• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.3
• /
• pp.11-19
• /
• 2008

Background subtraction, which separates moving objects in video sequences, is an essential technology for object recognition and tracking. However, background subtraction methods are often confused by shadow regions and this misclassification of shadow regions disturbs further processes to perceive the shapes or exact positions of moving objects. This paper proposes a method for shadow elimination which is based on shadow modeling by color information and Bayesian classification framework. Also, because of dynamic update of modeling parametres, the proposed method is able to correspond adaptively to illumination changes. Experimental results proved that the proposed method can eliminate shadow regions effectively even for circumstances with varying lighting condition.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.2
• /
• pp.122-129
• /
• 2022

In this paper, we propose a method to improve the performance of Transformer-based speech recognizers using data augmentation that locally adjusts the frame rate. First, the start time and length of the part to be augmented in the original voice data are randomly selected. Then, the frame rate of the selected part is changed to a new frame rate by using linear interpolation. Experimental results using the Wall Street Journal and LibriSpeech speech databases showed that the convergence time took longer than the baseline, but the recognition accuracy was improved in most cases. In order to further improve the performance, various parameters such as the length and the speed of the selected parts were optimized. The proposed method was shown to achieve relative performance improvement of 11.8 % and 14.9 % compared with the baseline in the Wall Street Journal and LibriSpeech speech databases, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.93-102
• /
• 2005

This paper proposes an approach to verify signature using autonomous self-organized Neural Network Model , fused with fuzzy membership equation of fuzzy c-means algorithm, based on the features of the signature. To overcome limitations of the functional approach and Parametric approach among the conventional on-line signature recognition approaches, this Paper presents novel autonomous signature classification approach based on clustering features. Thirty-six globa1 features and twelve local features were defined, so that a signature verifying system with FE-SONN that learns them was implemented. It was experimented for total 713 signatures that are composed of 155 original signatures and 180 forged signatures yet 378 original signatures written by oneself. The success rate of this test is more than 97.67$\%$ But, a few forged signatures that could not be detected by human eyes could not be done by the system either.

• Journal of the Korean GEO-environmental Society
• /
• v.9 no.6
• /
• pp.53-60
• /
• 2008

In recent years, finite strain consolidation theories including a mechanical nonlinearity and a reasonable coordinate system have been proposed and used in educations and practical consolidation problems. However, despite their reasonable ability to predict the consolidation behavior, their failure in the field can be attributed to the complexity of estimating and selecting proper parameters for simulating the consolidation phenomenon. In this study, therefore, the application of a piecewise-linear method was proposed to solve such problems including the assumption of the uniqueness in compressibility. Especially, the concept of reference curve was introduced to define the effect of strain rate dependency of clay. The applicability of the methodology is verified by several tests. It was found that the proposed method is applicable in restrictive ranges of study carried out in the laboratory. Finally it is expected that the verification in field consolidation problem has to be carried out through future study.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.46 no.1
• /
• pp.28-33
• /
• 2009

In the research of speech recognition, locating the beginning and end of a speech utterance in a background of noise is of great importance. The conventional methods for speech endpoint detection are based on two simple time-domain measurements-short-time energy, and short-time zero-crossing rate, which couldn't guarantee the precise results if in the low signal-to-noise ratio environments. This paper proposes a novel approach that finds the Lyapunov exponent of time-domain waveform. This proposed method has no use for obtaining the frequency-domain parameters for endpoint detection process, e.g. Mel-Scale Features, which have been introduced in other paper. Accordingly, this algorithm is low complexity and suitable for Digital Isolated Word Recognition System.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.5
• /
• pp.425-430
• /
• 2015

This paper is a study to improve the classification efficiency of rotating objects by using deep neural networks to which a deep learning algorithm was applied. For the classification experiment of rotating objects, COIL-20 is used as data and total 3 types of classifiers are compared and analyzed. 3 types of classifiers used in the study include PCA classifier to derive a feature value while reducing the dimension of data by using Principal Component Analysis and classify by using euclidean distance, MLP classifier of the way of reducing the error energy by using error back-propagation algorithm and finally, deep learning applied DBN classifier of the way of increasing the probability of observing learning data through pre-training and reducing the error energy through fine-tuning. In order to identify the structure-specific error rate of the deep neural networks, the experiment is carried out while changing the number of hidden layers and number of hidden neurons. The classifier using DBN showed the lowest error rate. Its structure of deep neural networks with 2 hidden layers showed a high recognition rate by moving parameters to a location helpful for recognition.

• Journal of Korea Game Society
• /
• v.2 no.1
• /
• pp.62-68
• /
• 2002

This paper presents a method for tessellating trimmed NURBS surface with preserving sharp shape Although several existing approaches need a large number of triangular meshes to represent sharp shape of surface, resulting triangular meshes may not reflect sharp edges properly. In this study, we flit detect the sharp shape of NURBS surface automatically using C1 continuous condition and then use constraint Delaunay triangulation method to present exact sharp shape with the minimum triangular meshes. And we also use approximated developed surface domain as triangulation domain of rimmed NURBS surface. In this way, the shape of triangular elements on the triangular domains is approximately preserved and can avoid distortion when mapped into three-dimensional space. finally, we show examples that demonstrate the effectiveness of the proposed scheme in terms of reducing the number of triangular meshes and preserving sharp shape of surface more exactly.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.5
• /
• pp.23-29
• /
• 2020

The National Institute of Agricultural Sciences of the Rural Developement Administration (NAS, RDA) is conducting various studies on various crops, such as monitoring the cultivation environment and analyzing harvested seeds for high-throughput phenotyping. In this paper, we propose a deep learning-based rice seed segmentation method to analyze the seeds of various crops owned by the NAS. Using Mask-RCNN deep learning model, we perform the rice seed segmentation from manually taken images under specific environment (constant lighting, white background) for analyzing the seed characteristics. For this purpose, we perform the parameter tuning process of the Mask-RCNN model. By the proposed method, the results of the test on seed object detection showed that the accuracy was 82% for rice stem image and 97% for rice grain image, respectively. As a future study, we are planning to researches of more reliable seeds extraction from cluttered seed images by a deep learning-based approach and selection of high-throughput phenotype through precise data analysis such as length, width, and thickness from the detected seed objects.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.311-320
• /
• 2007

This paper presents vision-based 3D facial expression animation technique and system which provide the robust 3D head pose estimation and real-time facial expression control. Many researches of 3D face animation have been done for the facial expression control itself rather than focusing on 3D head motion tracking. However, the head motion tracking is one of critical issues to be solved for developing realistic facial animation. In this research, we developed an integrated animation system that includes 3D head motion tracking and facial expression control at the same time. The proposed system consists of three major phases: face detection, 3D head motion tracking, and facial expression control. For face detection, with the non-parametric HT skin color model and template matching, we can detect the facial region efficiently from video frame. For 3D head motion tracking, we exploit the cylindrical head model that is projected to the initial head motion template. Given an initial reference template of the face image and the corresponding head motion, the cylindrical head model is created and the foil head motion is traced based on the optical flow method. For the facial expression cloning we utilize the feature-based method, The major facial feature points are detected by the geometry of information of the face with template matching and traced by optical flow. Since the locations of varying feature points are composed of head motion and facial expression information, the animation parameters which describe the variation of the facial features are acquired from geometrically transformed frontal head pose image. Finally, the facial expression cloning is done by two fitting process. The control points of the 3D model are varied applying the animation parameters to the face model, and the non-feature points around the control points are changed by use of Radial Basis Function(RBF). From the experiment, we can prove that the developed vision-based animation system can create realistic facial animation with robust head pose estimation and facial variation from input video image.

• Convergence Security Journal
• /
• v.17 no.2
• /
• pp.109-118
• /
• 2017

The study examines whether there is support for undergraduate students of Department of NCOs leadership needs and self-perceived any casualty, the purpose being placed to identify the cause-and effect relationship between student's behavior and these self-appointed leadership needs parameters. To study this end, the men and women college students Military major in Busan district using the convenience of the student sample extraction to extract the 362 students. Setting the model to achieve the object of the study, and then through a structural equation model (SEM) were studies a causal relationship among variables. Result on the basis of the research study model verification method as described above what is derived from this study were as follows. First, self-leadership is confirmed in the career planning of clarity on the impact of career beliefs centered strategies(+) target-oriented strategy(+), and independent self-reliance, check-centered strategies(+), constructive thinking strategies(+), ERA=centric strategy(+), in the natural course flexibility, compensation strategies(+), constructive thinking strategies(+) improve professional skills appeared to affect the check-centered strategies(+), ERA-centered strategies(+). Second, self-leadership is general satisfaction at the impact of major satisfaction natural reward strategies(+), the curriculum meets the natural reward strategies(+) target-oriented strategy(+) recognition satisfy the natural reward strategies(+) target-oriented strategy(+) appeared to affect this. Third, career beliefs Major General satisfaction in the impact on satisfaction Career Planning Clarity(+), an independent self-reliance(+), career flexibility(+)improve professional skills(+), the curriculum satisfies independent self-reliance(+), career flexibility(+) improve professional skills(+), the self-satisfied recognized independent trust(+), career flexibility(+), career planning clarity(+) it appeared to influence this.