• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.9
• /
• pp.84-93
• /
• 1993

Recently, several nonlinear shape normalization methods have been proposed in order to compensate for the shape distortions in handwritten characters. In this paper, we review these nonlinear shape normalization methods from the two points of view : feature projection and feature density equalization. The former makes feature projection histogram by projecting a certain feature at each point of input image into horizontal-or vertical-axis and the latter equalizes the feature densities of input image by re-sampling the feature projection histogram. A systematic comparison of these methods has been made based on the following criteria: recognition rate, processing speed, computational complexity and measure of variation. Then, we present the result of quantitative evaluation of each method based on these criteria for a large variety of handwritten Hangul syllables.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.2
• /
• pp.94-102
• /
• 2011

In this paper, a novel drowsiness detection algorithm using eye-blink pattern is proposed. The proposed drowsiness detection model using finite automata makes it easy to detect eye-blink, drowsiness and sleep by checking the number of input symbols standing for closed eye state only. Also it increases the accuracy by taking vertical projection histogram after locating the eye region using the feature of horizontal projection histogram, and minimizes the external effects such as eyebrows or black-framed glasses. Experimental results in eye-blinks detection using the JZU eye-blink database show that our approach achieves more than 93% precision and high performance.

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.521-524
• /
• 2003

In this paper, we propose a face region extraction algorithm using color information and projection. After the extraction of face candidate image using adaptive color information, we project it into vertical direction to estimate the width of the face. Then the redundant parts of the face are efficiently removed by using the estimated face width. And the width information of the face is used at the horizontal projection step to extract the height of the face, and non-face region such as the neck and some background regions, which are represented as the similar skin color, effectively eliminated. From the experiment results for the various images, the proposed algorithm shows more accurate results than the conventional algorithm.

• ETRI Journal
• /
• v.31 no.2
• /
• pp.105-110
• /
• 2009

In this paper, we propose a curved projection integral imaging system to improve the horizontal and vertical viewing angles. The proposed system can be easily implemented by additional use of a large-aperture convex lens in conventional projection integral imaging. To obtain the simultaneous display of 3D images through real and virtual image fields, we propose a computer-generated pickup method based on ray optics and elemental images, which are synthesized for the proposed system. To show the feasibility of the proposed system, preliminary experiments are carried out. Experimental results indicate that our system improves the viewing angle and displays 3D images simultaneously in real and virtual image fields.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.17 no.1
• /
• pp.115-121
• /
• 2014

In this paper, we propose a robust background removal integral projection(BRIP) method which can detect close surface targets in coastal environment for IRST. Row pixels of background region from coastal infrared image show similar response. Thus, the proposed BRIP is calculated after horizontal and vertical background estimations and removals are performed sequentially. Finally, surface large targets can be detected using the results of the BRIP. Experimental results on a set of real infrared image sequence show that the proposed method could fully detect ships in every frame.

• Korean Journal of Applied Biomechanics
• /
• v.21 no.5
• /
• pp.645-652
• /
• 2011

The purpose of this study was to analyze, in real time, the glide motion and release motion of domestic athletes and gold and bronze medalists employing the glide technique for the men's shot put at the Daegu World Athletic Championship in 2011. In the glide motion, the Korean athletes had a relatively high body center and shot put heights and lager stretching angles for their hips and knees. In the delivery phase, which shifts to the release phase, the Korean athletes showed slower vertical body center and shot put speeds, and they changed the phase, to the release phase by using a small body angle. In the release phase, the Korean athletes showed differences in their projection speeds and vertical body center speeds. The world-famous players showed high angle speeds, which refer to the composition of the rotation force at the moment of release (body, hip, and shoulder line). In the release phase, the Korean athletes did not have fully stretched hip and knee angles, which might have negatively influenced the vertical speed. Because the Korean athletes showed relatively low projection heights and projection angles. it was found that they need to enhance the muscular power of their, throwing arms and lower limbs.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.8
• /
• pp.818-823
• /
• 2008

In this paper, we propose a feature extraction method which extracts directional features of handwritten numerals by using the projection runlength. Our directional featrures are obtained from four directional images, each of which contains horizontal, vertical, right-diagonal and left-diagonal lines in entire numeral shape respectively. A conventional method which extracts directional features by using Kirsch masks generates edge-shaped double line directional images for four directions, whereas our method uses the projections and their runlengths for four directions to produces single line directional images for four directions. To obtain the directional projections for four directions from a numeral image, some preprocessing steps such as thinning and dilation are required, but the shapes of resultant directional lines are more similar to the numeral lines of input numerals. Four [$4{\times}4$] directional features of a numeral are obtained from four directional line images through a zoning method. By using a hybrid feature which is made by combining our feature with the conventional features of a mesh features, a kirsch directional feature and a concavity feature, higher recognition rates of the handwrittern numerals can be obtained. For recognition test with given features, we use a multi-layer perceptron neural network classifier which is trained with the back propagation algorithm. Through the experiments with the handwritten numeral database of Concordia University, we have achieved a recognition rate of 97.85%.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.6
• /
• pp.261-268
• /
• 2007

In this paper, We propose a new technique extract efficiently a car number plate based on edge projection. In order to obtain the region of car number plate, we use a motive that the luminance differences between the number plate background and characters. And, we introduce a projection technique to obtain character parts based on edge image. In vertical direction. we propose a shape matching method. Specially the new number plate standard has more characters than the old one in horizontal direction and, it is efficiently used to extract the number plate. Therefore, the proposed technique is useful to the new number plate standard. In simulation results. We have illustrated that our algorithm can recognize different number plates with a success ration of 90%.

• The korean journal of orthodontics
• /
• v.33 no.2 s.97
• /
• pp.73-84
• /
• 2003

This study was performed to find out how much projection errors in the cephalometric measurements were made by vertical head rotation in taking posteroanterior cephalograms. 25 adults without any apparent facial asymmetry or severe sagittal skeletal discrepancy were selected and the posteroanterior cephalograms were taken with the head rotated $5^{\circ},\;10^{\circ}$ superior and inferior each to the reference $position(0^{\circ})$. The 7 height, 5 width and 6 angular measurements were taken at each 5 positions. Through the statistical analysis of all measurements taken at each rotated position, folowing results were obtained.1. The projection errors of height measurements were remarkably target than those of width or angular measure nents. f. Among the height measurements, the farther to the rotation axis the measurements were, the larger the projection errors were. 3. Among the width measurements, mandibular width and mandibular width of mandibular first molars showed significant differences between the values taken at each rotated position, while nasal width, maxillary width and intermolar width of maxillary first molars did not. 4. Among the angular measurements, the angle between horizontal reference line and the line that is connected to crista galli and antegonion or maxillare showed significant differences between the values taken at each rotated Position. The above results suggest that it is needed to the effort to keep constant head position for taking the useful posteroanterior cephalogra, because projection errors are caused by vertical head rotation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.8
• /
• pp.1874-1884
• /
• 1996

In this paper, we proposed automatic searching algorithm of thresholding value using multilevel thresholding for face segmentation from input bust image effectively. The proposed algorithm extracted the thresholding value of brightness that is formed background region, face region and hair region without illumination, background and face size from input image. The statistical projection analysis project the brightness of multilevel thresholding image into horizontal and vertical direction and decide the thresholding value of face. And the algorithm extracted elliptical type block of face from input image in order to reduce the back ground region and hair region efficiently. The proposed algorithm can reduce searching area of feature extraction and processing time for face recognication.