• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.5
• /
• pp.115-123
• /
• 2015

The incremental learning method performs well in face face tracking. However, it has a drawback in that it is sensitive to the tracking error in the previous frame due to the environmental changes. In this paper, we propose a selective incremental learning method to track a face more reliably under various conditions. The proposed method is robust to illumination variation by using the LBP(Local Binary Pattern) features for each individual frame. We select patches to be used in incremental learning by using Staggered Multi-Scale LBP, which prevents the propagation of tracking errors occurred in the previous frame. The experimental results show that the proposed method improves the face tracking performance on the videos with environmental changes such as illumination variation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• 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
• /
• v.44 no.7
• /
• 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.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.45-51
• /
• 2021

With the development of deep learning, semantic segmentation methods are being studied in various fields. There is a problem that segmenation accuracy drops in fields that require accuracy such as medical image analysis. In this paper, we improved PSPNet, which is a deep learning based segmentation method to minimized the loss of features during semantic segmentation. Conventional deep learning based segmentation methods result in lower resolution and loss of object features during feature extraction and compression. Due to these losses, the edge and the internal information of the object are lost, and there is a problem that the accuracy at the time of object segmentation is lowered. To solve these problems, we improved PSPNet, which is a semantic segmentation model. The multi-scale attention proposed to the conventional PSPNet was added to prevent feature loss of objects. The feature purification process was performed by applying the attention method to the conventional PPM module. By suppressing unnecessary feature information, eadg and texture information was improved. The proposed method trained on the Cityscapes dataset and use the segmentation index MIoU for quantitative evaluation. As a result of the experiment, the segmentation accuracy was improved by about 1.5% compared to the conventional PSPNet.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• 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)
• /
• v.13 no.10
• /
• 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
• /
• v.7 no.5
• /
• 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.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.3
• /
• pp.95-103
• /
• 2017

Horizon correction is a crucial stage for image composition enhancement. In this paper, we propose a deep learning based method for estimating the slanted angle of a photograph and correcting it. To estimate and correct the horizon direction, existing methods use hand-crafted low-level features such as lines, planes, and gradient distributions. However, these methods may not work well on the images that contain no lines or planes. To tackle this limitation and robustly estimate the slanted angle, we propose a convolutional neural network (CNN) based method to estimate the slanted angle by learning more generic features using a huge dataset. In addition, we utilize multiple adaptive spatial pooling layers to extract multi-scale image features for better performance. In the experimental results, we show our CNN-based approach robustly and accurately estimates the slanted angle of an image regardless of the image content, even if the image contains no lines or planes at all.

• Journal of Korea Multimedia Society
• /
• v.17 no.12
• /
• 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.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.1
• /
• 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.