• 감성과학
• /
• 제1권1호
• /
• pp.93-103
• /
• 1998

In this paper, we present change of human sensiblity when the 26 healthy female subjects were exposed with visual picture stimulus. We used Intermational Affective Picture System as the visual stimulus. The methods are AutoRegressive(AR) spectrum which is a linear method and Return Map which is a nonlinear mithod. SR spectrum may variability(HRV). The LF/HF of HRV and the variation of Return Map were analyzed from ECG signal of the female subjects. Return Map of RR intervals were analyzed by computiong the variation. When the subjets were stimulated by the pleasant pictures, LF/HF and variation were decreased compared with unpleasant stimulus, We may obtain good parameters for the measurement of the change of human sensibility for the visual picture stimulus.

• Journal of Information Processing Systems
• /
• 제9권4호
• /
• pp.592-601
• /
• 2013

Object segmentation is a challenging task in image processing and computer vision. In this paper, we present a visual attention based segmentation method to segment small sized interesting objects in natural images. Different from the traditional methods, we first search the region of interest by using our novel saliency-based method, which is mainly based on band-pass filtering, to obtain the appropriate frequency. Secondly, we applied the Gaussian Mixture Model (GMM) to locate the object region. By incorporating the visual attention analysis into object segmentation, our proposed approach is able to narrow the search region for object segmentation, so that the accuracy is increased and the computational complexity is reduced. The experimental results indicate that our proposed approach is efficient for object segmentation in natural images, especially for small objects. Our proposed method significantly outperforms traditional GMM based segmentation.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 G
• /
• pp.2312-2314
• /
• 1998

To improve the visual servoing performance, several strategies were proposed in the past such as redundant feature points, using a point with different height and weighted selection of image features. The performance of these visual servoing methods depends on the configuration between the camera and object. And redundant feature points require much computation efforts. This paper proposes the visual servoing m based on the disturbance observer, which compe the upper off-diagonal component of image fe Jacobian to be null. The performance indices su sensitivity for a measure of richness, sensitiv the control to noise, and controllability are sho improved when the image feature Jacobian is giv a block diagonal matrix. Computer simulation carried out for a PUMA560 robot and show results to verify the effectiveness of the pro method.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권3호
• /
• pp.294-303
• /
• 1999

To improve the visual servoing performance, several strategies were proposed in the past such as redundant feature points, using a point with different height and weighted selection of image features. The performance of these visual servoing methods depends on the configuration between the camera and object. And redundant feature points require much computation efforts. This paper proposes the visual servoing method based on the disturbance obsever, which compensates the upper off-diagonal component of image feature jacobian to be the null. The performance indices such as sensitivity for a measure of richness, sensitivity of the control to noise, and comtrollability are shown to be improved when the image feature Jacobian is given as a block diagonal matrix. Computer simulations are carried out for a UUMA560 robot and show some results to verify the effectiveness of the proposed method.

• 대한약침학회지
• /
• 제9권2호
• /
• pp.93-97
• /
• 2006

Objective : This study was to evaluate the effectiveness of Bee Venom acupuncture therapy on external epicondylitis. Methods : We divided chronic arthritis of ankle patient into 2 groups; one group combined bee venom acupuncture therapy and acupuncture therapy, another group was only acupuncture therapy. To estimate the effectiveness of treatment that applied for two groups, we used visual analog scale(VAS). We compared the VAS score of two groups statistically. Results : 1. As a result of evaluation by using visual analog scale(VAS), treatment score at final was marked more higher than score before treatment on each groups. 2. treatment at final, acupuncture and bee venom acupuncture therapy group had significant result on visual analog scale(VAS) compared with acupuncture therapy group. Conclusion : Bee Venom acupuncture therapy can be used with acupuncture therapy for highly effective treatment for external epicondylitis.

• 한국의류학회지
• /
• 제26권8호
• /
• pp.1153-1164
• /
• 2002

The purpose of this study is to find out the creative visual expression in fashion illustration through the previous general theories on creativity. The creative visual expression, in fashion illustration works, can be summarized eight categories as follows. There are 'maximization & minimization'to emphasize the illustrators'emotions and contemporary trends, proposed specially in body expression, 'inversion' seen as the forms of contra-perspective, upside-down, rearrangement of parts, diverted process, etc, 'Unusual uses'to add the effect of caricature, parody, and humor to the fashion illustration works, 'extraordinary connection'seen as the shapes of various combination between animals, plants, stuff, and man, 'concealment & elimination'used frequently in creative visual expression includes a deformed human body, an abstracted human body, an extreme value contrast, simple colors, and dress in silhouette, 'association'seen in various methods; comparing the similar shapes, describing a certain situation or details for analogizing the whole, ‘illusion’ expressed in surreal, mysterious, and fairy depictions and 'substitution'to imitate the composition and colors of masterpieces, copy the parts.

• 대한원격탐사학회지
• /
• 제23권5호
• /
• pp.365-373
• /
• 2007

Car navigation system is a key application in geographic information system and telematics. A recent trend of car navigation system is using real video captured by camera equipped on the vehicle, because video has more representation power about real world than conventional map. In this paper, we suggest a visual car navigation system that visually represents route guidance. It can improve drivers' understanding about real world by capturing real-time video and displaying navigation information overlaid directly on the video. The system integrates real-time data acquisition, conventional route finding and guidance, computer vision, and augmented reality display. We also designed visual navigation controller, which controls other modules and dynamically determines visual representation methods of navigation information according to current location and driving circumstances. We briefly show implementation of the system.

• 로봇학회논문지
• /
• 제18권3호
• /
• pp.260-270
• /
• 2023

We introduce a novel Visual Inertial Odometry (VIO) algorithm designed to improve the performance of thermal-inertial odometry. Thermal infrared image, though advantageous for feature extraction in low-light conditions, typically suffers from a high noise level and significant information loss during the 8-bit conversion. Our algorithm overcomes these limitations by approximating a 14-bit raw pixel histogram into a Gaussian mixture model. The conversion method effectively emphasizes image regions where texture for visual tracking is abundant while reduces unnecessary background information. We incorporate the robust learning-based feature extraction and matching methods, SuperPoint and SuperGlue, and zero velocity detection module to further reduce the uncertainty of visual odometry. Tested across various datasets, the proposed algorithm shows improved performance compared to other state-of-the-art VIO algorithms, paving the way for robust thermal-inertial odometry.

• 한국멀티미디어학회논문지
• /
• 제7권12호
• /
• pp.1671-1679
• /
• 2004

This study has proposed visual-feature extraction methods for each band in wavelet domain with both spatial frequency features and multi resolution features. In addition, it has brought forward similarity measurement method using fuzzy theory and new color feature expression method taking advantage of the frequency of the same color after color quantization for reducing quantization error, a disadvantage of the existing color histogram intersection method. Experiments are performed on a database containing 1,000 color images. The proposed method gives better performance than the conventional method in both objective and subjective performance evaluation.

• Journal of information and communication convergence engineering
• /
• 제21권2호
• /
• pp.152-158
• /
• 2023

In recent years, as computer-generated imagery has been applied to more industries, realistic facial animation is one of the important research topics. The current solution for realistic facial animation is to create realistic rendered 3D characters, but the 3D characters created by traditional methods are always different from the actual characters and require high cost in terms of staff and time. Deepfake technology can achieve the effect of realistic faces and replicate facial animation. The facial details and animations are automatically done by the computer after the AI model is trained, and the AI model can be reused, thus reducing the human and time costs of realistic face animation. In addition, this study summarizes the way human face information is captured and proposes a new workflow for video to image conversion and demonstrates that the new work scheme can obtain higher quality images and exchange effects by evaluating the quality of No Reference Image Quality Assessment.