• Journal of Institute of Convergence Technology
• /
• v.6 no.1
• /
• pp.23-26
• /
• 2016

DC motor shafts have several defects such as double cut, deep scratch on surface, and defects in diameter and length. The deep scratches are due to collision among the other shafts. So the scratches are long and thin but their orientations are random. If the smallest enclosing box, i.e. oriented bounding box for a detective point group is found, then the size of the corresponding defect can be modeled as its diagonal length. This paper proposes an suface inspection algorithm for the DC motor shaft using the oriented bounding box. To evaluate the proposed algorithm, a test bed is made with a line scan CCD camera (4096 pixels/line) and two rollers mechanism to rotate the shaft. The experimental result on a pre-processed image with contrast streching algorithm, shows that the proposed algorithm sucessfully finds 150 surface defects and its computation time (0.291 msec) is enough fast for the requirement (4 seconds).

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.8
• /
• pp.3654-3659
• /
• 2012

Active contour model or snake is widely used for segmentation method in the area of the image processing and computer vision. The main problem in the active contour model is that results are very dependent to the closet points of the numbers and the location in initial step. Especially, in case of balloon-like active contour model, the small region which consist of intial closet points are expanded until the edge is reached. It is a serious problem because the considered region are huge with limited points. To solve this problem, in this paper, we propose the method that the number of closet points could be change based on the distance between points.

• Journal of Korea Multimedia Society
• /
• v.14 no.5
• /
• pp.632-641
• /
• 2011

This paper presents a position error recognition system when the wafer is mounted in cleaning equipment among the wafer manufacturing processes. The proposed system is to enhance the performance in cost and reliability by preventing the wafer cleaning system from damaging by alerting it when it is put in correct position. The proposed algorithm is in obtaining a mapping function from camera and physical wafer by designing and manufacturing the radial shape calibrator to reduce the error by using the conventional chess board one. The system is to install in-line process using high reliable and high accurate position recognition. The experimental results show that the performance of the proposed system is better than that of the existing method for detecting errors within tolerance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.343-344
• /
• 2010

markerless system to a two-dimensional imaging is used to estimate the depth map as a stereo vision system uses expensive equipment. We estimate the depth map from monocular image enhancement and object extracted relative to the vanishing point is estimated depth map. Augmented objects in order to get better virtual immersion depending on the distance of the objects should be drawn in different sizes. In this paper, creating images obtained from the vanishing point, and in-depth information on the augmented object, augmented with different sizes and improved engagement of inter-object interaction.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.3
• /
• pp.250-255
• /
• 2012

Face recognition has wide applications in security and surveillance systems as well as in robot vision and machine interfaces. Conventional challenges in face recognition include pose, illumination, and expression, and face recognition at a distance involves additional challenges because long-distance images are often degraded due to poor focusing and motion blurring. This study investigates the effectiveness of applying photon-counting linear discriminant analysis (Pc-LDA) to face recognition in harsh environments. A related technique, Fisher linear discriminant analysis, has been found to be optimal, but it often suffers from the singularity problem because the number of available training images is generally much smaller than the number of pixels. Pc-LDA, on the other hand, realizes the Fisher criterion in high-dimensional space without any dimensionality reduction. Therefore, it provides more invariant solutions to image recognition under distortion and degradation. Two decision rules are employed: one is based on Euclidean distance; the other, on normalized correlation. In the experiments, the asymptotic equivalence of the photon-counting method to the Fisher method is verified with simulated data. Degraded facial images are employed to demonstrate the robustness of the photon-counting classifier in harsh environments. Four types of blurring point spread functions are applied to the test images in order to simulate long-distance acquisition. The results are compared with those of conventional Eigen face and Fisher face methods. The results indicate that Pc-LDA is better than conventional facial recognition techniques.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.8
• /
• pp.98-103
• /
• 2019

A more accurate method of feature point extraction and matching for three-dimensional reconstruction using low-resolution images of crops is proposed herein. This method is important in basic computer vision. In addition to three-dimensional reconstruction from exact matching, map-making and camera location information such as simultaneous localization and mapping can be calculated. The results of this study suggest applicable methods for low-resolution images that produce accurate results. This is expected to contribute to a system that measures crop growth condition.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.2
• /
• pp.101-106
• /
• 2021

In this paper, an inspection system has been developed where pneumatic instruments are used to stretch the film using compressed air, thus the curl problem can be overcome. When the pneumatic system is applied, a line scan camera should be used instead of an area camera because the COF surface makes an arc by the air pressure. The distance between the COF and the inspection camera should be kept constant to get a clear image, thus the position of COF is to be monitored on real-time. An operating software has been also developed which is switching on/off the pneumatic system, determining the COF position using a camera vision, displaying the contour of the COF side view, sending self-diagnosis result and etc. The developed system has been examined using the actual roll of COF, which convince that the system can be an effective device to inspect the COF rolls in process.

• Trans-
• /
• v.10
• /
• pp.1-13
• /
• 2021

If virtual reality is well known through the medias, it seems that a few visual concepts are clearly related to VR. We try to think about it and introduce to a philosophy of VR techniques. So, from techniques and media techno-powers promotional campaigns, we aim to areal technology, it means an objective reflection on the VR techniques. To do so, we study the representations of VR in films. And we conclude that a negative image is the most common representation, related, often, to an Orwellian vision of the future world. In the second part, we study some VR films, and especially some made by famous film directors (Iñárritu, Bigelow). 'Head-turn' and 'Walk-around' films are commented to check their limits. Finally, we consider that for the moment, VR remains only a new space to screen films (into VR platforms connected to the Internet).

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.750-755
• /
• 2021

This paper proposes techniques for detecting the damage status of each part of a vehicle using YOLOv4. The proposed algorithm learns the parts and their damages of the vehicle through YOLOv4, extracts the coordinate information of the detected bounding boxes, and applies the algorithm to determine the relationship between the damage and the vehicle part to derive the damage status for each part. In addition, the technique using VGGNet, the technique using image segmentation and U-Net model, and Weproove.AI deep learning model, etc. are included for objectivity of performance comparison. Through this, the performance of the proposed algorithm is compared and evaluated, and a method to improve the detection model is proposed.

• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.411-427
• /
• 2022

Digging historical and cultural information from seals in ancient books is of great significance. However, ancient Chinese seal samples are scarce and carving methods are diverse, and traditional digital image processing methods based on greyscale have difficulty achieving superior segmentation and recognition performance. Recently, some deep learning algorithms have been proposed to address this problem; however, current neural networks are difficult to train owing to the lack of datasets. To solve the afore-mentioned problems, we proposed an SEL-RefineMask which combines selector of feature pyramid network (SEL-FPN) with RefineMask to segment and recognize seals. We designed an SEL-FPN to intelligently select a specific layer which represents different scales in the FPN and reduces the number of anchor frames. We performed experiments on some instance segmentation networks as the baseline method, and the top-1 segmentation result of 64.93% is 5.73% higher than that of humans. The top-1 result of the SEL-RefineMask network reached 67.96% which surpassed the baseline results. After segmentation, a vision transformer was used to recognize the segmentation output, and the accuracy reached 91%. Furthermore, a dataset of seals in ancient Chinese books (SACB) for segmentation and small seal font (SSF) for recognition were established which are publicly available on the website.