• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.5
• /
• pp.601-607
• /
• 2018

Median filtering is a nonlinear method which is known to be effective in removing impulse noise while preserving local image structure relatively well. However, it could still suffer the smearing phenomena of edges and fine details into neighbors due to undesirable influence from the pixels whose values are far off from the true value of the pixel at hand. This drawback mainly comes from the fact that median filters typically employ a regular shape window for collecting the pixels used in the filtering operation. In this paper, we propose a median filtering method which employs an irregular shape filter window in collecting neighboring pixels around the pixel to be denoised. By employing an irregular shape window, we can achieve good noise suppression while preserving image details. Experimental results have shown that our approach is superior to regular window-based methods.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.6
• /
• pp.85-90
• /
• 1998

The most important step image processing is stereo matching process. That is finding pixels of 3 dimensional pair in the left and right image. There are two matching methods. One is an area based approach and the other is a feature based approach. An area based approach needs much calculation time. In the other hand, we have the advantage of calculation time in the feature based approach, but can not obtain matched data for all pixels in the image. In recent years, fuzzy image processing methods are developed to manage vagueness and noise in image and ambiguous, inconsistent knowledge in recognition step. In this paper, we propose a fuzzy stereo matching algorithm. This method converts brightness data of image to fuzzy membership value and processes an area based approach method for stereo matching algorithm. We experiment with some stereo images to validate effectiveness of this algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.4
• /
• pp.957-964
• /
• 2011

The image stabilization is the procedure of stabilizing the blurred image with image processing method. Due to easy detection of global motion, PA(Projection algorithm) based on digital image stabilization has been studied by many researchers. PA has the advantage of easy implementation and low complexity, but in the case of serious rotational motion the accuracy of the algorithm will be cut down because of its fixed exploring range, and, on the other hand, if extending the exploring range, the block for detecting motion will become small, then we cannot detect correct global motion. In this paper, to overcome the drawback of conventional PA, an Iterative Projection Algorithm (IPA) is proposed, which improved the correctness of global motion by detecting global motion with detecting block which is appropriate to different extent of motion. With IPA, in the case of processing 1000 continual frames shot in automobile, compared with conventional algorithm and other detecting range, the results of PSNR is improved 6.8% at least, and 28.9% at the most.

• Journal of Bio-Environment Control
• /
• v.10 no.3
• /
• pp.172-180
• /
• 2001

A grape fruit is required for a lot of labor to harvest in time in Korea, since the fruit is cut and grabbed currently by hand. In foreign country, especially France, a grape harvester has been developed for processing to make wine out of a grape, not to eat a fresh grape fruit. However, a harvester which harvests to eat a fresh grape fruit has not been developed yet. Therefore, this study was designed and constructed to develope a image processing system for a fresh grape harvester. Its development involved the integration of a vision system along with an personal computer and two cameras. Grape recognition, which was able to found the accurate cutting position in three dimension by the end-effector, needed to find out the object from the background by using two different images from two cameras. Based on the results of this research the following conclusions were made: The model grape was located and measured within less than 1,100 mm from camera center, which means center between two cameras. The distance error of the calculated distance had the distance error within 5mm by using model image in the laboratory. The image processing system proved to be a reliable system for measuring the accurate distance between the camera center and the grape fruit. Also, difference between actual distance and calculated distance was found within 5 mm using stereo vision system in the field. Therefore, the image processing system would be mounted on a grape harvester to be founded to the position of the a grape fruit.

• Korean journal of food and cookery science
• /
• v.22 no.6 s.96
• /
• pp.864-868
• /
• 2006

The characteristics of Backsulgi were studied by digital image analysis using CrumScan software. Among many other processing parameters for Backsulgi production, sifting method and levels are important factors for product quality. Traditional and mechanical sifting methods showed a reduction in volume and weight due to air intake during the mixing process. Traditional hand sifting for one time resulted in flour saving for an equal volume of Backsulgi. While mechanical sifting has the advantage of efficiency, the particle fineness shows greater variation than achieved by hand sifting. When using mechanical sifting, hand sifting should be used at least once to improve the product quality such as crumb fineness and product, weight.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.4
• /
• pp.117-123
• /
• 2016

A hand-gesture interface to manipulate a 3D object of augmented reality is implemented by recognizing the user hand-gesture in this paper. Proposed method extracts the hand region from real image, and creates augmented object by hand marker recognized user hand-gesture. Also, 3D object manipulation corresponding to user hand-gesture is performed by analyzing a hand region ratio, a numbet of finger and a variation ratio of hand region center. In order to evaluate the performance of the our proposed method, after making a 3D object by using the OpenGL library, all processing tasks are implemented by using the Intel OpenCV library and C++ language. As a result, the proposed method showed the average 90% recognition ratio by the user command-modes successfully.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.1
• /
• pp.103-113
• /
• 2003

We must enhance a fingerprint image to improve the performance of a fingerprint recognition. Because of this reason, many researches were achieved about the fingerprint image enhancement. Representative method is to use Gabor-Filter among them. However GF has the weakness which a processing hour takes long. In this paper, we proposed Half Gabor Filter (HGF) to enhance the fingerprint image fast in the on-line. The HGF, however, can make calculation much simpler, as well as both minutiae-extraction rate and recognition rate. On the other hand, the fingerprint image to enhance using HGF has almost same with the case effectiveness to apply GF. In this paper, we confirme it mathematically and experimentally.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.713-722
• /
• 2013

This paper proposes a method of using depth information to detect the hand region in real-time based on the cascade method. In order to ensure stable and speedy detection of the hand region even under conditions of lighting changes in the test environment, this study uses only features based on depth information, and proposes a method of detecting the hand region by means of a classifier that uses boosting and cascading methods. First, in order to extract features using only depth information, we calculate the difference between the depth value at the center of the input image and the average of depth value within the segmented block, and to ensure that hand regions of all sizes will be detected, we use the central depth value and the second order linear model to predict the size of the hand region. The cascade method is applied to implement training and recognition by extracting features from the hand region. The classifier proposed in this paper maintains accuracy and enhances speed by composing each stage into a single weak classifier and obtaining the threshold value that satisfies the detection rate while exhibiting the lowest error rate to perform over-fitting training. The trained classifier is used to classify the hand region, and detects the final hand region in the final merger stage. Lastly, to verify performance, we perform quantitative and qualitative comparative analyses with various conventional AdaBoost algorithms to confirm the efficiency of the hand region detection algorithm proposed in this paper.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2291-2294
• /
• 2003

본 논문에서는 손목이나 손바닥 아래에 부착된 PC카메라와 두 개의 광원을 이용한 데이터 글러브 구현 방법을 제안한다 기존의 데이터 글러브 방식은 글러브를 손에 착용하여야 하는 단점이 있으며 영상처리 기반의 HCI 방법 또한 공간상에 고정된 카메라를 이용함으로써 웨어러블 컴퓨팅이나 모바일 환경하에서는 사용할 수 없다. 이 문제를 해결하기 위해 본 논문은 착용 가능한 한대의 카메라와 두 개의 평행 광을 사용하여 손 모양을 입력하는 방법을 제안하였다. 또한 손 영상을 제외한 배경영상을 이용하여 손의 변위를 얻어낼 수 있는 방법을 제안한다. 제안된 방법을 구현한 "BareHand 1.0"과 테스트 결과에 대해서도 논하였다.

• Korean Journal of Mathematics
• /
• v.14 no.1
• /
• pp.35-46
• /
• 2006

The concept of convolution is a fundamental mathematical concept in a wide variety of disciplines and applications including probability, image processing, physics, and many more. The visualization of convolution for the continuous case is generally predetermined. On the other hand, the convolution structure embedded in the discrete case is often subtle and its visualization is non- trivial. This paper purports to develop the CAS techniques in visualizing the logical structure in the concept of a discrete convolution.