training data set, the pest detection rate was 81.35%, and the pest detection reliability was 73.35%. On the other hand, when the deep learning model was trained with the segmented image dataset, the pest detection rate increased to 91.93%, and detection reliability was increased to 83.41%. This study concludes with the possibility of improving the performance of the deep learning model by using a segmented image dataset instead of a general image dataset.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.69-72
• /
• 2000

본 논문에서는 디지털 이미지 안에서의 얼굴 영상 분할을 위해서 데이터로부터 얼굴 영상과 배경 영상의 소속도(membership degree)를 학습시켜 구한다. 그리고 입력 이미지의 각 픽셀 값에 해당하는 소속도를 이용하여 얼굴 영상의 분할을 수행한다. 실험에서는 8-bit 그레이 스케일 영상의 ORL Database를 이용하였다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.11a
• /
• pp.380-382
• /
• 2022

해상풍력발전단지 환경평가를 위한 조류충돌저감장치를 개발하기 위하여, 천연기념물 조류를 구부할 수 있는 인공지능 카메라를 개발한다. 보호해야 할 조류를 90프로 이상 정확하게 구분하기 위한 계층구조 라벨링 방법을 고안하고 YOLO5 모델을 사용하여 학습을 수행하고, 그 결과를 보인다.

• The Journal of the Korea Contents Association
• /
• v.21 no.6
• /
• pp.701-715
• /
• 2021

The drastic advance of recent deep learning technologies is heavily dependent on training datasets which are essential to train models by themselves with less human efforts. In comparison with the work to design deep learning models, preparing datasets is a long haul; at the moment, in the domain of vision intelligent, datasets are still being made by handwork requiring a lot of time and efforts, where workers need to directly make labels on each image usually with GUI-based labeling tools. In this paper, we overview the current status of vision datasets focusing on what datasets are being shared and how they are prepared with various labeling tools. Particularly, in order to relieve the repetitive and tiring labeling work, we present an interactive smart image annotating system with which the annotation work can be transformed from the direct human-only manual labeling to a correction-after-checking by means of a support of automatic labeling. In an experiment, we show that automatic labeling can greatly improve the productivity of datasets especially reducing time and efforts to specify regions of objects found in images. Finally, we discuss critical issues that we faced in the experiment to our annotation system and describe future work to raise the productivity of image datasets creation for accelerating AI technology.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.45-52
• /
• 2021

In this paper, we propose a prediction model for osteopenia and osteoporosis based on a convolutional neural network(CNN) using computed tomography(CT) images. In a single CT image, CNN had a limitation in utilizing important local features for diagnosis. So we propose a compound model which has two identical structures. As an input, two different texture images are used, which are converted from a single normalized CT image. The two networks train different information by using dissimilarity loss function. As a result, our model trains various features in a single CT image which includes important local features, then we ensemble them to improve the accuracy of predicting osteopenia and osteoporosis. In experiment results, our method shows an accuracy of 77.11% and the feature visualize of this model is confirmed by using Grad-CAM.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1079-1087
• /
• 2018

Recently, computer vision field based deep learning artificial intelligence has become a hot topic among various image analysis boundaries. In this study, flames are detected in fire images using the Faster R-CNN algorithm, which is used to detect objects within the image, among various image recognition algorithms based on deep learning. In order to improve fire detection accuracy through a small amount of data sets in the learning process, we use image augmentation techniques, and learn image augmentation by dividing into 6 types and compare accuracy, precision and detection rate. As a result, the detection rate increases as the type of image augmentation increases. However, as with the general accuracy and detection rate of other object detection models, the false detection rate is also increased from 10% to 30%.

• Journal of the Society of Disaster Information
• /
• v.19 no.2
• /
• pp.432-438
• /
• 2023

Purpose: The purpose of this study is to enable users to conveniently report risks by automatically classifying risk categories in real time using AI for images reported in the life safety prevention service app. Method: Through a system consisting of a life safety prevention service platform, life safety prevention service app, AI model serving server and sftp server interconnected through the Internet, the reported life safety images are automatically classified in real time, and the AI model used at this time An AI learning algorithm for generation was also developed. Result: Images can be automatically classified by AI processing in real time, making it easier for reporters to report matters related to life safety.Conclusion: The AI image automatic classification system presented in this paper automatically classifies reported images in real time with a classification accuracy of over 90%, enabling reporters to easily report images related to life safety. It is necessary to develop faster and more accurate AI models and improve system processing capacity.