• Transactions on Electrical and Electronic Materials
• /
• v.13 no.1
• /
• pp.10-15
• /
• 2012

In conventional, skin detection methods using for skin color definitions is based on prior knowledge. By experimentation, the threshold value for dividing the background from the skin region is determined subjectively. A drawback of such techniques is that their performance is dependent on a threshold value which is estimated from repeated experiments. To overcome this, the present paper introduces a skin region detection method. This method uses a histogram approximation based on the mean shift algorithm. This proposed method applies the mean shift procedure to a histogram of a skin map of the input image. It is generated by comparing with the standard skin colors in the $C_bC_r$ color space. It divides the background from the skin region by selecting the maximum value according to the brightness level. As the histogram has the form of a discontinuous function. It is accumulated according to the brightness values of the pixels. It is then, approximated by a Gaussian mixture model (GMM) using the Bezier curve technique. Thus, the proposed method detects the skin region using the mean shift procedure to determine a maximum value. Rather than using a manually selected threshold value, as in existing techniques this becomes the dividing point. Experiments confirm that the new procedure effectively detects the skin region.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1671-1686
• /
• 2022

Face manipulation tools represented by Deepfake have threatened the security of people's biological identity information. Particularly, manipulation tools with deep learning technology have brought great challenges to Deepfake detection. There are many solutions for Deepfake detection based on traditional machine learning and advanced deep learning. However, those solutions of detectors almost have problems of poor performance when evaluated on different quality datasets. In this paper, for the sake of making high-quality Deepfake datasets, we provide a preprocessing method based on the image pixel matrix feature to eliminate similar images and the residual channel attention network (RCAN) to resize the scale of images. Significantly, we also describe a Deepfake detector named Cascaded-Hop which is based on the PixelHop++ system and the successive subspace learning (SSL) model. By feeding the preprocessed datasets, Cascaded-Hop achieves a good classification result on different manipulation types and multiple quality datasets. According to the experiment on FaceForensics++ and Celeb-DF, the AUC (area under curve) results of our proposed methods are comparable to the state-of-the-art models.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.5
• /
• pp.72-82
• /
• 1998

Power transformer protective relay should block the tripping during magnetizing imrush and rapidly operate the tripping during internal faults. But traditional approaches maloperate in the case of magnetizing inrush with low second harmonic component and internal faults with high second harmounic component. To enhance the fault detection sensitivities of conventional technuques, flux-differential current derivative curve by fuzzy theory approaches is used. This paper deals with fuzzy logic based protective relaying for power transformer. The proposed fuzzy based relaying algorithm consisits of flux-differential current derivative curve, harmonics restraint, and precentage differential characteristic curv. The proposed relaying was tested with relaying signals obtained from Salford EMTP simulation package and showed a fast and accurate trip operation.

• Journal of information and communication convergence engineering
• /
• v.14 no.4
• /
• pp.233-239
• /
• 2016

A remote control system (RCS) can monitor a user's confidential information by using the broadcast receivers in Android OS. However, the current RCS detection methods are based only on a virus vaccine. Therefore, if the user's smartphone is infected by a brand new RCS, these methods cannot detect this new RCS immediately. In this paper, we present a secure message transmission medium. This medium is completely isolated from networks and can communicate securely through a QR code channel by using symmetric key cryptography such as the AES block cipher and public key cryptography such as elliptic curve cryptography for providing security. Therefore, the RCS cannot detect any confidential information. This approach is completely immune to any RCS attacks. Furthermore, we present a secure QR code-based key exchange protocol by using the elliptic curve Diffie-Hellman method and message transmission protocols; the proposed protocol has high usability and is very secure.

• KIEE International Transactions on Power Engineering
• /
• v.2A no.4
• /
• pp.153-159
• /
• 2002

Power transformer protective relay should block the tripping during magnetizing inrush and rapidly operate the tripping during internal faults. Recently, the frequency environment of power system has been made more complicated and the quantity of 2nd frequency component in inrush state has been decreased because of the improvement of core steel. And then, traditional approaches will likely be maloperate in the case of magnetizing inrush with low second harmonic component and internal faults with high second harmonic component. This paper proposes a new relaying algorithm to enhance the fault detection sensitivities of conventional techniques by using a fuzzy logic approach. The proposed fuzzy based relaying algorithm consists of flux-differential current derivative curve, harmonic restraint, and percentage differential characteristic curve. The proposed relaying was tested with relaying signals obtained from EMTP simulation package and showed a fast and accurate trip operation.

• Korean Journal of Digital Imaging in Medicine
• /
• v.13 no.1
• /
• pp.7-11
• /
• 2011

As applications of radiation grow wider from use in the early detection of lesions and preventive diagnosis purposes to the treatment of diseases, the possibilities for patients and working professionals to be exposed to radiation are becoming greater than ever. This can not only directly bring about an increase in patient's individual radiation exposure, but also brings about an increase in the annual radiation dose of working professionals. Therefore, research and countermeasures to reduce radiation dosage are required. In this study, space dosimetry has been divided into two separate measuments with an understanding of the increasing number of angiography procedures: front perspective and side perspective. According to the results of the isodose curve, a way to minimize radiation exposure in working professionals has been suggested. This was made possible by workers through awareness of suitable working positions.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.939-944
• /
• 2007

Edge is a significant element to represent boundary information between objects in images. There are various edge detection methods, which are based on differential operation, such as Sobel, Prewitt, Roberts, Canny, Laplacian, and etc. However the conventional methods have drawbacks as follow : (i) insensitivity to edges with gentle curve intensity, (ii) detection of double edges for edges with one pixel width. For the detection of edges, not only development of the effective operators but also that of appropriate thresholding methods are necessary. But it is very complicate problem to find an appropriate threshold. In this paper, we propose an edge detection method based on the region separateness between objects to overcome the drawbacks of the conventional methods, and a thresholding method for the proposed edge detection method. We show the effectiveness of the proposed method through experimental results obtained by applying the proposed and the conventional methods to well-known test images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.9
• /
• pp.2105-2112
• /
• 2010

The noise component of electrocardiogram is not distributed in a certain frequency band. It is expressed in various types of signals by rater's physical and environmental conditions. Particularly, since the baseline wander is occurred by the mixture of the original signal and 0 ~ 2 [Hz] range of the frequency components according to muscle constraction of part attaching to an electrode and respiration rythm, it makes the ECG signal analysis difficult. Several methods have been proposed to eliminate the wandering effectually. However, they have some problems. In some methods, the high processing time is required due to the computational complexity, while in other cases ECG signal morphology can be distorted. This paper suggests a simple and effective algorithm that eliminates baseline wander with low computational complexity and without distorting signal morphology. First, the algorithm detects and segments a baseline wandering interval using slope analysis and curve point detection, second, approximates the wandering in the interval as a sinusoid, and then subtracts the sinusoid from signal. Finally, ecg signals without baseline wander are obtained. In order to evaluate the performance of the algorithm, several ECG signals with baseline wandering in MIT/BIH ECG database 101, 111, 113, 234 record were chosen and applied to the algorithm. It is found that the algorithm removes baseline wanders effectively without significant morphological distortion.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.21-29
• /
• 2011

At existing skin detection methods using skin color information defined based on the prior knowldege, threshold value to be used at the stage of dividing the backround and the skin region was decided on a subjective point of view through experiments. Also, threshold value was selected in a passive manner according to their background and illumination environments in these existing methods. These existing methods displayed a drawback in that their performance was fully influenced by the threshold value estimated through repetitive experiments. To overcome the drawback of existing methods, this paper propose a skin region detection method using a histogram approximation based on the mean shift algorithm. The proposed method is to divide the background region and the skin region by using the mean shift method at the histogram of the skin-map of the input image generated by the comparison of the similarity with the standard skin color at the CbCr color space and actively finding the maximum value converged by brightness level. Since the histogram has a form of discontinuous function accumulated according to the brightness value of the pixel, it gets approximated as a Gaussian Mixture Model (GMM) using the Bezier Curve method. Thus, the proposed method detects the skin region by using the mean shift method and actively finding the maximum value which eventually becomes the dividing point, not by using the manually selected threshold value unlike other existing methods. This method detects the skin region high performance effectively through experiments.

• Journal of Veterinary Clinics
• /
• v.29 no.1
• /
• pp.18-22
• /
• 2012

This study was performed to evaluate the sensitivity of conventional film-screen radiography (CFSR) and direct digital radiography (DDR) for detection of various amounts of free peritoneal fluid. Ten adult male healthy beagles were used in this study. Radiographic examinations were performed in the right lateral and ventrodorsal positions. Fluid was injected in increments of 2.0 ml/kg of body weight up to 20.0 ml/kg of body weight. The images of CFSR and DDR were evaluated by two veterinary radiologists for evidence of abdominal fluid without knowledge of injected fluid volume. Data were evaluated by using the receiver operation curve (ROC) analysis and the area under the curve (AUC). There was no significant difference in detection of peritoneal fluid between DDR and CFSR in the ROC analysis. The accuracy of CFSR (0.805) was relatively higher than that of DDR (0.733), based on the ROC analysis and AUC. AUC of CFSR was higher in most injection doses. These results suggest that CFSR is more accurate than DDR for the detecting peritoneal fluid. Therefore, for situation in which digital radiographs are equivocal or small amount of fluid is suspected, other imaging modalities, such as ultrasonography would be helpful for determining the presence of fluids.