• Journal of the Korea Computer Graphics Society
• /
• v.26 no.3
• /
• pp.31-37
• /
• 2020

Identification of the mandibular canal path in Computed Tomography (CT) scans is important in dental implantology. Typically, prior to the implant planning, dentists find a sagittal plane where the mandibular canal path is maximally observed, to manually identify the mandibular canal. However, this is time-consuming and requires extensive experience. In this paper, we propose a deep-learning-based framework to detect the desired sagittal plane automatically. This is accomplished by utilizing two main techniques: 1) a modified version of the iterative transformation network (ITN) method for obtaining initial planes, and 2) a fine searching method based on a convolutional neural network (CNN) classifier for detecting the desirable sagittal plane. This combination of techniques facilitates accurate plane detection, which is a limitation of the stand-alone ITN method. We have tested on a number of CT datasets to demonstrate that the proposed method can achieve more satisfactory results compared to the ITN method. This allows dentists to identify the mandibular canal path efficiently, providing a foundation for future research into more efficient, automatic mandibular canal detection methods.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.2
• /
• pp.63-70
• /
• 2022

Although 2D Object detection has been largely improved in the past years with the advance of deep learning methods and the use of large labeled image datasets, 3D object detection from 2D imagery is a challenging problem in a variety of applications such as robotics, due to the lack of data and diversity of appearances and shapes of objects within a category. Google has just announced the launch of Objectron that has a novel data pipeline using mobile augmented reality session data. However, it also is corresponding to 2D-driven 3D object detection technique. This study explores more mature 2D object detection method, and applies its 2D projection to Objectron 3D lifting system. Most object detection methods use bounding boxes to encode and represent the object shape and location. In this work, we explore a stochastic representation of object regions using Gaussian distributions. We also present a similarity measure for the Gaussian distributions based on the Hellinger Distance, which can be viewed as a stochastic Intersection-over-Union. Our experimental results show that the proposed Gaussian representations are closer to annotated segmentation masks in available datasets. Thus, less accuracy problem that is one of several limitations of Objectron can be relaxed.

• The Korean Journal of Applied Statistics
• /
• v.36 no.2
• /
• pp.101-114
• /
• 2023

The data augmentation technique is effectively used to solve the problem of overfitting the model by allowing the training dataset to be viewed from various perspectives. In addition to image augmentation techniques such as rotation, cropping, horizontal flip, and vertical flip, occlusion-based data augmentation methods such as Cutmix and Cutout have been proposed. For models based on speech data, it is possible to use an occlusion-based data-based augmentation technique after converting a 1D speech signal into a 2D spectrogram. In particular, SpecAugment is an occlusion-based augmentation technique for speech spectrograms. In this study, we intend to compare and study data augmentation techniques that can be used in the problem of false-voice detection. Using data from the ASVspoof2017 and ASVspoof2019 competitions held to detect fake audio, a dataset applied with Cutout, Cutmix, and SpecAugment, an occlusion-based data augmentation method, was trained through an LCNN model. All three augmentation techniques, Cutout, Cutmix, and SpecAugment, generally improved the performance of the model. In ASVspoof2017, Cutmix, in ASVspoof2019 LA, Mixup, and in ASVspoof2019 PA, SpecAugment showed the best performance. In addition, increasing the number of masks for SpecAugment helps to improve performance. In conclusion, it is understood that the appropriate augmentation technique differs depending on the situation and data.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.246-246
• /
• 2021

본 연구는 강우 발생시 유량을 추정하는 것에 목적이 있다. 이를 위해 본 연구는 선행연구의 모형 개발방법론에서 벗어나 딥러닝 알고리즘 중 하나인 합성곱 신경망 (convolution neural network)과 수문학적 이미지 (hydrological image)를 이용하여 강우 발생시 유량을 추정하였다. 합성곱 신경망은 일반적으로 분류 문제 (classification)을 해결하기 위한 목적으로 개발되었기 때문에 불특정 연속변수인 유량을 모의하기에는 적합하지 않다. 이를 위해 본 연구에서는 합성곱 신경망의 완전 연결층 (Fully connected layer)를 개선하여 연속변수를 모의할 수 있도록 개선하였다. 대부분 합성곱 신경망은 RGB (red, green, blue) 사진 (photograph)을 이용하여 해당 사진이 나타내는 것을 예측하는 목적으로 사용하지만, 본 연구의 경우 일반 RGB 사진을 이용하여 유출량을 예측하는 것은 경험적 모형의 전제(독립변수와 종속변수의 관계)를 무너뜨리는 결과를 초래할 수 있다. 이를 위해 본 연구에서는 임의의 유역에 대해 2차원 공간에서 무차원의 수문학적 속성을 갖는 grid의 집합으로 정의되는 수문학적 이미지는 입력자료로 활용했다. 합성곱 신경망의 구조는 Convolution Layer와 Pulling Layer가 5회 반복하는 구조로 설정하고, 이후 Flatten Layer, 2개의 Dense Layer, 1개의 Batch Normalization Layer를 배열하고, 다시 1개의 Dense Layer가 이어지는 구조로 설계하였다. 마지막 Dense Layer의 활성화 함수는 분류모형에 이용되는 softmax 또는 sigmoid 함수를 대신하여 회귀모형에서 자주 사용되는 Linear 함수로 설정하였다. 이와 함께 각 층의 활성화 함수는 정규화 선형함수 (ReLu)를 이용하였으며, 모형의 학습 평가 및 검정을 판단하기 위해 MSE 및 MAE를 사용했다. 또한, 모형평가는 NSE와 RMSE를 이용하였다. 그 결과, 모형의 학습 평가에 대한 MSE는 11.629.8 m3/s에서 118.6 m3/s로, MAE는 25.4 m3/s에서 4.7 m3/s로 감소하였으며, 모형의 검정에 대한 MSE는 1,997.9 m3/s에서 527.9 m3/s로, MAE는 21.5 m3/s에서 9.4 m3/s로 감소한 것으로 나타났다. 또한, 모형평가를 위한 NSE는 0.7, RMSE는 27.0 m3/s로 나타나, 본 연구의 모형은 양호(moderate)한 것으로 판단하였다. 이에, 본 연구를 통해 제시된 방법론에 기반을 두어 CNN 모형 구조의 확장과 수문학적 이미지의 개선 또는 새로운 이미지 개발 등을 추진할 경우 모형의 예측 성능이 향상될 수 있는 여지가 있으며, 원격탐사 분야나, 위성 영상을 이용한 전 지구적 또는 광역 단위의 실시간 유량 모의 분야 등으로의 응용이 가능할 것으로 기대된다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1321-1330
• /
• 2023

This study attempts to address the problem of 3D pose estimation for multiple human objects through a single image generated during the character development process that can be used in augmented reality. In the existing top-down method, all objects in the image are first detected, and then each is reconstructed independently. The problem is that inconsistent results may occur due to overlap or depth order mismatch between the reconstructed objects. The goal of this study is to solve these problems and develop a single network that provides consistent 3D reconstruction of all humans in a scene. Integrating a human body model based on the SMPL parametric system into a top-down framework became an important choice. Through this, two types of collision loss based on distance field and loss that considers depth order were introduced. The first loss prevents overlap between reconstructed people, and the second loss adjusts the depth ordering of people to render occlusion inference and annotated instance segmentation consistently. This method allows depth information to be provided to the network without explicit 3D annotation of the image. Experimental results show that this study's methodology performs better than existing methods on standard 3D pose benchmarks, and the proposed losses enable more consistent reconstruction from natural images.