• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.881-886
• /
• 2012

The paper is facial expression recognition based on the inclined face geometrical information. In facial expression recognition, mouth has a key role in expressing emotions, in this paper the features is mainly based on the shapes of mouth, followed by eyes and eyebrows. This paper makes its efforts to disperse every feature values via the weighting function and proposes method of expression classification with excellent classification effects; the final recognition model has been constructed.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.2
• /
• pp.178-183
• /
• 2008

Human motion analysis is researched as a new method for human-robot interaction (HRI) because it concerns with the key techniques of HRI such as motion tracking and pose recognition. To analysis human motion, extracting features of human body from sequential images plays an important role. After finding the silhouette of human body from the sequential images obtained by CCD color camera, the skeleton model is frequently used in order to represent the human motion. In this paper, using the silhouette of human body, we propose the feature extraction method based on hybrid skeleton for detecting human motion. Finally, we show the effectiveness and feasibility of the proposed method through some experiments.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.2
• /
• pp.138-144
• /
• 2010

This paper presents the experimental analysis of a F-Hessian SIFT-Based Railroad Level-Crossing Safety Vision System. Region of surveillance, region of interests, data matching based on extracting feature points has been examined under the laboratory condition by the model rig on a small scale. Real-time system were observed by using SIFT based on F-Hessian feature tracking method and other common algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.9
• /
• pp.21-27
• /
• 2019

In this paper, we propose a deep auto-encoder-based pipe leak detection (PLD) technique from time-series acoustic data collected by microphone sensor nodes. The key idea of the proposed technique is to learn representative features of the leak-free state using leak-free time-series acoustic data and the deep auto-encoder. The proposed technique can be used to create a PLD model that detects leaks in the pipeline in an unsupervised learning manner. This means that we only use leak-free data without labeling while training the deep auto-encoder. In addition, when compared to the previous supervised learning-based PLD method that uses image features, this technique does not require complex preprocessing of time-series acoustic data owing to the unsupervised feature extraction scheme. The experimental results show that the proposed PLD method using the deep auto-encoder can provide reliable PLD accuracy even considering unsupervised learning-based feature extraction.

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3359-3366
• /
• 2023

In this study, a spiking cortical model (SCM) based n-g discrimination method is proposed. The SCM-based algorithm is compared with three other methods, namely: (i) the pulse-coupled neural network (PCNN), (ii) the charge comparison, and (iii) the zero-crossing. The objective evaluation criteria used for the comparison are the FoM-value and the time consumption of discrimination. Experimental results demonstrated that our proposed method outperforms the other methods significantly with the highest FoM-value. Specifically, the proposed method exhibits a 34.81% improvement compared with the PCNN, a 50.29% improvement compared with the charge comparison, and a 110.02% improvement compared with the zero-crossing. Additionally, the proposed method features the second-fastest discrimination time, where it is 75.67% faster than the PCNN, 70.65% faster than the charge comparison and 38.4% slower than the zero-crossing. Our study also discusses the role and change pattern of each parameter of the SCM to guide the selection process. It concludes that the SCM's outstanding ability to recognize the dynamic information in the pulse signal, improved accuracy when compared to the PCNN, and better computational complexity enables the SCM to exhibit excellent n-γ discrimination performance while consuming less time.

• The Journal of Korea Robotics Society
• /
• v.4 no.1
• /
• pp.17-24
• /
• 2009

This work deals with an intuitive method for a planar biped to walk, which is named Relative Trajectory Control (RTC) method. A key feature of the proposed RTC method is that feet of the robot are controlled to track a given trajectory, which is specially designed relative to the base body of the robot. The trajectory of feet is presumed from analysis of the walking motion of a human being. A simple method to maintain a stable posture while the robot is walking is also introduced in RTC method. In this work, the biped is modeled as a free-floating robot, of which dynamic model is obtained in the Cartesian space. Using the obtained dynamic model, the robot is controlled by a model-based feedback control scheme. The author shows a preliminary experimental result to verify that the biped robot with RTC method can walk on the even or uneven surfaces.

• Journal of KIISE:Software and Applications
• /
• v.36 no.12
• /
• pp.996-1008
• /
• 2009

This paper proposes a novel approach for the model-based pose matching of a human body using Active Shape Models. To improve the processing time of model creation and registration, we use a skeleton-type model instead of the conventional silhouette-based models. The skeleton model defines feature information that is used to match the human pose. Images used to make the model are for 600 human bodies, and the model has 17 landmarks which indicate the body junction and key features of a human pose. When applying primary Active Shape Models to the skeleton-type model in the matching process, a problem may occur in the proximal joints of the arm and leg due to the color variations on a human body and the insufficient information for the fore-rear directions of profile normals. This problem is solved by using the background subtraction information of a body region in the input image and adding a 4-directions feature of the profile normal in the proximal parts of the arm and leg. In the matching process, the maximum iteration is less than 30 times. As a result, the execution time is quite fast, and was observed to be less than 0.03 sec in an experiment.

• Current Optics and Photonics
• /
• v.1 no.6
• /
• pp.587-597
• /
• 2017

The extraction of the valid measurement region from the interference fringe pattern is a significant step when measuring gear tooth flank form deviation with grazing incidence interferometry, which will affect the measurement accuracy. In order to overcome the drawback of the conventionally used method in which the object image pattern must be captured, an improved segmentation approach is proposed in this paper. The interference fringe patterns feature, which is smoothed by the nonlinear diffusion, would be extracted by the structure tensor first. And then they are incorporated into the vector-valued Chan-Vese model to extract the valid measurement region. This method is verified in a variety of interference fringe patterns, and the segmentation results show its feasibility and accuracy.

• 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 Korea Society of Computer and Information
• /
• v.13 no.7
• /
• pp.37-49
• /
• 2008

Services are reusable units in business level. Ubiquitous computing provides computing services anytime and anywhere. The combination of both is becoming an important paradigm of computing environment. Fundamentals of services require flexibility and interoperability, and key elements of ubiquitous modeling require interoperability and context-awareness. There are two kinds of methods to identify services. The top-down approach is based on business process, and the bottom-up approach is based on components. The first approach depends on experts' intuitions, while the second approach suffers the incapability of expressing non-functional expression through components. Although a feature-based approach is capable of expressing non-functional expression and identifying services in ubiquitous environment, the research on this issue is not adequately addressed by far. To promote this research, this paper proposes a feature-based method to identify services in ubiquitous computing. The method extracts initial-candidate-services from a feature model. Then, the ultimate services are identified through optimizing and analyzing the candidate-services. The proposed method is expected to enhance the service reusability by effectively analyzing ubiquitous domain based on feature, and varying reusable service units.