• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5546-5559
• /
• 2019

Facial action units (AUs) have recently drawn increased attention because they can be used to recognize facial expressions. A variety of methods have been designed for frontal-view AU detection, but few have been able to handle multi-view face images. In this paper we propose a method for multi-view facial AU detection using a fused multilayer, multi-task, and multi-label deep learning network. The network can complete two tasks: AU detection and facial view detection. AU detection is a multi-label problem and facial view detection is a single-label problem. A residual network and multilayer fusion are applied to obtain more representative features. Our method is effective and performs well. The F1 score on FERA 2017 is 13.1% higher than the baseline. The facial view recognition accuracy is 0.991. This shows that our multi-task, multi-label model could achieve good performance on the two tasks.

• The Korean Journal of Applied Statistics
• /
• v.32 no.1
• /
• pp.41-68
• /
• 2019

Multi-view learning considers data from various viewpoints as well as attempts to integrate various information from data. Multi-view learning has been studied recently and has showed superior performance to a model learned from only a single view. With the introduction of deep learning techniques to a multi-view learning approach, it has showed good results in various fields such as image, text, voice, and video. In this study, we introduce how multi-view learning methods solve various problems faced in human behavior recognition, medical areas, information retrieval and facial expression recognition. In addition, we review data integration principles of multi-view learning methods by classifying traditional multi-view learning methods into data integration, classifiers integration, and representation integration. Finally, we examine how CNN, RNN, RBM, Autoencoder, and GAN, which are commonly used among various deep learning methods, are applied to multi-view learning algorithms. We categorize CNN and RNN-based learning methods as supervised learning, and RBM, Autoencoder, and GAN-based learning methods as unsupervised learning.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.3
• /
• pp.177-183
• /
• 2022

To measure the size and weight of the fish, we developed an automatic fish size measurement system using a deep neural network, where the YOLO (You Only Look Once)v3 model was used. To detect fish, an IP camera with infrared function was installed over the fish pool to acquire image data and used as input data for the deep neural network. Using the bounding box information generated as a result of detecting the fish and the structure for which the actual length is known, the size of the fish can be obtained. A GUI (Graphical User Interface) program was implemented using LabVIEW and RTSP (Real-Time Streaming protocol). The automatic fish size measurement system shows the results and stores them in a database for future work.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2006.11a
• /
• pp.265-268
• /
• 2006

The preliminary design of a deep-sea injection system for carbon dioxide ocean sequestration is performed. Common functional requirements for a deep-sea injection system of mid-depth type and lake type are determined, Liquid transport system, liquid storage system and liquid injection system are conceptually determined for the functional requirements. For liquid injection system, the control of flow rate and temperature of liquid $CO_2$ in the injection pipe is needed in the view of internal flow. The function of depressing VIV(Vortex Induced Vibration) is also required in the view of dynamic stability of the injection pipe. A case study is performed for $CO_2$ sequestration capacity of 10 million tons per year. In this study, the total number of injection ships, the flow rate of liquid $CO_2$ and the configuration of a injection pipe are designed. The static structural analysis of the injection pipe is also performed. Finally the preliminary design of a deep-sea injection system is proposed.

• Journal of Multimedia Information System
• /
• v.7 no.1
• /
• pp.11-16
• /
• 2020

Deep Learning has become the most important technology in the field of artificial intelligence machine learning, with its high performance overwhelming existing methods in various applications. In this paper, an interactive window service based on object recognition technology is proposed. The main goal is to implement an object recognition technology using this deep learning technology to remove the existing eye tracking technology, which requires users to wear eye tracking devices themselves, and to implement an eye tracking technology that uses only usual cameras to track users' eye. We design an interactive system based on efficient eye detection and pupil tracking method that can verify the user's eye movement. To estimate the view-direction of user's eye, we initialize to make the reference (origin) coordinate. Then the view direction is estimated from the extracted eye pupils from the origin coordinate. Also, we propose a blink detection technique based on the eye apply ratio (EAR). With the extracted view direction and eye action, we provide some augmented information of interest without the existing complex and expensive eye-tracking systems with various service topics and situations. For verification, the user guiding service is implemented as a proto-type model with the school map to inform the location information of the desired location or building.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.2
• /
• pp.71-78
• /
• 2020

This paper proposes vision sensors and deep learning-based around view monitoring system for ship berthing. Ship berthing to the port requires precise relative position and relative speed information between the mooring facility and the ship. For ships of Handysize or higher, the vesselships must be docked with the help of pilots and tugboats. In the case of ships handling dangerous cargo, tug boats push the ship and dock it in the port, using the distance and velocity information receiving from the berthing aid system (BAS). However, the existing BAS is very expensive and there is a limit on the size of the vessel that can be measured. Also, there is a limitation that it is difficult to measure distance and speed when there are obstacles near the port. This paper proposes a relative distance and speed estimation system that can be used as a ship berthing assist system. The proposed system is verified by comparing the performance with the existing laser-based distance and speed measurement system through the field tests at the actual port.

• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.26 no.2
• /
• pp.7-17
• /
• 1996

This study was performed to determine the postitional relationships of two lobes of parenchyma and to analysis the anatomical feature and its variations of duct on the panoramic views of the normal parotid glands in adults. Materials included 66 panoramic views and anterioposterior views of sialograms of selected persons and the radiograms of the gland experimentally reproduced on dry skull with lead foil and the reference images of computed tomograms of normal persons. Results were as follows : 1. On panoramic view of sialogram, the superficial lobe was revealed with totally being superimposed with the mandibular ramus and condyle and its tail portion superimposed with mandibular angle area, the deep lobe was revealed between the posterior border of the ramus and the mastoid process, and the isthmus was begin from the marked furcation off main duct and superimposed partially with the medial part of the deep lobe. 2, The mean length and the lateral extension of parenchyma was 63.18±8.05mm and 21.78±4.87mm respectively on panoramic view and showed no statistical relationship between them. 3. The main duct was generally perpendicular to the posterior border of ramus at middle portion and its configurations revealed 57,58％ of curvilinear type, 21.21％ sigmoid type, 15.15％ reverse sigmoid type. 4, The interlobular ducts of the deep lobe showed relatively well defined features between the mandibular ramus and the mastoid process.

• Journal of Multimedia Information System
• /
• v.6 no.4
• /
• pp.235-238
• /
• 2019

In real world object detection is an active research topic for understanding different objects from images. There are different models presented in past and had significant results. In this paper we are presenting vehicle logo detection using previous object detection models such as You only look once (YOLO) and Faster Region-based CNN (F-RCNN). Both the front and rear view of the vehicles were used for training and testing the proposed method. Along with deep learning an image pre-processing algorithm called perspective transformation is proposed for all the test images. Using perspective transformation, the top view images were transformed into front view images. This algorithm has higher detection rate as compared to raw images. Furthermore, YOLO model has better result as compare to F-RCNN model.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.929-937
• /
• 2020

In this manuscript, the UNet++ model, which is one of the representative deep learning techniques for semantic segmentation, was used to detect changes in temporal satellite images. To analyze the learning results according to various loss functions, we evaluated the change detection results using trained UNet++ models by binary cross entropy and the Jaccard coefficient. In addition, the learning results of the deep learning model were analyzed compared to existing pixel-based change detection algorithms by using WorldView-3 images. In the experiment, it was confirmed that the performance of the deep learning model could be determined depending on the characteristics of the loss function, but it showed better results compared to the existing techniques.

• Transactions of Materials Processing
• /
• v.10 no.6
• /
• pp.456-464
• /
• 2001

Deep drawing and ironing are tile major process today in manufacturing of aluminum alloy battery case used in cellular phone. Most of these process require multi-stage ironing following the deep drawing and redrawing processes. The practical aspects of this technology are well known and gained through extensive experiment and production know-how. However, the fundamental aspects of these processes are relatively less known. Thus, it is expected that process analysis using FEM techniques would provide additional detailed information that could be utilized to improve the process condition. This paper illustrates the application of process modeling to deep drawing and redrawing operations. To verify the simulation results, the experimental investigations were also carried out on a real industrial product. The numerical analysis by FEM shows good agreement with the experimental results in view of the deformation shape of the product. A commercially available finite element code LS-DYNA3D was used to simulate deep drawing and redrawing operations.