• Proceedings of the IEEK Conference
• /
• 2003.11b
• /
• pp.255-258
• /
• 2003

This paper defines Normalized Term Frequency Weighting method for automatic text categorization by using Box-Cox, and then it applies automatic text categorization. Box-Cox transformation is statistical transformation method which makes normalized data. This paper applies that and suggests new term frequency weighting method. Because Normalized Term Frequency is different from every term compared by existing term frequency weighting method, it is general method more than fixed weighting method such as log or root. Normalized term frequency weighting method's reasonability has been proved though experiments, used 8000 newspapers divided in 4 groups, which resulted high categorization correctness in all cases.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1997.06a
• /
• pp.101-106
• /
• 1997

A method is proposed to generalize the image transformation from an image to another one according to a pair of example images. When an original image and its target image are given, the unknown image transformation from the original image to the target one in automatically approximated by a sequence of several known image transformation filters by the method. The target image is assumed to be generated manually by using a drawing software. In this method, the order of image transformation filers is regarded as the chromosome of a virtual living thing and is evolved according to Genetic Algorithm. This method can be applied to automatic construction of expert systems for image processing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3981-4004
• /
• 2019

This paper proposes a novel method for locating objects in real space from a single remote image and measuring actual distances between them by automatic detection and perspective transformation. The dimensions of the real space are known in advance. First, the corner points of the interested region are detected from an image using deep learning. Then, based on the corner points, the region of interest (ROI) is extracted and made proportional to real space by applying warp-perspective transformation. Finally, the objects are detected and mapped to the real-world location. Removing distortion from the image using camera calibration improves the accuracy in most of the cases. The deep learning framework Darknet is used for detection, and necessary modifications are made to integrate perspective transformation, camera calibration, un-distortion, etc. Experiments are performed with two types of cameras, one with barrel and the other with pincushion distortions. The results show that the difference between calculated distances and measured on real space with measurement tapes are very small; approximately 1 cm on an average. Furthermore, automatic corner detection allows the system to be used with any type of camera that has a fixed pose or in motion; using more points significantly enhances the accuracy of real-world mapping even without camera calibration. Perspective transformation also increases the object detection efficiency by making unified sizes of all objects.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.415-418
• /
• 2001

The automatic construction of large, high-resolution image mosaics is an active area of reasearch in the fields of photogrammetry, computer vision, image processing, and computer graphics. In this study, we describe a automatic mosaicing method that makes a panorama from images by placing camera in a emitted-grid. In the images captured by cameras, there must be a matched area and the area is in the particular area of the image. Initial transformation matrix, there(ore, is calculated from points searched in the partial area. It is possible to find best transformation matrix by Levenberg-Marquardt method. Finally, each images are multiplied by blending function and stitched by the transformation matrix to complete panoramic image.

• Journal of Welding and Joining
• /
• v.16 no.6
• /
• pp.68-76
• /
• 1998

A CCD camera with a laser stripe was applied to realized the automatic weld seam tracking. The 3-dimensional information obtained from the vision system made it possible to generate the weld torch path. The adaptive Hough transformation was used to extract laser stripes an to obtain specific weld points. It takes relatively long time to process image on-line control using the basic control using the basic Hough transformation, but it has a tendency of robustness over the noises such as spatter. For this reason, it was complemented with adaptive Hough transformation to have an on-line processing ability for scanning specific weld points. The dead zone, where the sensing of weld line is impossible, was eliminated by rotating the camera with its rotating axis centered at the weld torch. When weld lines were detected, the camera angle was controlled in order to get the minimum image data for sensing of weld lines. Consequently, the image processing time was reduced.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.1105-1109
• /
• 1995

A CCD-camera, which is structured with vision system, was used to realize automatic seam-tracking system and 3-D information which is needed to generate torch path, was obtained by using laser-slip beam. To extract laser strip and obtain welding-specific point, Adaptive Hough-transformation was used. Although the basic Hough transformation takes too much time to process image on line, it has a tendency to be robust to the noises as like spatter. For that reson, it was complemented with Adaptive Hough transformation to have an on-line processing ability for scanning a welding-specific point. the dead zone,where the sensing of weld line is impossible, is eliminated by rotating the camera with its rotating axis centered at welding torch. The camera angle is controlled so as to get the minimum image data for the sensing of weld line, hence the image processing time is reduced. The fuzzy controller is adapted to control the camera angle.

• Proceedings of the KSME Conference
• /
• 2000.11a
• /
• pp.813-817
• /
• 2000

Cam mechanism is one of the common devices used in many automatic machinery. Specially cylindrical cam generates three dimensional motions. Thus, the shape design procedure must have high accuracy. This paper proposes the shape design procedure for a cylindrical cam and follower mechanism using a relative velocity method. The relative velocity method and coordinate transformation are used to find a contact point between cam and follower. Also, the full shape of the cylindrical cam can be generated by using the geometric relationships and the contact constraints. As a result, this paper presents an example for the sape design of the cylindrical cam in order to prove the accuracy of the design procedures.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.238-240
• /
• 2003

As remote sensing is weighty in GIS updating, it is indispensable to get spatial information quickly and exactly. In this study, we have designed and implemented the program by two algorithms of GDPA (Gradient Direction Profile Analysis) and Hough transformation to extract linear features automatically from high-resolution imagery. We applied the software to embody both algorithms to KOMPSAT-EOC, IKONOS, and Landsat-ETM and made a comparative study of results.

• Korean Journal of Remote Sensing
• /
• v.26 no.1
• /
• pp.39-45
• /
• 2010

This study used the keypoint observed simultaneously on two images and on twodimensional intensity image data, which was obtained along with the two point clouds data that were approached for automatic focus among points on terrestrial LiDAR data, and selected matching point through SIFT algorithm. Also, for matching error diploid, RANSAC algorithm was applied to improve the accuracy of focus. As calculating the degree of three-dimensional rotating transformation, which is the transformation-type parameters between two points, and also the moving amounts of vertical/horizontal, the result was compared with the existing result by hand. As testing the building of College of Science at Konkuk University, the difference of the transformation parameters between the one through automatic matching and the one by hand showed 0.011m, 0.008m, and 0.052m in X, Y, Z directions, which concluded to be used as the data for automatic focus.

• Journal of Korea Multimedia Society
• /
• v.10 no.10
• /
• pp.1240-1250
• /
• 2007

We introduce technique for color transformation of characters between scenes in 2D animation. As colors are perceived differently owing to light source, so character colors like clothes, skin and so on are colored differently owing to atmosphere of each scene. This paper is made an attempt to solve mathematically color assignment of characters which has been worked by hand so far. We can find a matrix for color transformation of characters by appling principle of color stimulus to our algorithm. In scenes of existing 2D animation, basic colors and colors under light source of characters are used for the matrix. And matrixes are obtained for each scenes of 2D animation. If we are known basic colors of some characters, you can derive character colors under other light source environments using the matrix. Therefore, this paper describes automatic color transformation of characters between animation scenes.