• The KIPS Transactions:PartB
• /
• v.16B no.4
• /
• pp.299-308
• /
• 2009

AAM(Active Appearance Model) is an algorithm to extract face feature points with statistical models of shape and texture information based on PCA(Principal Component Analysis). This method is widely used for face recognition, face modeling and expression recognition. However, the detection performance of AAM algorithm is sensitive to initial value and the AAM method has the problem that detection error is increased when an input image is quite different from training data. Especially, the algorithm shows high accuracy in case of closed lips but the detection error is increased in case of opened lips and deformed lips according to the facial expression of user. To solve these problems, we propose the improved AAM algorithm using lip feature points which is extracted based on a new lip detection algorithm. In this paper, we select a searching region based on the face feature points which are detected by AAM algorithm. And lip corner points are extracted by using Canny edge detection and histogram projection method in the selected searching region. Then, lip region is accurately detected by combining color and edge information of lip in the searching region which is adjusted based on the position of the detected lip corners. Based on that, the accuracy and processing speed of lip detection are improved. Experimental results showed that the RMS(Root Mean Square) error of the proposed method was reduced as much as 4.21 pixels compared to that only using AAM algorithm.

• Journal of Broadcast Engineering
• /
• v.9 no.1
• /
• pp.2-7
• /
• 2004

In this paper, we proposed the content-based music information retrieval technique using some MPEG-7 low-level descriptors. Especially, pitch information and timbral features can be applied in music genre classification, music retrieval, or QBH(Query By Humming) because these can be modeling the stochasticpattern or timbral information of music signal. In this work, we restricted the music domain as O.S.T of movie or soap opera to apply broadcasting system. That is, the user can retrievalthe information of the unknown music using only an audio clip with a few seconds extracted from video content when background music sound greeted user's ear. We proposed the audio feature set organized by MPEG-7 descriptors and distance function by vector distance or ratio computation. Thus, we observed that the feature set organized by pitch information is superior to timbral spectral feature set and IFCR(Intra-Feature Component Ratio) is better than ED(Euclidean Distance) as a vector distance function. To evaluate music recognition, k-NN is used as a classifier

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.8
• /
• pp.1537-1545
• /
• 2016

In real time video sequence, object segmentation and tracking method are actively applied in various application tasks, such as surveillance system, mobile robots, augmented reality. This paper propose a robust object tracking method. The background models are constructed by learning the initial part of each video sequences. After that, the moving objects are detected via object segmentation by using background subtraction method. The region of detected objects are continuously tracked by using the HSV color histogram with particle filter. The proposed segmentation method is superior to average background model in term of moving object detection. In addition, the proposed tracking method provide a continuous tracking result even in the case that multiple objects are existed with similar color, and severe occlusion are occurred with multiple objects. The experiment results provided with 85.9 % of average object overlapping rate and 96.3% of average object tracking rate using two video sequences.

• The KIPS Transactions:PartB
• /
• v.13B no.7 s.110
• /
• pp.653-662
• /
• 2006

In ubiquitous computing that is to build computing environments to provide proper services according to user's context, human being's emotion recognition based on facial expression is used as essential means of HCI in order to make man-machine interaction more efficient and to do user's context-awareness. This paper addresses a problem of rigidly basic emotion recognition in context-sensitive facial expressions through a new Bayesian classifier. The task for emotion recognition of facial expressions consists of two steps, where the extraction step of facial feature is based on a color-histogram method and the classification step employs a new Bayesian teaming algorithm in performing efficient training and test. New context-sensitive Bayesian learning algorithm of EADF(Extended Assumed-Density Filtering) is proposed to recognize more exact emotions as it utilizes different classifier complexities for different contexts. Experimental results show an expression classification accuracy of over 91% on the test database and achieve the error rate of 10.6% by modeling facial expression as hidden context.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.19-26
• /
• 2005

Image interpolation in the wavelet domain usually takes advantage of the probabilistic models for the intrascale statistics and the interscale dependency. In this paper, we adopt the linear model for the absolute values of wavelet coefficients of interpolated image across scale to estimate the variances of extrapolated bands. The proposed algorithm uses randomly generated wavelet coefficients based on the estimated parameters for probabilistic model. Random number generation according to the estimated probabilistic model may induce the 'salt and pepper' noise in subbands. We reduce the noise power by Wiener filtering. We observe that the proposed method generates the histogram of the subband coefficients similar to the that of original image. Experimental results show that our method outperforms the previous wavelet-domain interpolation method as well as the conventional bicubic method.

• Korea Trade Review
• /
• v.48 no.1
• /
• pp.83-126
• /
• 2023

The revenue histogram of venture businesses is shifting from bell-shaped normal distribution to power-law distribution, which implies that the fitness landscape of the venture businesses ecosystem is changing to be more rugged terrain. We argue that the firm should adopt both exploitation (fast follower) and exploration (or first mover) strategies not to get stuck in local maxima in the rugged fitness landscape from the complex system perspective. By designing and performing agent-based modeling simulation experiments which consist of three types of agents (new technologies, entrepreneurs, and consumers), we demonstrated that the ambidexterity strategy showed the highest performance score in three of four different environment except 'Fast Widening' case where the exploitation strategy showed the highest performance score under low technology appropriation and fast disruptive technology development speed. By investigating the financial and other statistics of 617 top venture businesses who have earned 100B won or higher annual revenue, we concluded that 82% and 9% of firms are bent on the exploitation and exploration strategy.

• Journal of KIISE:Software and Applications
• /
• v.28 no.7
• /
• pp.501-510
• /
• 2001

Generally, it is essential to estimate exact disparity for the 3D modeling from stereo images. Because existing methods calculate disparities from a whole image, they require too much cimputational time and bring about the mismatching problem. In this article, using the characteristic that the disparity vectors in stereo images are distributed not equally in a whole image but only exist about the background and obhect, we do a wavelet transformation on stereo images and estimate coarse disparity fields from the reduced lowpass field using area-based method at first-step. From these coarse disparity vectors, we generate disparity histogram and then separate object from background area using it. Afterwards, we restore only object area to the original image and estimate dense and accurate disparity by our two-step pixel-based method which does not use pixel brightness but use second gradient. We also extract feature points from the separated object area and estimate depth information by applying disparity vectors and camera parameters. Finally, we generate 3D model using both feature points and their z coordinates. By using our proposed, we can considerably reduce the computation time and estimate the precise disparity through the additional pixel-based method using LOG filter. Furthermore, our proposed foreground/background method can solve the mismatching problem of existing Delaunay triangulation and generate accurate 3D model.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.6 s.312
• /
• pp.65-84
• /
• 2006

In this paper, we present an improved image formation model and propose a color image enhancement based on the model. In the presented image formation model, an input image is represented as a product of global illumination, local illumination, and reflectance. In the proposed color image enhancement, an input RGB color image is converted into an HSV color image. Under the assumption of white-light illumination, the H and S component images are remained as they are and the V component image only is enhanced based on the image formation model. The global illumination is estimated by applying a linear LPF with wide support region to the input V component image and the local illumination by applying a JND (just noticeable difference)-based nonlinear LPF with narrow support region to the processed image, where the estimated global illumination is eliminated from the input V component image. The reflectance is estimated by dividing the input V component image by the estimated global and local illuminations. After performing the gamma correction on the three estimated components, the output V component image is obtained from their product. Histogram modeling is next executed such that the final output V component image is obtained. Finally an output RGB color image is obtained from the H and S component images of the input color image and the final output V component image. Experimental results for the test image DB built with color images downloaded from NASA homepage and MPEG-7 CCD color images show that the proposed method gives output color images of very well-increased global and local contrast without halo effect and color shift.

• Progress in Medical Physics
• /
• v.25 no.3
• /
• pp.128-138
• /
• 2014

In gated radiation therapy (gRT), due to residual motion, beam delivery is intended to irradiate not only the true extent of disease, but also neighboring normal tissues. It is desired that the delivery covers the true extent (i.e. clinical target volume or CTV) as a minimum, although target moves under dose delivery. The objectives of our study are to validate if the intended dose is surely delivered to the true target in gRT and to quantitatively understand the trend of dose delivery on it and neighboring normal tissues when gating window (GW), motion amplitude (MA), and CTV size changes. To fulfill the objectives, experimental and computational studies have been designed and performed. A custom-made phantom with rectangle- and pyramid-shaped targets (CTVs) on a moving platform was scanned for four-dimensional imaging. Various GWs were selected and image integration was performed to generate targets (internal target volume or ITV) for planning that included the CTVs and internal margins (IM). The planning was done conventionally for the rectangle target and IMRT optimization was done for the pyramid target. Dose evaluation was then performed on a diode array aligned perpendicularly to the gated beams through measurements and computational modeling of dose delivery under motion. This study has quantitatively demonstrated and analytically interpreted the impact of residual motion including penumbral broadening for both targets, perturbed but secured dose coverage on the CTV, and significant doses delivered in the neighboring normal tissues. Dose volume histogram analyses also demonstrated and interpreted the trend of dose coverage: for ITV, it increased as GW or MA decreased or CTV size increased; for IM, it increased as GW or MA decreased; for the neighboring normal tissue, opposite trend to that of IM was observed. This study has provided a clear understanding on the impact of the residual motion and proved that if breathing is reproducible gRT is secure despite discontinuous delivery and target motion. The procedures and computational model can be used for commissioning, routine quality assurance, and patient-specific validation of gRT. More work needs to be done for patient-specific dose reconstruction on CT images.