• Journal of Korea Multimedia Society
• /
• v.23 no.7
• /
• pp.803-811
• /
• 2020

This paper proposes an image classification algorithm that transforms the number of convolution layers in the residual block of ResNet, CNN's representative method. The proposed method modified the structure of 34/50 layer of ResNet structure. First, we analyzed the performance of small and many convolution layers for the structure consisting of only shortcut and 3 × 3 convolution layers for 34 and 50 layers. And then the performance was analyzed in the case of small and many cases of convolutional layers for the bottleneck structure of 50 layers. By applying the results, the best classification method in the residual block was applied to construct a 34-layer simple structure and a 50-layer bottleneck image classification model. To evaluate the performance of the proposed image classification model, the results were analyzed by applying to the cifar10 dataset. The proposed 34-layer simple structure and 50-layer bottleneck showed improved performance over the ResNet-110 and Densnet-40 models.

• Journal of the Korean Wood Science and Technology
• /
• v.49 no.5
• /
• pp.491-503
• /
• 2021

Wood identification is regularly performed by observing the wood anatomy, such as colour, texture, fibre direction, and other characteristics. The manual process, however, could be time consuming, especially when identification work is required at high quantity. Considering this condition, a convolutional neural networks (CNN)-based program is applied to improve the image classification results. The research focuses on the algorithm accuracy and efficiency in dealing with the dataset limitations. For this, it is proposed to do the sample selection process or only take a small portion of the existing image. Still, it can be expected to represent the overall picture to maintain and improve the generalisation capabilities of the CNN method in the classification stages. The experiments yielded an incredible F1 score average up to 93.4% for medium sample area sizes (200 × 200 pixels) on each CNN architecture (VGG16, ResNet50, MobileNet, DenseNet121, and Xception based). Whereas DenseNet121-based architecture was found to be the best architecture in maintaining the generalisation of its model for each sample area size (100, 200, and 300 pixels). The experimental results showed that the proposed algorithm can be an accurate and reliable solution.

• Journal of information and communication convergence engineering
• /
• v.20 no.3
• /
• pp.219-225
• /
• 2022

In this study, we propose training a support vector machine (SVM) model on top of deep networks for detecting Covid-19 from chest X-ray images. We started by gathering a real chest X-ray image dataset, including positive Covid-19, normal cases, and other lung diseases not caused by Covid-19. Instead of training deep networks from scratch, we fine-tuned recent pre-trained deep network models, such as DenseNet121, MobileNet v2, Inception v3, Xception, ResNet50, VGG16, and VGG19, to classify chest X-ray images into one of three classes (Covid-19, normal, and other lung). We propose training an SVM model on top of deep networks to perform a nonlinear combination of deep network outputs, improving classification over any single deep network. The empirical test results on the real chest X-ray image dataset show that deep network models, with an exception of ResNet50 with 82.44%, provide an accuracy of at least 92% on the test set. The proposed SVM on top of the deep network achieved the highest accuracy of 96.16%.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.5
• /
• pp.313-322
• /
• 2020

A large volume of data will improve the robustness of deep learning models and avoid overfitting problems. In automatic tongue segmentation, the availability of annotated tongue images is often limited because of the difficulty of collecting and labeling the tongue image datasets in reality. Data augmentation can expand the training dataset and increase the diversity of training data by using label-preserving transformations without collecting new data. In this paper, augmented tongue image datasets were developed using seven augmentation techniques such as image cropping, rotation, flipping, color transformations. Performance of the data augmentation techniques were studied using state-of-the-art transfer learning models, for instance, InceptionV3, EfficientNet, ResNet, DenseNet and etc. Our results show that geometric transformations can lead to more performance gains than color transformations and the segmentation accuracy can be increased by 5% to 20% compared with no augmentation. Furthermore, a random linear combination of geometric and color transformations augmentation dataset gives the superior segmentation performance than all other datasets and results in a better accuracy of 94.98% with InceptionV3 models.

• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.21-32
• /
• 2022

The importance of the classical theme of how the Top-of-Atmosphere (TOA) and Top-of-Canopy (TOC) reflectance of high-resolution satellite images match the actual atmospheric reflectance and surface reflectance has been emphasized. Based on the Radiometric Calibration Network (RadCalNet) BTCN and BSCN data, this study compared the accuracy of TOA and TOC reflectance products of the currently available optical satellites, including KOMPSAT-3, WorldView-2, and Pléiades-1A image sets calculated using the absolute atmospheric correction function of the Orfeo Toolbox (OTB) tool. The comparison experiment used data in 2018 and 2019, and the Landsat-8 image sets from the same period were applied together. The experiment results showed that the product of TOA and TOC reflectance obtained from the three sets of images were highly consistent with RadCalNet data. It implies that any imagery may be applied when high-resolution reflectance products are required for a certain application. Meanwhile, the processed results of the OTB tool and those by the Apparent Reflection method of another tool for WorldView-2 images were nearly identical. However, in some cases, the reflectance products of Landsat-8 images provided by USGS sometimes showed relatively low consistency than those computed by the OTB tool, with the reference of RadCalNet BTCN and BSCN data. Continuous experiments on active vegetation areas in addition to the RadCalNet sites are necessary to obtain generalized results.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_3
• /
• pp.1095-1107
• /
• 2020

Flood monitoring using satellite data has been constrained by obtaining satellite images for flood peak and accurately extracting flooded areas from satellite data. Deep learning is a promising method for satellite image classification, yet the potential of deep learning-based flooded area extraction using SAR data remained uncertain, which has advantages in obtaining data, comparing to optical satellite data. This research explores the performance of SegNet and U-Net on image segmentation by extracting flooded areas in the Khorat basin, Mekong river basin, and Cagayan river basin in Thailand, Laos, and the Philippines from Sentinel-1 A/B satellite data. Results show that Global Accuracy, Mean IoU, and Mean BF Score of SegNet are 0.9847, 0.6016, and 0.6467 respectively, whereas those of U-Net are 0.9937, 0.7022, 0.7125. Visual interpretation shows that the classification accuracy of U-Net is higher than SegNet, but overall processing time of SegNet is around three times faster than that of U-Net. It is anticipated that the results of this research could be used when developing deep learning-based flood monitoring models and presenting fully automated flooded area extraction models.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.201-202
• /
• 2018

In this paper, a dog breed image provided by Dataset of existing ImageNet and Oxford-IIIT Pet Image is combined with a dog breed image obtained through data mining on Internet and a random-label is added. this paper introduces to recognize 122 classes of dog breeds and 1 class that is not dog breeds. The recognition rate of dog breeds using both conventional DB and collection DB was improved 1.5% over Top-1 compared to recognition rate of dog breeds using only existing DB. The image recognition rate about non-dog image, was 93% recognition rate in case of 10000 random DBs.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.391-394
• /
• 2023

일반적으로 화재 감지 시스템은 정확하고 빠르게 화재를 감지하는 것은 어려운 문제 중 하나이다. 본 논문에서는 U-net을 활용하여 기존의 화재(불) 영역 추출 기법으로 Segmentation으로 보다 정밀하게 탐지하는 기법을 제안한다. 이 기법은 화재 이미지에서 연기제거 및 색상보정을 통해 이미지를 전처리하여 화염 영역을 추출한 뒤 U-Net으로 학습시켜 이미지를 입력하면 불 영역의 Segmentation을 추출하도록 한다.

• Journal of Biomedical Engineering Research
• /
• v.42 no.4
• /
• pp.150-158
• /
• 2021

Intracranial hemorrhage (ICH) refers to acute bleeding inside the intracranial vault. Not only does this devastating disease record a very high mortality rate, but it can also cause serious chronic impairment of sensory, motor, and cognitive functions. Therefore, a prompt and professional diagnosis of the disease is highly critical. Noninvasive brain imaging data are essential for clinicians to efficiently diagnose the locus of brain lesion, volume of bleeding, and subsequent cortical damage, and to take clinical interventions. In particular, computed tomography (CT) images are used most often for the diagnosis of ICH. In order to diagnose ICH through CT images, not only medical specialists with a sufficient number of diagnosis experiences are required, but even when this condition is met, there are many cases where bleeding cannot be successfully detected due to factors such as low signal ratio and artifacts of the image itself. In addition, discrepancies between interpretations or even misinterpretations might exist causing critical clinical consequences. To resolve these clinical problems, we developed a diagnostic model predicting intracranial bleeding and its subtypes (intraparenchymal, intraventricular, subarachnoid, subdural, and epidural) by applying deep learning algorithms to CT images. We also constructed a visualization tool highlighting important regions in a CT image for predicting ICH. Specifically, 1) 27,758 CT brain images from RSNA were pre-processed to minimize the computational load. 2) Three different CNN-based models (ResNet, EfficientNet-B2, and EfficientNet-B7) were trained based on a training image data set. 3) Diagnosis performance of each of the three models was evaluated based on an independent test image data set: As a result of the model comparison, EfficientNet-B7's performance (classification accuracy = 91%) was a way greater than the other models. 4) Finally, based on the result of EfficientNet-B7, we visualized the lesions of internal bleeding using the Grad-CAM. Our research suggests that artificial intelligence-based diagnostic systems can help diagnose and treat brain diseases resolving various problems in clinical situations.

• Proceedings of the Korea Database Society Conference
• /
• 1997.10a
• /
• pp.358-375
• /
• 1997

가. 패션 디자인 기초 정보 수집/분석 - 국내외에 산재하는 패션디자인 정보의 기초자료를 입수 - 디자이너별/ 컬렉션별/주제별로 분류 - 가공 나- 패션디자인정보의 멀티미디어 DATA BASE개발 - 화상(IMAGE)/해설(TEXT)/ SOUND의 복합 DATA BASE SYSTEM - PC통신망 서비스를 위한 DATA개발 다. 패션디자인 관련자료의 DB화 - 패션디자인 이론서 - 패션디자인 컨테스트 / 이벤트 정보 - 패션디자인 교육기관 정보 - 패션브랜드 정보 (내셔널 / 디자이너 / 수입) 라. DATA BASE 공급 서비스 - PC통신망을 통한 서비스(DOWN LOAD 가능) - 디자인작품 IMAGE 및 CONCEPT/ DETAILS/ CAPTION - PC통신을 이용 디자인 인력 구인/구직정보 활용 - 패션디자인 해외유학 정보 마. Inter-NET 서비스 - Inter-NET을 이용 국내디자이너작품 해외 소개(중략)