• Journal of Animal Science and Technology
• /
• v.66 no.1
• /
• pp.167-177
• /
• 2024

Iris segmentation is an initial step for identifying the biometrics of animals when establishing a traceability system for livestock. In this study, we propose a deep learning framework for pixel-wise segmentation of bovine iris with a minimized use of annotation labels utilizing the BovineAAEyes80 public dataset. The proposed image segmentation framework encompasses data collection, data preparation, data augmentation selection, training of 15 deep neural network (DNN) models with varying encoder backbones and segmentation decoder DNNs, and evaluation of the models using multiple metrics and graphical segmentation results. This framework aims to provide comprehensive and in-depth information on each model's training and testing outcomes to optimize bovine iris segmentation performance. In the experiment, U-Net with a VGG16 backbone was identified as the optimal combination of encoder and decoder models for the dataset, achieving an accuracy and dice coefficient score of 99.50% and 98.35%, respectively. Notably, the selected model accurately segmented even corrupted images without proper annotation data. This study contributes to the advancement of iris segmentation and the establishment of a reliable DNN training framework.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.13-14
• /
• 2023

집중 안전 점검의 대상인 노후 건축물에서 균열은 건물의 안전도를 점검할 수 있는 지표이다. 안전 점검에 드론을 활용하면서 고해상도의 드론 기반 균열 이미지 수집이 가능해졌고, 육안이 아닌 AI기반으로 균열을 탐지, 구획화할 수 있다. 본 연구에서는 주변 사물과 배경에 구애받지 않고 안전 점검이 가능한 구획화 알고리즘을 제안한다. METU와 POC데이터셋을 가공하여 데이터셋을 구축하고, 이를 바탕으로 ResNet50을 통해 균열과 유사한 배경을 분류하였으며, 균열 구획화 모델을 선정하여 DesneNet201-UNet++으로 mIoU 82.27%를 달성하였다. 본 연구는 노후 건축물 안전 점검에 필요한 균열 폭 추정에 도움이 될 것으로 기대된다.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1464-1475
• /
• 2020

Due to the spread of COVID-19, the online lecture has become more prevalent. However, it was found that a lot of students and professors are experiencing lack of communication. This study is therefore designed to improve interactive communication between professors and students in real-time online lectures. To do so, we explore deep learning approaches for automatic recognition of students' facial expressions and classification of their understanding into 3 classes (Understand / Neutral / Not Understand). We use 'BlazeFace' model for face detection and 'ResNet-GRU' model for facial expression recognition (FER). We name this entire process 'Degree of Understanding (DoU)' algorithm. DoU algorithm can analyze a multitude of students collectively and present the result in visualized statistics. To our knowledge, this study has great significance in that this is the first study offers the statistics of understanding in lectures using FER. As a result, the algorithm achieved rapid speed of 0.098sec/frame with high accuracy of 94.3% in CPU environment, demonstrating the potential to be applied to real-time online lectures. DoU Algorithm can be extended to various fields where facial expressions play important roles in communications such as interactions with hearing impaired people.

• Journal of Korea Multimedia Society
• /
• v.22 no.5
• /
• pp.547-557
• /
• 2019

To extract the depth map from a single image, a number of CNN-based deep learning methods have been performed in recent research. In this study, the GAN structure of Pix2Pix is maintained. this model allows to converge well, because it has the structure of the generator and the discriminator. But the convolution in this model takes a long time to compute. So we change the convolution form in the generator to a depthwise convolution to improve the speed while preserving the result. Thus, the seven down-sizing convolutional hidden layers in the generator U-Net are changed to depthwise convolution. This type of convolution decreases the number of parameters, and also speeds up computation time. The proposed model shows similar depth map prediction results as in the case of the existing structure, and the computation time in case of a inference is decreased by 64%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.60-79
• /
• 2022

The U-Net architecture-based segmentation models attained remarkable performance in numerous medical image segmentation missions like skin lesion segmentation. Nevertheless, the resolution gradually decreases and the loss of spatial information increases with deeper network. The fusion of adjacent layers is not enough to make up for the lost spatial information, thus resulting in errors of segmentation boundary so as to decline the accuracy of segmentation. To tackle the issue, we propose a new deep learning-based segmentation model. In the decoding stage, the feature channels of each decoding unit are concatenated with all the feature channels of the upper coding unit. Which is done in order to ensure the segmentation effect by integrating spatial and semantic information, and promotes the robustness and generalization of our model by combining the atrous spatial pyramid pooling (ASPP) module and channel attention module (CAM). Extensive experiments on ISIC2016 and ISIC2017 common datasets proved that our model implements well and outperforms compared segmentation models for skin lesion segmentation.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.134-141
• /
• 2023

We present a novel method aimed at refining ground truth data through regularization and modification, particularly applicable when working with the original ground truth set. Enhancing the performance of deep neural networks is achieved by applying regularization techniques to the existing ground truth data. In many machine learning tasks requiring pixel-level segmentation sets, accurately delineating objects is vital. However, it proves challenging for thin and elongated objects such as blood vessels in X-ray coronary angiography, often resulting in inconsistent generation of ground truth data. This method involves an analysis of the quality of training set pairs - comprising images and ground truth data - to automatically regulate and modify the boundaries of ground truth segmentation. Employing the active contour model and a recursive ground truth generation approach results in stable and precisely defined boundary contours. Following the regularization and adjustment of the ground truth set, there is a substantial improvement in the performance of deep neural networks.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1371-1388
• /
• 2023

Floods are becoming more severe and frequent due to global warming-induced climate change. Water disasters are rising in Korea due to severe rainfall and wet seasons. This makes preventive climate change measures and efficient water catastrophe responses crucial, and synthetic aperture radar satellite imagery can help. This research created 1,423 water body learning datasets for individual water body regions along the Han and Nakdong waterways to reflect domestic water body properties discovered by Sentinel-1 satellite radar imagery. We created a document with exact data annotation criteria for many situations. After the dataset was processed, U-Net, a deep learning model, analyzed water body detection results. The results from applying the learned model to water body locations not involved in the learning process were studied to validate soil water body monitoring on a national scale. The analysis showed that the created water body area detected water bodies accurately (F1-Score: 0.987, Intersection over Union [IoU]: 0.955). Other domestic water body regions not used for training and evaluation showed similar accuracy (F1-Score: 0.941, IoU: 0.89). Both outcomes showed that the computer accurately spotted water bodies in most areas, however tiny streams and gloomy areas had problems. This work should improve water resource change and disaster damage surveillance. Future studies will likely include more water body attribute datasets. Such databases could help manage and monitor water bodies nationwide and shed light on misclassified regions.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.1
• /
• pp.17-27
• /
• 2023

Weeds are one of the factors that reduce crop yield through nutrient and photosynthetic competition. Quantification of weed density are an important part of making accurate decisions for precision weeding. In this study, we tried to quantify the density of weeds in images of maize fields taken by unmanned aerial vehicle (UAV). UAV image data collection took place in maize fields from May 17 to June 4, 2021, when maize was in its early growth stage. UAV images were labeled with pixels from maize and those without and the cropped to be used as the input data of the semantic segmentation network for the maize detection model. We trained a model to separate maize from background using the deep learning segmentation networks DeepLabV3+, U-Net, Linknet, and FPN. All four models showed pixel accuracy of 0.97, and the mIOU score was 0.76 and 0.74 in DeepLabV3+ and U-Net, higher than 0.69 for Linknet and FPN. Weed density was calculated as the difference between the green area classified as ExGR (Excess green-Excess red) and the maize area predicted by the model. Each image evaluated for weed density was recombined to quantify and visualize the distribution and density of weeds in a wide range of maize fields. We propose a method to quantify weed density for accurate weeding by effectively separating weeds, maize, and background from UAV images of maize fields.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1691-1707
• /
• 2022

Cheonji Lake, the caldera of Baekdu Mountain, located on the border of the Korean Peninsula and China, alternates between melting and freezing seasonally. There is a magma chamber beneath Cheonji, and variations in the magma chamber cause volcanic antecedents such as changes in the temperature and water pressure of hot spring water. Consequently, there is an abnormal region in Cheonji where ice melts quicker than in other areas, freezes late even during the freezing period, and has a high-temperature water surface. The abnormal area is a discharge region for hot spring water, and its ice gradient may be used to monitor volcanic activity. However, due to geographical, political and spatial issues, periodic observation of abnormal regions of Cheonji is limited. In this study, the degree of ice change in the optimal region was quantified using a Landsat -5/-7/-8 optical satellite image and a Modified U-Net regression model. From January 22, 1985 to December 8, 2020, the Visible and Near Infrared (VNIR) band of 83 Landsat images including anomalous regions was utilized. Using the relative spectral reflectance of water and ice in the VNIR band, unique data were generated for quantitative ice variability monitoring. To preserve as much information as possible from the visible and near-infrared bands, ice gradient was noticed by applying it to U-Net with two encoders, achieving good prediction accuracy with a Root Mean Square Error (RMSE) of 140 and a correlation value of 0.9968. Since the ice change value can be seen with high precision from Landsat images using Modified U-Net in the future may be utilized as one of the methods to monitor Baekdu Mountain's volcanic activity, and a more specific volcano monitoring system can be built.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.377-380
• /
• 2023

본 논문에서는 합성곱 신경망(Convolutional Neural Networks, CNN)과 탄성왜곡(Elastic Distortion) 기법을 통한 데이터 증강 기법을 활용하여 학습 데이터를 구축하는 프레임워크를 제안한다. 실제 균열 이미지는 정형화된 형태가 없고 복잡한 패턴을 지니고 있어 구하기 어려울 뿐만 아니라, 데이터를 확보할 때 위험한 상황에 노출될 우려가 있다. 이러한 데이터베이스 구축 문제점을 본 논문에서 제안하는 데이터 증강 기법을 통해 비용적, 시간적 측면에서 효율적으로 해결한다. 세부적으로는 DeepCrack의 데이터를 10배 이상 증가하여 실제 균열의 특징을 반영한 메타 데이터를 생성하여 U-net을 학습하였다. 성능을 검증하기 위해 균열 탐지 연구를 진행한 결과, IoU 정확도가 향상되었음을 확인하였다. 데이터를 증강하지 않았을 경우 잘못 예측(FP)된 경우의 비율이 약 25%였으나, 데이터 증강을 통해 3%까지 감소하였음을 확인하였다.