• 전자공학회논문지
• /
• 제52권5호
• /
• pp.115-123
• /
• 2015

점진 학습은 비교적 높은 얼굴 추적 성능을 보이지만, 환경적인 변화로 인해 추적에 오차가 발생하면 그 이후의 추적에 오차가 전파되어 추적 성능이 감소한다는 단점이 있다. 본 논문에서는, 다양한 변이 조건에서 강인하게 동작할 수 있는 선택적인 점진 학습 방법을 제안한다. 먼저, 개별 프레임에 대해 LBP(Local Binary Pattern) 특징을 추출하여 사용함으로써 조명 변이에 보다 강인하게 동작 할수 있고, Staggered Multi-Scale LBP를 사용하여 점진 학습에 사용할 패치(patch)를 선택하여 이전 프레임에서의 오차가 전파되는 것을 방지하였다. 실험을 통해, 제안한 방법이 조명 변이와 같은 환경적 변이가 존재하는 비디오 영상에 대해서도 기존의 추적 방법들보다 우수한 얼굴 추적 성능을 보이는 것을 확인할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권5호
• /
• pp.1597-1610
• /
• 2022

At present, the main method of high-speed train chassis detection is using computer vision technology to extract keypoints from two related chassis images firstly, then matching these keypoints to find the pixel-level correspondence between these two images, finally, detection and other steps are performed. The quality and accuracy of image matching are very important for subsequent defect detection. Current traditional matching methods are difficult to meet the actual requirements for the generalization of complex scenes such as weather, illumination, and seasonal changes. Therefore, it is of great significance to study the high-speed train image matching method based on deep learning. This paper establishes a high-speed train chassis image matching dataset, including random perspective changes and optical distortion, to simulate the changes in the actual working environment of the high-speed rail system as much as possible. This work designs a convolutional neural network to intensively extract keypoints, so as to alleviate the problems of current methods. With multi-level features, on the one hand, the network restores low-level details, thereby improving the localization accuracy of keypoints, on the other hand, the network can generate robust keypoint descriptors. Detailed experiments show the huge improvement of the proposed network over traditional methods.

• Molecules and Cells
• /
• 제44권7호
• /
• pp.433-443
• /
• 2021

Multi-omics approaches are novel frameworks that integrate multiple omics datasets generated from the same patients to better understand the molecular and clinical features of cancers. A wide range of emerging omics and multi-view clustering algorithms now provide unprecedented opportunities to further classify cancers into subtypes, improve the survival prediction and therapeutic outcome of these subtypes, and understand key pathophysiological processes through different molecular layers. In this review, we overview the concept and rationale of multi-omics approaches in cancer research. We also introduce recent advances in the development of multi-omics algorithms and integration methods for multiple-layered datasets from cancer patients. Finally, we summarize the latest findings from large-scale multi-omics studies of various cancers and their implications for patient subtyping and drug development.

• 한국융합학회논문지
• /
• 제12권11호
• /
• pp.45-51
• /
• 2021

딥러닝의 발전으로 인하여 의미론적 분할 방법은 다양한 분야에서 연구되고 있다. 의료 영상 분석과 같이 정확성을 요구하는 분야에서 분할 정확도가 떨어지는 문제가 있다. 본 논문은 의미론적 분할 시 특징 손실을 최소화하기 위해 딥러닝 기반 분할 방법인 PSPNet을 개선하였다. 기존 딥러닝 기반의 분할 방법은 특징 추출 및 압축 과정에서 해상도가 낮아져 객체에 대한 특징 손실이 발생한다. 이러한 손실로 윤곽선이나 객체 내부 정보에 손실이 발생하여 객체 분류 시 정확도가 낮아지는 문제가 있다. 이러한 문제를 해결하기 위해 의미론적 분할 모델인 PSPNet을 개선하였다. 기존 PSPNet에 제안하는 multi scale attention을 추가하여 객체의 특징 손실을 방지하였다. 기존 PPM 모듈에 attention 방법을 적용하여 특징 정제 과정을 수행하였다. 불필요한 특징 정보를 억제함으로써 윤곽선 및 질감 정보가 개선되었다. 제안하는 방법은 Cityscapes 데이터 셋으로 학습하였으며, 정량적 평가를 위해 분할 지표인 MIoU를 사용하였다. 실험을 통해 기존 PSPNet 대비 분할 정확도가 약 1.5% 향상되었다.

• Journal of Electrical Engineering and Technology
• /
• 제10권4호
• /
• pp.1851-1863
• /
• 2015

– In the paper, to handle the problem of traditional bag-of-features model ignoring the spatial relationship of local features in human action recognition, we proposed a Multiscale Spatial Position Coding under Locality Constraint method. Specifically, to describe this spatial relationship, we proposed a mixed feature combining motion feature and multi-spatial-scale configuration. To utilize temporal information between features, sub spatial-temporal-volumes are built. Next, the pooled features of sub-STVs are obtained via max-pooling method. In classification stage, the Locality-Constrained Group Sparse Representation is adopted to utilize the intrinsic group information of the sub-STV features. The experimental results on the KTH, Weizmann, and UCF sports datasets show that our action recognition system outperforms the classical local ST feature-based recognition systems published recently.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권10호
• /
• pp.5112-5129
• /
• 2019

Image enhancement is a challenging problem in the field of image processing, especially low-light color images enhancement. This paper proposed a robust and comprehensive enhancement method based several points. First, the idea of bright channel is introduced to estimate the illumination map which is used to attain the enhancing result with Retinex model, and the color constancy is keep as well. Second, in order eliminate the illumination offsets wrongly estimated, morphological closing operation is used to modify the initial estimating illumination. Furthermore, in order to avoid fabricating edges, enlarged noises and over-smoothed visual features appearing in enhancing result, a multi-scale closing operation is used. At last, in order to avoiding the haloes and artifacts presented in enhancing result caused by gradient information lost in previous step, guided filtering is introduced to deal with previous result with guided image is initial bright channel. The proposed method can get good illumination map, and attain very effective enhancing results, including dark area is enhanced with more visual features, color natural and constancy, avoiding artifacts and over-enhanced, and eliminating Incorrect light offsets.

• Coupled systems mechanics
• /
• 제7권5호
• /
• pp.509-524
• /
• 2018

A hierarchical multi-scale modeling strategy devoted to the study of a Bitumen-Bound Gravel (BBG) is presented in this paper. More precisely, the paper investigates the temperature-dependent linear viscoelastic of the material when submitted to low deformations levels and moderate number of cycles. In such a hierarchical approach, 3D digital Representative Elementary Volumes are built and the outcomes at a scale (here, the sub-mesoscale) are used as input data at the next higher scale (here, the mesoscale). The viscoelastic behavior of the bituminous phases at each scale is taken into account by means of a generalized Maxwell model: the bulk part of the behavior is separated from the deviatoric one and bulk and shear moduli are expanded into Prony series. Furthermore, the viscoelastic phases are considered to be thermorheologically simple: time and temperature are not independent. This behavior is reproduced by the Williams-Landel-Ferry law. By means of the FE simulations of stress relaxation tests, the parameters of the various features of this temperature-dependent viscoelastic behavior are identified.

• 한국컴퓨터그래픽스학회논문지
• /
• 제23권3호
• /
• pp.95-103
• /
• 2017

본 논문은 딥 러닝(deep learning)을 이용하여 입력 영상의 기울어진 정도를 측정하고 수평에 맞게 바로 세우는 방법을 제시한다. 기존 방법들은 일반적으로 영상 내에서 선분, 평면 등 하위 레벨의 특징들을 추출한 후 이를 이용해 영상의 기울어진 정도를 측정한다. 이러한 방법들은 영상 내에 선이나 평면이 존재하지 않는 경우에는 제대로 동작하지 않는다. 본 논문에서는 대규모 데이터 셋을 통해 영상의 다양한 특징들에 대해 학습 가능한 Convolutional Neural Network (CNN)를 이용하여 인물이나 복잡한 배경으로 구성된 기울어진 영상에 대해서도 강인하게 동작하는 프레임워크를 제시한다. 또한, 네트워크에 가변 공간적 (adaptive spatial) pooling 레이어를 추가하여 영상의 다중 스케일 특징을 동시에 고려할 수 있게 하여 영상의 기울어진 정도를 측정하는 성능을 높인다. 실험 결과를 통해 다양한 콘텐츠를 포함한 영상의 기울어짐을 높은 정확도로 바로 세울 수 있음을 확인할 수 있다.

• 한국멀티미디어학회논문지
• /
• 제17권12호
• /
• pp.1383-1392
• /
• 2014

In this paper, we proposed a method to automatically determine the optimal radius through multi-scale LBP operation generalizing the size of radius variation and boosting learning in facial emotion recognition. When we looked at the distribution of features vectors, the most common was $LBP_{8.1}$ of 31% and sum of $LBP_{8.1}$ and $LBP_{8.2}$ was 57.5%, $LBP_{8.3}$, $LBP_{8.4}$, and $LBP_{8.5}$ were respectively 18.5%, 12.0%, and 12.0%. It was found that the patterns of relatively greater radius express characteristics of face well. In case of normal and anger, $LBP_{8.1}$ and $LBP_{8.2}$ were mainly distributed. The distribution of $LBP_{8.3}$ is greater than or equal to the that of $LBP_{8.1}$ in laugh and surprise. It was found that the radius greater than 1 or 2 was useful for a specific emotion recognition. The facial expression recognition rate of proposed multi-scale LBP method was 97.5%. This showed the superiority of proposed method and it was confirmed through various experiments.

• 산업경영시스템학회지
• /
• 제43권1호
• /
• pp.16-25
• /
• 2020

Vegetation segmentation in a field color image is a process of distinguishing vegetation objects of interests like crops and weeds from a background of soil and/or other residues. The performance of the process is crucial in automatic precision agriculture which includes weed control and crop status monitoring. To facilitate the segmentation, color indices have predominantly been used to transform the color image into its gray-scale image. A thresholding technique like the Otsu method is then applied to distinguish vegetation parts from the background. An obvious demerit of the thresholding based segmentation will be that classification of each pixel into vegetation or background is carried out solely by using the color feature of the pixel itself without taking into account color features of its neighboring pixels. This paper presents a new pixel-based segmentation method which employs a multi-layer perceptron neural network to classify the gray-scale image into vegetation and nonvegetation pixels. The input data of the neural network for each pixel are 2-dimensional gray-level values surrounding the pixel. To generate a gray-scale image from a raw RGB color image, a well-known color index called Excess Green minus Excess Red Index was used. Experimental results using 80 field images of 4 vegetation species demonstrate the superiority of the neural network to existing threshold-based segmentation methods in terms of accuracy, precision, recall, and harmonic mean.