• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.6
• /
• pp.309-317
• /
• 2022

In this paper, we propose a machine learning-based copy-move forgery detection network with dual branches. Because the rotation or scaling operation is frequently involved in copy-move forger, the conventional convolutional neural network is not effectively applied in detecting copy-move tampering. Therefore, we divide the input into rotation-invariant and scaling-invariant features based on the wavelet coefficients. Each of the features is input to different branches having the same structure, and is fused in the combination module. Each branch comprises feature extraction, correlation, and mask decoder modules. In the proposed network, VGG16 is used for the feature extraction module. To check similarity of features generated by the feature extraction module, the conventional correlation module used. Finally, the mask decoder model is applied to develop a pixel-level localization map. We perform experiments on test dataset and compare the proposed method with state-of-the-art tampering localization methods. The results demonstrate that the proposed scheme outperforms the existing approaches.

• Journal of Korean Society of Water and Wastewater
• /
• v.18 no.5
• /
• pp.598-607
• /
• 2004

In this study, the effects of two pre-treatment processes were observed prior to membrane filtration: pre-coagulation and pre-ozonation. To compare the effect of two above-mentioned pre-treatments, we adopted the four schemes: first one is direct membrane filtration of river surface water, second one is membrane filtration after pre-coagulation, third one is membrane filtration after pre-ozonation and fourth one is membrane filtration after pre-coagulation and pre-ozonation. There are two exceptional characteristics in applied processes. One is the usage of the MF membrane which has high ozone resisting characteristic. Therefore, ozone resides in membrane module during filtration. The other is adoption of Jet Mixed Separator (JMS) as coagulation-sedimentation process. The change in transmembrane pressure and permeate water quality were also examined. As a result, considering the filtration performance efficiency and permeate water quality, the process composed of filtration with combination of both pre-coagulation and pre-ozonation was proved most effective. The improved efficiency was due to the reduction of loading rate of fouling inducing materials to membrane module by coagulation process as well as variable reactions, such as degradation, particle destabilization and coagulation, occurred by residual ozone in membrane module. The additional effect of pre-coagulation before pre-ozonation is suppression of AOC, one of the by-products induced by ozonation. Therefore, combination of pre-coagulation and pre-ozonation is the effective process to overcome the major de-merit of ozonation i.e. by-products formation.

• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.1113-1121
• /
• 2019

In this paper, we propose the face anti-spoofing method based on combination of luminance and chrominance with convolutional neural networks. The proposed method extracts luminance and chrominance features independently from live and fake faces by using stacked convolutional neural networks and auxiliary networks. Unlike previous methods, an attention module has been adopted to adaptively combine extracted features instead of simply concatenating them. In addition, we propose a new loss function, called the contrast loss, to learn the classifier more efficiently. Specifically, the contrast loss improves the discriminative power of the features by maximizing the distance of the inter-class features while minimizing that of the intra-class features. Experimental results demonstrate that our method achieves the significant improvement for face anti-spoofing compared to existing methods.

• International journal of advanced smart convergence
• /
• v.6 no.1
• /
• pp.76-81
• /
• 2017

This paper presents a low cost and flexible IoT enabled smart LED controller using Arduino that is used for emergency exit signs. The Internet of Things (IoT) is become a global network that put together physical objects using network communications for the purpose of inter-communication of devices, access information on internet, interaction with users as well as permanent connected environment. A crucial point in this paper, is underlined on the potential key points of applying the Arduino platform as low cost, easy to use microcontroller with combination of various sensors applied in IoT technology to facilitate and establishment of intelligent products. To demonstrate the feasibility and effectiveness of the system, devices such as LED strip, combination of various sensors, Arduino, power plug and ZigBee module have been integrated to setup smart emergency exit sign system. The general concept of the proposed system design discussed in this paper is all about the combination of various sensor such as smoke detector sensor, humidity, temperature sensor, glass break sensors as well as camera sensor that are connected to the main controller (Arduino) for the purpose of communicating with LED exit signs displayer and dedicated PC monitors from integrated system monitoring (controller room) through gateway devices using Zig bee module. A critical appraisal of the approach in the area concludes the paper.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.11
• /
• pp.1133-1144
• /
• 2019

Recently, the amount of image on the Internet has rapidly increased, due to the advancement of smart devices and various approaches to effective image retrieval have been researched under these situation. Existing image retrieval methods simply detect the objects in a image and carry out image retrieval based on the label of each object. Therefore, the semantic gap occurs between the image desired by a user and the image obtained from the retrieval result. To reduce the semantic gap in image retrievals, we connect the module for multiple objects classification based on deep learning with the module for human behavior classification. And we combine the connected modules with a behavior ontology. That is to say, we propose an image retrieval system considering the relationship between objects by using the combination of deep learning and behavior ontology. We analyzed the experiment results using walking and running data to take into account dynamic behaviors in images. The proposed method can be extended to the study of automatic annotation generation of images that can improve the accuracy of image retrieval results.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2009.11a
• /
• pp.273-276
• /
• 2009

Photovoltaic-thermal(PVT) collectors are a combination of photovoltaic modules with solar thermal collectors, forming one device that receives solar radiation and produces electricity and heat simultaneously. Of various PV modules, dye-sensitized solar cell(DSC) is a relatively new type of solar cell technology that can transmit light while they can generate electricity. With this aspect, DSC can be applied into solar thermal collectors. The object of this study is to evaluate the thermal performance of PVT collector with DSC. The thermal performance of the DSC PVT combind collector was measured in outdoor conditions with the solar radiation of over $700W/m^2$. In this study, the PVT collector with the 30% light transmittance of DSC achieved its thermal efficiency of about 36%.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.10
• /
• pp.1-12
• /
• 1993

A multiprocessor system for high-speed processing of hybrid image coding algorithms such as H.261, MPEG, or Digital HDTV is presented in this study. Using a combination of highly parallel 32-bit microprocessor, DCT(Discrete Cosine Transform), and motion detection processor, a new processing module is designed for the implementation of high performance coding system. The sysyem is implemented to allow parallel processing since a single module alone cannot perform hybrid coding algorithms at high speed, and crossbar switch is used to realize various parallel processing architectures by altering interconnections between processing modules within the system.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1053-1056
• /
• 2004

Chunghwa Picture Tubes, LTD. (CPT) has developed a Novel TFT-LCD Driving Techniquel. This new technique is developed in combination with other state-of-the-art image processing solutions such as image compression / decompression, motion detection, and noise reduction. By applying the Novel Driving Technique to the high resolution TFT-LCD, it was found that the response time can be effectively reduced with a lower overall system cost by smaller frame memory requirement, lower EMI by less memory band-width. Likewise, higher display quality can also be achieved in that the unexpected noises generated by over-drive can be eliminated. The Novel TFT-LCD Driving Technique has been successfully implemented to the 30 inch WXGA (1280${\times}$768) resolution TFT LCD commercial TV module. It was found that the quality of moving picture was better improved compared with that of the conventional fast response driving method.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1561-1564
• /
• 2003

Intelligent Wearable Module is intelligent system that arises when a human is part of the feedback loop of a computational process like a certain control system. Applied system is mobile robot. This paper represents the mobile robot control system remote controlled by Intelligent Wearable Module. So far, owing to the development of 802.l1b technologies, lots of remote control methods through internet have been proposed. To control a mobile robot through internet and guide it under unknown environment. The information about the direction and velocity of the mobile robot feedbacks to the PDA and the PDA send new control method produced from the combination of Neuro and Hierarchical Fuzzy Algorithm

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1798-1799
• /
• 2011

In this paper, A new cost-effective and accurate input noise rejection method for High Speed Counter module of PLC (Programmable Logic Controller) is proposed. By using combination of simple additional logic circuit and the Timer Pulse function of general purpose MPU, Cost-effectiveness and improvement of accuracy of filtering function can be achieved. This proposed method is verified by simulation. This proposed method is much useful for simple industrial controller based on simple microprocessor because of simplicity, accuracy and low cost.