• Journal of KIISE:Software and Applications
• /
• v.31 no.2
• /
• pp.189-202
• /
• 2004

In this paper, we propose a new salient region detection method in an image. The algorithm is based on the characteristics of human's bottom-up visual attention. Several features known to influence human visual attention like color, intensity and etc. are extracted from the each regions of an image. These features are then converted to importance values for each region using its local competition function and are combined to produce a saliency map, which represents the saliency at every location in the image by a scalar quantity, and guides the selection of attended locations, based on the spatial distribution of saliency region of the image in relation to its Perceptual importance. Results shown indicate that the calculated Saliency Maps correlate well with human perception of visually important regions.

• Journal of the Institute of Convergence Signal Processing
• /
• v.15 no.3
• /
• pp.85-90
• /
• 2014

In this paper, we propose a virtual violin implementation using the detection of bowing and finger dropping position from the estimated finger tip and finger board information with the 3D image data from a Kinect. Violin finger board pattern and depth information are extracted from the color image and depth image to detect the touch event on the violin finger board and to identify the touched position. Final decision of activated musical alphabet is carried out with the finger drop position and bowing information. Our virtual violin uses PC MIDI to output synthesized violin sound. The experimental results showed that the proposed method can detect finger drop position and bowing detection with high accuracy. Virtual violin can be utilized for the easy and convenient interface for a beginner to learn playing violin with the PC-based learning software.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.2
• /
• pp.145-150
• /
• 2013

A film colored overlay has been used as an assistive device for dyslexics, Recently, several virtual colored overlays which can be used in computer were developed. But mobile virtual overlay has not been developed yet. In this paper, I implemented a mobile overlay application which is based android operating system and displays a colored overlay of screen all the time while user can freely interact with rest of apps in normal manner by using root window and service. A method is presented to determine the source color of a virtual overlays by estimating alpha value of alpha blending algorithm through measurement of the chromaticity and transmissivity of film overlays and I implemented all colors which are presented by using Intuitive Overlays. Test results of the developed virtual overlay show that all colors of the overlays are almost identical to the colors of Intuitive Overlay by using the chroma meter CS-200A.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.21 no.2
• /
• pp.133-138
• /
• 2010

Background and Objectives : High-speed imaging can be useful in studies of linguistic and artistic singing styles, and laryngeal examination of patients with voice disorders, particularly in irregular vocal fold vibrations. In this study, we introduce new laryngeal imaging systems which are commercially available high speed cameras connected with a laryngoscope. Materials and Method : The laryngeal images were captured from three different types of cameras. First, the adapter was made to connect with laryngoscope and Casio EX-F1 to capture the images using $2{\times}150$ Watt Halogen light source (EndoSTROB) at speeds of 1,200 tps (frame per second)($336{\times}96$). Second, Phantom Miro ex4 was used to capture the digital laryngeal images using Xenon Nova light source 175 Watt (STORZ) at speeds of 1,920 fps ($512{\times}384$). Finally, laryngeal images were captured using MotionXtra N-4 with 250 Watt halogen lamp (Olympus CLH-250) light source at speeds of 2,000tps ($384{\times}400$) by connecting with laryngoscope. All images were transformed into the Kymograph using KIPS (Kay's image processing Software) of Kay Pentex Inc. Results: Casio EX-F1 was too small to adjust the focus and screen size was diminished once the images were captured despite of high resolution images. High quality of color images could be obtained with Phantom Miro ex4 whereas good black and white images from Motion Xtra N-4 Despite of some limitations of illumination problems, limited recording time capacity, and time consuming procedures in Phantom Miro ex4 and Motion Xtra N-4, those portable devices provided high resolution images. Conclusion : All those high speed cameras could capture the laryngeal images by connecting with laryngoscope. High resolution images were able to be captured at the fixed position under the good lightness. Accordingly, these techniques could be applicable to observe the vocal fold vibration properties in the clinical practice.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.11
• /
• pp.29-39
• /
• 2019

As mobile robot applications increase in real life, the need of low cost autonomous driving are gradually increasing. We propose a novel vision-based real-time lane detection and tracking system that supports autonomous driving of mobile robots in constrained tracks which are designed considering indoor driving conditions of mobile robots. Considering the processing of lanes with various shapes and the pre-adjustment of operation parameters, the system structure with multi-operation modes are designed. In parameter tuning mode, thresholds of the color filter is dynamically adjusted based on the geometric property of the lane thickness. And in the unstable input mode of curved tracks and the stable input mode of straight tracks, lane feature pixels are adaptively extracted based on the geometric and temporal characteristics of the lanes and the lane model is fitted using the least-squared method. The track centerline is calculated using lane models and the motion model is simplified and tracked by a linear Kalman filter. In the driving experiments, it was confirmed that even in low-performance robot configurations, real-time processing produces the accurate autonomous driving in the constrained track.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.251-256
• /
• 2021

Unlike general cameras, a high-speed camera capable of capturing a large number of frames per second can enable the advancement of some image processing technologies that have been limited so far. This paper proposes a method of removing undesirable noise from an high-speed input color image, and then detecting a human face from the noise-free image. In this paper, noise pixels included in the ultrafast input image are first removed by applying a bidirectional filter. Then, using RetinaFace, a region representing the person's personal information is robustly detected from the image where noise was removed. The experimental results show that the described algorithm removes noise from the input image and then robustly detects a human face using the generated model. The model-based face-detection method presented in this paper is expected to be used as basic technology for many practical application fields related to image processing and pattern recognition, such as indoor and outdoor building monitoring, door opening and closing management, and mobile biometric authentication.

• Fashion & Textile Research Journal
• /
• v.23 no.3
• /
• pp.358-369
• /
• 2021

This study aims to classify the dimensions of the sales information of secondhand clothing goods on the C2C secondhand trading platform and to systematically analyze the components of each dimension. To this end, the NVivo 12.0 qualitative data analysis software was used. The content analysis showed that the sales information of secondhand clothing goods was classified into four dimensions: detailed information of the sale goods, information specific to secondhand clothing goods, seller opinion information, and service information. The components of each dimension were as follows. The detailed information of the sale goods included size, sale price, item, design, brand name, material, color, wearing season, fit, gender, etc. The information specific to secondhand clothing goods included the number of times the item was worn, its purchase history, and product condition. Seller opinion information included product review, sales motivation, notes for the transaction, coordination proposal, and usage proposal. The service information included the transaction mode, exchange·return·refund, and promotion. The frequency analysis showed that the highest frequencies were sale goods(37.47%), information specific to secondhand clothing goods(24.63%), seller opinion information(20.54%), and service information(17.37%). This study will help C2C secondhand trading platform managers or sellers establish clear standards for presenting sales information and developing ideas toward constructing differentiated platform contents.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.43-49
• /
• 2019

The wired and wireless Internet is a useful window to easily acquire various types of media data. On the other hand, the public can easily get the media data including the object to which the personal information is exposed, which is a social problem. In this paper, we propose a method to robustly detect a target object that has exposed personal information using a learning algorithm and effectively block the detected target object area. In the proposed method, only the target object containing the personal information is detected using a neural network-based learning algorithm. Then, a grid-like mosaic is created and overlapped on the target object area detected in the previous step, thereby effectively blocking the object area containing the personal information. Experimental results show that the proposed algorithm robustly detects the object area in which personal information is exposed and effectively blocks the detected area through mosaic processing. The object blocking method presented in this paper is expected to be useful in many applications related to computer vision.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.672-678
• /
• 2020

Ultra-high-speed images that accurately depict the minute movements of objects have become common as low-cost and high-performance cameras that can film at high speeds have emerged. In this paper, the proposed method removes unexpected noise contained in images after input at high speed, and then extracts an area of interest that can represent personal information, such as skin areas, from the image in which noise has been removed. In this paper, noise generated by abnormal electrical signals is removed by applying bilateral filters. A color model created through pre-learning is then used to extract the area of interest that represents the personal information contained within the image. Experimental results show that the introduced algorithms remove noise from high-speed images and then extract the area of interest robustly. The approach presented in this paper is expected to be useful in various applications related to computer vision, such as image preprocessing, noise elimination, tracking and monitoring of target areas, etc.

• The Journal of Advanced Prosthodontics
• /
• v.14 no.3
• /
• pp.150-161
• /
• 2022

PURPOSE. The purpose of the study was to assess the influence of build orientations and density of support structures on the trueness of the 3D printed removable partial denture (RPD) frameworks. MATERIALS AND METHODS. A maxillary Kennedy class III and mandibular class I casts were 3D scanned and used to design and produce two 3D virtual models of RPD frameworks. Using digital light processing (DLP) 3D printing, 47 RPD frameworks were fabricated at 3 different build orientations (100, 135 and 150-degree angles) and 2 support structure densities. All frameworks were scanned and 3D compared to the original virtual RPD models by metrology software to check 3D deviations quantitatively and qualitatively. The accuracy data were statistically analyzed using one-way ANOVA for build orientation comparison and independent sample t-test for structure density comparison at (α = .05). Points study analysis targeting RPD components and representative color maps were also studied. RESULTS. The build orientation of 135-degree angle of the maxillary frameworks showed the lowest deviation at the clasp arms of tooth 26 of the 135-degree angle group. The mandibular frameworks with 150-degree angle build orientation showed the least deviation at the rest on tooth 44 and the arm of the I-bar clasp of tooth 45. No significant difference was seen between different support structure densities. CONCLUSION. Build orientation had an influence on the accuracy of the frameworks, especially at a 135-degree angle of maxillary design and 150-degree of mandibular design. The difference in the support's density structure revealed no considerable effect on the accuracy.