• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.98-108
• /
• 2023

This paper is an attempt to design segmentation method based on fully convolutional networks (FCN) and attention mechanism. The first five layers of the Visual Geometry Group (VGG) 16 network serve as the coding part in the semantic segmentation network structure with the convolutional layer used to replace pooling to reduce loss of image feature extraction information. The up-sampling and deconvolution unit of the FCN is then used as the decoding part in the semantic segmentation network. In the deconvolution process, the skip structure is used to fuse different levels of information and the attention mechanism is incorporated to reduce accuracy loss. Finally, the segmentation results are obtained through pixel layer classification. The results show that our method outperforms the comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU).

• Journal of Digital Convergence
• /
• v.17 no.1
• /
• pp.123-130
• /
• 2019

One of the most commonly used methods of web recommendation techniques is collaborative filtering. Many studies on collaborative filtering have suggested ways to improve accuracy. This study proposes a method of movie recommendation using Word2Vec and an ensemble convolutional neural networks. First, in the user, movie, and rating information, construct the user sentences and movie sentences. It inputs user sentences and movie sentences into Word2Vec to obtain user vectors and movie vectors. User vectors are entered into user convolution model and movie vectors are input to movie convolution model. The user and the movie convolution models are linked to a fully connected neural network model. Finally, the output layer of the fully connected neural network outputs forecasts of user movie ratings. Experimentation results showed that the accuracy of the technique proposed in this study accuracy of conventional collaborative filtering techniques was improved compared to those of conventional collaborative filtering technique and the technique using Word2Vec and deep neural networks proposed in a similar study.

• Journal of Semiconductor Engineering
• /
• v.2 no.1
• /
• pp.125-129
• /
• 2021

As the interest of deep learning, techniques to control the color of images in image processing field are evolving together. However, there is no clear standard for color, and it is not easy to find a way to represent only the color itself like the color-palette. In this paper, we propose a novel color palette extraction system by chroma fine-tuning with reinforcement learning. It helps to recognize the color combination to represent an input image. First, we use RGBY images to create feature maps by transferring the backbone network with well-trained model-weight which is verified at super resolution convolutional neural networks. Second, feature maps are trained to 3 fully connected layers for the color-palette generation with a generative adversarial network (GAN). Third, we use the reinforcement learning method which only changes chroma information of the GAN-output by slightly moving each Y component of YCbCr color gamut of pixel values up and down. The proposed method outperforms existing color palette extraction methods as given the accuracy of 0.9140.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1431-1445
• /
• 2022

We construct a deep neural network model named ECGResNet. This model can diagnosis diseases based on 12-lead ECG data of eight common cardiovascular diseases with a high accuracy. We chose the 16 Blocks of ResNet50 as the main body of the model and added the Squeeze-and-Excitation module to learn the data information between channels adaptively. We modified the first convolutional layer of ResNet50 which has a convolutional kernel of 7 to a superposition of convolutional kernels of 8 and 16 as our feature extraction method. This way allows the model to focus on the overall trend of the ECG signal while also noticing subtle changes. The model further improves the accuracy of cardiovascular and cerebrovascular disease classification by using a fully connected layer that integrates factors such as gender and age. The ECGResNet model adds Dropout layers to both the residual block and SE module of ResNet50, further avoiding the phenomenon of model overfitting. The model was eventually trained using a five-fold cross-validation and Flooding training method, with an accuracy of 95% on the test set and an F1-score of 0.841.We design a new deep neural network, innovate a multi-scale feature extraction method, and apply the SE module to extract features of ECG data.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1591-1604
• /
• 2020

This study is a study on classifying land cover by applying high-resolution satellite images to deep learning algorithms and verifying the performance of algorithms for each spatial object. For this, the Fully Convolutional Network-based algorithm was selected, and a dataset was constructed using Kompasat-3 satellite images, land cover maps, and forest maps. By applying the constructed data set to the algorithm, each optimal hyperparameter was calculated. Final classification was performed after hyperparameter optimization, and the overall accuracy of DeeplabV3+ was calculated the highest at 81.7%. However, when looking at the accuracy of each category, SegNet showed the best performance in roads and buildings, and U-Net showed the highest accuracy in hardwood trees and discussion items. In the case of Deeplab V3+, it performed better than the other two models in fields, facility cultivation, and grassland. Through the results, the limitations of applying one algorithm for land cover classification were confirmed, and if an appropriate algorithm for each spatial object is applied in the future, it is expected that high quality land cover classification results can be produced.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

• Journal of Biomedical Engineering Research
• /
• v.38 no.5
• /
• pp.237-241
• /
• 2017

Early detection of the pulmonary nodule is important for diagnosis and treatment of lung cancer. Recently, CT has been used as a screening tool for lung nodule detection. And, it has been reported that computer aided detection(CAD) systems can improve the accuracy of the radiologist in detection nodules on CT scan. The previous study has been proposed a method using Convolutional Neural Network(CNN) in Lung CAD system. But the proposed model has a limitation in accuracy due to its sparse layer structure. Therefore, we propose a Deep Convolutional Neural Network to overcome this limitation. The model proposed in this work is consist of 14 layers including 8 convolutional layers and 4 fully connected layers. The CNN model is trained and tested with 61,404 regions-of-interest (ROIs) patches of lung image including 39,760 nodules and 21,644 non-nodules extracted from the Lung Image Database Consortium(LIDC) dataset. We could obtain the classification accuracy of 91.79% with the CNN model presented in this work. To prevent overfitting, we trained the model with Augmented Dataset and regularization term in the cost function. With L1, L2 regularization at Training process, we obtained 92.39%, 92.52% of accuracy respectively. And we obtained 93.52% with data augmentation. In conclusion, we could obtain the accuracy of 93.75% with L2 Regularization and Data Augmentation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1778-1797
• /
• 2021

Document image binarization is an important pre-processing step in document analysis and archiving. The state-of-the-art models for document image binarization are variants of encoder-decoder architectures, such as FCN (fully convolutional network) and U-Net. Despite their success, they still suffer from three limitations: (1) reduced feature map resolution due to consecutive strided pooling or convolutions, (2) multiple scales of target objects, and (3) reduced localization accuracy due to the built-in invariance of deep convolutional neural networks (DCNNs). To overcome these three challenges, we propose an improved semantic segmentation model, referred to as DP-LinkNet, which adopts the D-LinkNet architecture as its backbone, with the proposed hybrid dilated convolution (HDC) and spatial pyramid pooling (SPP) modules between the encoder and the decoder. Extensive experiments are conducted on recent document image binarization competition (DIBCO) and handwritten document image binarization competition (H-DIBCO) benchmark datasets. Results show that our proposed DP-LinkNet outperforms other state-of-the-art techniques by a large margin. Our implementation and the pre-trained models are available at https://github.com/beargolden/DP-LinkNet.

• The Journal of Korean Medicine
• /
• v.44 no.4
• /
• pp.136-149
• /
• 2023

Objectives: Facial diagnosis is an important part of clinical diagnosis in traditional East Asian Medicine. In this paper, we proposed a model to quantitatively classify cold sensitivity using a fully automated facial image analysis system. Methods: We investigated cold sensitivity in 452 subjects. Cold sensitivity was determined using a questionnaire and the Cold Pattern Score (CPS) was used for analysis. Subjects with a CPS score below the first quartile (low CPS group) belonged to the cold non-sensitivity group, and subjects with a CPS score above the third quartile (high CPS group) belonged to the cold sensitivity group. After splitting the facial images into train/validation/test sets, the train and validation set were input into a convolutional neural network to learn the model, and then the classification accuracy was calculated for the test set. Results: The classification accuracy of the low CPS group and high CPS group using facial images in all subjects was 76.17%. The classification accuracy by sex was 69.91% for female and 62.86% for male. It is presumed that the deep learning model used facial color or facial shape to classify the low CPS group and the high CPS group, but it is difficult to specifically determine which feature was more important. Conclusions: The experimental results of this study showed that the low CPS group and the high CPS group can be classified with a modest level of accuracy using only facial images. There was a need to develop more advanced models to increase classification accuracy.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.686-689
• /
• 2018

3D 손 포즈 추정(Hand Pose Estimation, HPE)은 스마트 인간 컴퓨터 인터페이스를 위해서 중요한 기술이다. 이 연구에서는 딥러닝 방법을 기반으로 하여 단일 RGB-Depth 카메라로 촬영한 양손의 3D 손 자세를 실시간으로 인식하는 손 포즈 추정 시스템을 제시한다. 손 포즈 추정 시스템은 4단계로 구성된다. 첫째, Skin Detection 및 Depth cutting 알고리즘을 사용하여 양손을 RGB와 깊이 영상에서 감지하고 추출한다. 둘째, Convolutional Neural Network(CNN) Classifier는 오른손과 왼손을 구별하는데 사용된다. CNN Classifier 는 3개의 convolution layer와 2개의 Fully-Connected Layer로 구성되어 있으며, 추출된 깊이 영상을 입력으로 사용한다. 셋째, 학습된 CNN regressor는 추출된 왼쪽 및 오른쪽 손의 깊이 영상에서 손 관절을 추정하기 위해 다수의 Convolutional Layers, Pooling Layers, Fully Connected Layers로 구성된다. CNN classifier와 regressor는 22,000개 깊이 영상 데이터셋으로 학습된다. 마지막으로, 각 손의 3D 손 자세는 추정된 손 관절 정보로부터 재구성된다. 테스트 결과, CNN classifier는 오른쪽 손과 왼쪽 손을 96.9%의 정확도로 구별할 수 있으며, CNN regressor는 형균 8.48mm의 오차 범위로 3D 손 관절 정보를 추정할 수 있다. 본 연구에서 제안하는 손 포즈 추정 시스템은 가상 현실(virtual reality, VR), 증강 현실(Augmented Reality, AR) 및 융합 현실 (Mixed Reality, MR) 응용 프로그램을 포함한 다양한 응용 분야에서 사용할 수 있다.