• Journal of KIISE:Databases
• /
• v.34 no.2
• /
• pp.99-108
• /
• 2007

In this paper, we design and implement the Film Defect Inspection System (FDIS) that detects film defects and determines their types which can be used for producing polarized films of TFT-LCD. The proposed system is designed to detect film defects from polarized film images using image segmentation techniques and to determine defect types through the image analysis of detected defects. To determine defect types, we extract features such as shape and texture of defects, and compare those features with corresponding features of referential images stored in a template database. Experimental results using FDIS show that the proposed system detects all defects of test images effectively (Precision 1.0, Recall 1.0) and efficiently (within 0.64 second in average), and achieves the considerably high correctness in determining defect types (Precision 0.96 and Recall 0.95 in average). In addition, our system shows the high robustness for rotated transformation of images, achieving Precision 0.95 and Recall 0.89 in average.

• The KIPS Transactions:PartA
• /
• v.13A no.5 s.102
• /
• pp.429-434
• /
• 2006

A CCTV system reduces some number of cameras if we use convex-mirror. In this case, convex-mirror Image distorted, we need transformation to flat images. In the center of mirror images, a transformed image has no distortion, but at near boundary image has plentiful distortion. This distortion is caused by occlusion of angled ray and diffraction. We know that the linear filtering approach cannot separate noise from signal where their Fourier spectra overlap. But using a non-linear discretization method, we shall reduce blurred noise. In this paper, we introduce the backward solution of nonlinear wave equation for reducing blurred noise and biased expansion of equilibrium contour. We propose, after applying the introduced method, and calculate with discretization method. To analysis the experimental result, we investigate to PSNR and get about 4dB better than current method.

• Cartoon and Animation Studies
• /
• s.48
• /
• pp.199-215
• /
• 2017

Recently, a drone is used for the general purpose application although the drone was builtfor the military purpose. A drone is actively used for the creation of contents, and an image acquisition. In this paper, we develop a 3D library module platform using 3D mesh model data, which is generated by a drone image and its point cloud. First, a lot of 2D image data are taken by a drone, and a point cloud data is generated from 2D drone images. A 3D mesh data is acquired from point cloud data. Then, we develop a service library platform using a transformed 3D data for multi-purpose uses. Our platform with 3D data can minimize the cost and time of contents creation for special effects during the production of a movie, drama, or documentary. Our platform can contribute the creation of experts for the digital contents production in the field of a realistic media, a special image, and exhibitions.

• Journal of the Korean Society of Radiology
• /
• v.10 no.8
• /
• pp.571-576
• /
• 2016

3D printing has recently been used in various fields. Among various applications, 3D face data must be generated for 3D face printing. A laser scanner is used to acquire 3D face data, but there is a restriction that a person should not move during scanning. In this paper, we propose a 3D face modeling method based on a single image and a face transformation system to use the generated 3D face for virtual cosmetic surgery. We have defined facial feature points from the 3D face database for 3D face data generation. After extracting feature points from a single face image, 3D face of the input face image is generated corresponding to the 3D face feature points defined from the 3D face database. After 3D face modeling, 3D face modification part is applied for use such as virtual cosmetic surgery.

• Journal of Internet Computing and Services
• /
• v.12 no.2
• /
• pp.37-46
• /
• 2011

The importance of data service with mobile is becoming more and more significant with the development of wireless network. However, due to the several type of mobile devices and contents, there is a problem that mobile contents should be edited according to the features of the mobile devices and the service providers. Fortunately, there is some solutions that convert mobile contents automatically according to mobile operator. Nevertheless, it has some issues that the response time of content service is delayed when converting mobile contents in real-time. In this paper, we propose an image cache replacement algorithm for minizing the volume of the real-time image transformation. Also, using both of the pre-conversion method and the real-time conversion method to improve storage space and response time.

• Journal of Digital Contents Society
• /
• v.12 no.1
• /
• pp.49-55
• /
• 2011

Because of causing the geometrical transformation of the magnetic field, the patient implementing the fixation using the nonmagnetic metal screw causes the magnetic susceptibility artifact at an image. Thus, in this research, the distortion measure of the image according to the frequency oblique direction conversion tried to be compared in the magnetic susceptibility artifact occurence. First, the itself phantom inserting the nonmagnetic metal screw of the titanium component was made and the region of interest was set up and the frequency oblique direction the anterior - back side was converted to the right-to-left direction in the axial image and a right-to-left was converted to the upper side - bottom side in the coronal plane and the upper - bottom side was converted to the anterior - back side in the sagittal plane and the distortion measure of the region of interest was compared, it observed. In a result, when converting the frequency oblique direction, the distortion difference of the region of interest could be confirmed and it is considered to enhance the diagnostics efficiency changing the oblique direction appropriately.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.2
• /
• pp.92-99
• /
• 2009

This paper established the range of the wavelength of traffic lights to detection the color of traffic lights and the color component segmentation with the range of the wavelength. Development of traffic light automatic discrimination system is consists of the color detection and the traffic lights recognition. In this thesis, it established the range of the wavelength of traffic lights to detection the color of traffic lights and the color segmentation with the range of the wavelength. By the segmentation, the traffic light colors(red, orange and green) can be detected and the background is changed into gray image. Next, we proposed the algorithm which can detect the area of traffic lights in the various surroundings with the wavelet transformation algorithm. Also, we proposed traffic lights recognition algorithm using between the edge operator and the Hausdorff distance algorithm based on CBIR(Content-based Image retrieval). Therefore, the proposed algorithm is more superior to the conventional algorithm by experimenting with the illumination including the traffic lights and the backgrounds with various images.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2843-2845
• /
• 2000

A lane detection based on a road model or feature all need correct acquirement of information on the lane in a image, It is inefficient to implement a lane detection algorithm through the full range of a image when being applied to a real road in real time because of the calculating time. This paper defines two searching range of detecting lane in a road, First is searching mode that is searching the lane without any prior information of a road, Second is recognition mode, which is able to reduce the size and change the position of a searching range by predicting the position of a lane through the acquired information in a previous frame. It is allow to extract accurately and efficiently the edge candidates points of a lane as not conducting an unnecessary searching. By means of removing the perspective effect of the edge candidate points which are acquired by using the inverse perspective transformation, we transform the edge candidate information in the Image Coordinate System(ICS) into the plane-view image in the World Coordinate System(WCS). We define linear approximation filter and remove the fault edge candidate points by using it This paper aims to approximate more correctly the lane of an actual road by applying the least-mean square method with the fault-removed edge information for curve fitting.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1280-1287
• /
• 2020

This paper proposes a vision-based food recognition method for automated production of custom cakes. A small camera module mounted on a food art printer recognizes objects' shape and estimates their center points through image processing. Through the perspective transformation, the top-view image is obtained from the original image taken at an oblique position. The line and circular hough transformations are applied to recognize square and circular shapes respectively. In addition, the center of gravity of each figure are accurately detected in units of pixels. The test results show that the shape recognition rate is more than 98.75% under 180 ~ 250 lux of light and the positioning error rate is less than 0.87% under 50 ~ 120 lux. These values sufficiently meet the needs of the corresponding market. In addition, the processing delay is also less than 0.5 seconds per frame, so the proposed algorithm is suitable for commercial purpose.

• Journal of IKEEE
• /
• v.26 no.2
• /
• pp.176-185
• /
• 2022

Data augmentation is general approach to solve overfitting of machine learning models by applying various data transformations and distortions to dataset. However, when data augmentation is applied in GAN-based model, which is deep learning image generation model, data transformation and distortion are reflected in the generated image, then the generated image quality decrease. To prevent this problem called augmentation leak, we propose a scheme that can prevent augmentation leak regardless of the type and number of augmentations. Specifically, we analyze the conditions of augmentation leak occurrence by type and implement auxiliary augmentation task classifier that can prevent augmentation leak. Through experiments, we show that the proposed technique prevents augmentation leak in the GAN model, and as a result improves the quality of the generated image. We also demonstrate the superiority of the proposed scheme through ablation study and comparison with other representative augmentation leak prevention technique.