• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.410-412
• /
• 2021

This paper proposes an improved pedestrian detection method using object and background histograms. Objects detected through the HOG & SVM algorithm are detected in a square shape. Inside the square area, the background and the object area are mixed. If only the area of the object excluding the background is detected, various object-related information may be easily obtained. The size of the detected rectangle is readjusted using an xy-axis projection algorithm to fit the size of the object. And then, the improved object is detected by dividing the background and the object based on the histogram of the object in the readjusted square. The average values of precision and recall, which are reliability evaluations comparing the detected object with the original object, are 97.9% and 90%, respectively.

• Journal of Korea Multimedia Society
• /
• v.15 no.11
• /
• pp.1341-1348
• /
• 2012

In this paper, an efficient scheme for correcting rotated objects in medical images using the Mojette transform is presented. The Mojette transform is a kind of discrete Radon transform, where the transform domain is represented by a set of projections. The Mojette transform currently studied in the image compression area is modified for detecting the rotation angle of objects in medical images. First, in order to find accurate rotation angle, the projection value in the Mojette transform is determined by using pixels on the projection line and in addition the linear interpolation of pixels adjacent to the line. Second, at each projection angle, only one projection is implemented for reducing the amount of the calculation in the process of the Mojette transform. Finally, the projection in the Mojette transform is carried out at the predetermined ROI(Region Of Interest) at which the objects are not cropped or added by rotating the image. The simulation results show that the proposed method has good performance for correcting the rotation angle in medical images.

• The Journal of the Korea Contents Association
• /
• v.22 no.2
• /
• pp.35-43
• /
• 2022

The 2020 Gwangju Media Art Festival (2020 GMAF) was held in the area of the National Asian Cultural Center. Under the slogan "The entire Gwangju shines under the theme of "Aesthetics of Light and Coexistence," the media festival demonstrated projection mapping to Jeonnam (former) Provincial Office at the DATA+ Research Institute of Chung-Ang University's Graduate School of Advanced Video. This paper focuses on explaining the overall production process and content development of projection mapping demonstrated in the Jeollanam-do Provincial Government, which is a symbol of Korean democratization and is located in the center of Gwangju, Jeolla-do. It was intended to faithfully express the history of the 2020 GMAF and Jeonnam (former) provincial government, Gwangju's history, and democratization records. It was intended to show images, background sounds, sound effects, and visual effects using various special effects and high-power laser devices using unique characteristics of projection mapping. To this end, about 5 minutes and 30 seconds of content were planned, and it was divided into parts and topics, and one individual story was developed for each chapter.

• Laser Solutions
• /
• v.17 no.3
• /
• pp.19-23
• /
• 2014

To directly engrave circuit-line patterns as wide as $6{\mu}m$ in a buildup film to be used as an IC substrate, we applied a projection ablation technique in which an 8 inch dielectric ($ZrO_2/SiO_2$) mask, a DPSS 355nm laser instead of an excimer laser, a ${\pi}$-shaper and a galvo scanner are used. With the ${\pi}$-shaper and a square aperture, the Gaussian beam from the laser is shaped into a square flap-top beam. The galvo scanner before the $f-{\theta}$ lens moves the flat-top beam ($115{\mu}m{\times}105{\mu}m$) across the 8 inch dielectric mask whose patterned area is $120mm{\times}120mm$. Based on the results of the previous research by the authors, the projection ratio was set at 3:1. Experiments showed that the average width and depth of the engraved patterns are $5.41{\mu}m$ and $7.30{\mu}m$, respectively.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.575-578
• /
• 2005

Topographical images, in case of aerial or satellite images, are usually similar in colors and textures, and complex in shapes. Thus we have to use shape features of images for efficiently retrieving a query image from topographical image databases. In this paper, we propose a shape feature extraction method which is suitable for topographical images. This method, which improves the existing projection in the Cartesian coordinates, performs the projection operation in the polar coordinates. This method extracts three attributes, namely the number of region pixels, the boundary pixel length of the region from the centroid, the number of alternations between region and background, along each angular direction of the polar coordinates. It extracts the features of complex shape objects which may have holes and disconnected regions. An advantage of our method is that it is invariant to rotation/scale/translation of images. Finally we show the advantages of our method through experiments by comparing it with CSS which is one of the most successful methods in the area of shape feature extraction

• Progress in Medical Physics
• /
• v.15 no.2
• /
• pp.70-76
• /
• 2004

The most important work for early detection of liver cancer and decision of its characteristic and location is good segmentation of a liver region from other abdominal organs. This paper proposes a fully automatic liver segmentation algorithm based on the abdominal morphology characteristic as an easy and efficient method. Multi-modal threshold as pre-processing is peformed and a spine is segmented for finding morphological coordinates of an abdomen. Then the liver region is extracted using C-class maximum a posteriori (MAP) decision and morphological filtering. In order to estimate results of the automatic segmented liver region, area error rate (AER) and correlation coefficients of rotational binary region projection matching (RBRPM) are utilized. Experimental results showed automatic liver segmentation obtained by the proposed algorithm provided strong similarity to manual liver segmentation.

• Journal of Korea Technical Association of The Pulp and Paper Industry
• /
• v.41 no.4
• /
• pp.25-32
• /
• 2009

Forest biomass can be used as various types of raw materials such as pulp, wood pellets, solid charcoals and so on. This paper estimates the nation wide amount of forest biomass based on the projection of forest areas for its effective and economic use. Several trend equations are used in projecting the forest areas. In 2009, the forest biomass arising from thinning is estimated be 6,591,575 $m^3$. The estimates of forest biomass in 2015 and 2018 are 6,375,627 $m^3$ and 6,284,779 $m^3$, respectively. Since the forest areas are projected to be declining, the biomass generated by thinning will decrease. This implies that the new alternatives for supplying raw materials for biofuels must be prepared before then.

• Journal of Welding and Joining
• /
• v.27 no.3
• /
• pp.92-96
• /
• 2009

Metallic sandwich plate has many good properties such as high specific stiffness, high specific strength, good impact absorptivity, effective thermal insulation and soundproofing. In our study, a new bonding method, 3-layer roll projection welding, is introduced to fabricate the metallic sandwich plate. The new method uses a pair of roll electrodes like the seam welding, and projection welding is made at two internal interfaces of the 3-layer weldment consisting of a structured inner sheet and a pair of skin sheets. During the welding process, skin sheet temperature are measured to produce metallic sandwich plate with uniform and good quality. But it is difficult to observe or measure the temperature at the welding points during welding process because the welding points exist at the internal interfaces. Therefore FEM numerical analysis using ABAQUS is conducted to estimate the generated heat at the welding points with different welding conditions.

• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.13 no.1
• /
• pp.7-15
• /
• 1983

The purpose of this study was to investigate the radiographic images of the condylar head in clinically normal subjects and the TMJ patients using standardized projection technique. 45 subjects who have not clinical evidence of TMJ problems and 96 patients who have the clinical evidence of TMJ problems were evaluated, but the patients who had fracture, trauma and tumor on TMJ area were discluded in this study. For the evaluation of radiographic images, the author has observed the condylar head positions in closed mouth and 2.54㎝ open mouth position taken by the standardized transcranial oblique lateral projection technique. The results were as follows: 1. In closed mouth position, the crest of condylar head took relatively posterior position to the deepest point of the glenoid fossa in 8.9 % of the normals and in 26.6% of TMJ patients. 2. In 2.54㎝ open mouth position, condylar head took relatively posterior position to the articular eminence in 2.2% of TMJ patients and 39.6% of the normals. 3. In open mouth position, the horizontal distance from the deepest point of the glenoid fossa to the condyla head was 13.96㎜ in the normals and 10.68㎜ in TMJ patients. 4. The distance of true movement of condyalr head was 13.49㎜ in the normals and l0.27㎜ in TMJ patients. 5. The deviation of mandible in TMJ patients was slightly greater than that of the normals.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.1
• /
• pp.378-390
• /
• 2015

Image projectors can turn any surface into a display. Integrating a surface projection with a user interface transforms it into an interactive display with many possible applications. Hand gesture interfaces are often used with projector-camera systems. Hand detection through color image processing is affected by the surrounding environment. The lack of illumination and color details greatly influences the detection process and drops the recognition success rate. In addition, there can be interference from the projection system itself due to image projection. In order to overcome these problems, a gesture interface based on depth images is proposed for projected surfaces. In this paper, a depth camera is used for hand recognition and for effectively extracting the area of the hand from the scene. A hand detection and finger tracking method based on depth images is proposed. Based on the proposed method, a touch interface for the projected surface is implemented and evaluated.