• 제어로봇시스템학회:학술대회논문집
• /
• 1986.10a
• /
• pp.331-336
• /
• 1986

Because the threshold technique using the histogram of intensity is the most attractive for segmentation in the sense of fast image processing, this paper defined the new function of inverse histogram of intensity and found out a threshold by means of it. The segmented errors are removed by regulating a scan size of blob coloring. Blob-coloring algorithm presented by [6] was reproved for good performance i.e., no change of feature in bolobs after blob coloring. The ratio of successful recognition was about 85 percents.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.8
• /
• pp.799-806
• /
• 2011

This paper proposes an algorithm to detect the stop line and crosswalk on the road surface using edge information and blob coloring. The detection has been considered as an important area of autonomous vehicle technologies. The proposed algorithm is composed of three phases: 1) hypothesis generation of stop lines, 2) hypothesis generation of crosswalks, and 3) hypothesis verification of stop lines. The last two phases are not performed if the first phase does not provide a hypothesis of a stop line. The last one is carried out by the combination of both hypotheses of stop lines and crosswalks, and determines the stop lines among stop line hypotheses. The proposed algorithm is proven to be effective through experiments with various images captured on the roads.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.261-264
• /
• 2019

There is the boundary following algorithm called by blob coloring or connected region labeling, which means that each pixel of the internal region can be filled with group label values by the raster scanning. This process represents to assigns the individual label value to each region. In this paper an improved equivalent table algorithm to be simpler and faster than the previous tangled complex labelling algorithm will be proposed when grouping different labels to the same region. 8 steps algorithms for grouping in the equivalent table will be presented and the yielding results will be shown.

• The Journal of the Korea Contents Association
• /
• v.11 no.10
• /
• pp.11-18
• /
• 2011

In the field of image processing to track the fingertip much research has been done. The most common way to calculate the fingertip first, to extract color information. Then, it uses Blob Coloring algorithms which are expressed in blob functions the skin contour and calculates. The algorithm from contour decides the highest location with the fingertip. But this method when measuring it location from the finger condition which bents is not the actual fingertip and has the problem which detects the location which goes wrong. This paper proposes the color space correction algorithm to tracks the fingertip which bents. The method which proposes when tracking the fingertip from the finger condition which bents solves the problem which measures the location which goes wrong. Aim of this paper in compliance with the propensity of the users forecasts a problem in advance and corrects with improvement at the time of height boil an efficiency. Ultimately, this paper suggests empirical application to verify the adequacy and the validity with the proposed method. Accordingly, the satisfaction and the quality of services will be improved the image recognition.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.478-481
• /
• 2008

기존 핑거 트래킹(Finger Tracking)을 수행하는데 있어 핑거팁(Finger-tip)을 구하는 방법 중 가장 일반적인 방법은 먼저 피부색 정보(Skin Color)를 추출한다. 그 다음 블럽(Blob) 함수의 블럽 컬러링(Blob Coloring) 알고리즘을 통하여 피부 윤곽선(Skin Contour)를 구하고, 그 중 가장 최상위 점을 핑거팁으로 정한다. 그러나 이 방법은 밴딩 핑거(Bending Finger) 상태에서 핑거팁 위치를 측정할 때 실제 손가락 끝이 아닌 잘못된 위치를 잡는 문제점을 가지고 있다. 본 논문에서 제안하는 방법은 밴딩 핑거 상태에서의 핑거 트래킹시 잘못된 핑거팁을 측정하는 문제점을 사용자들의 성향을 통해 미리 예상하고 보정함으로써 성능을 향상시키고자 한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.3
• /
• pp.101-110
• /
• 1995

본 논문에서는 새로은 자소분리 기법을 이용한 필기체 한글인식 시스템을 제안하였다. 새로운 자소분리 기법에는 국소영역 투영기법과 국소영역 Blob Coloring 기법이 포함되어 있다. 한극 각 자소의 특징들을 이용하여 Backpropagaton 알고리듬으로 학습시켰고 인식과정에서 관심영역 탐색기법이 이용되었다. 4명의 필기자가 작성한 1600자의 한글을 학습시키고 학습되지 않은 밝기 영상의 문서에 대한 인식을 시도한 결과 95%의 인식률을 얻었다.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.52 no.1
• /
• pp.35-41
• /
• 2003

In this paper, a machine vision system for recognizing and classifying the patterns and marks engraved by die molding or laser marking on the glass panels of computer monitors is suggested and evaluated experimentally. The vision system is equipped with a neural network and an NGC pattern classifier including searching process based on normalized grayscale correlation and adaptive binarization. This system is found to be applicable even to the cases in which the segmentation of the pattern area from the background using ordinary blob coloring technique is quite difficult. The inspection process is accomplished by the use of the NGC hypothesis and ANN verification. The proposed pattern recognition system is composed of three parts: NGC matching process and the preprocessing unit for acquiring the best quality of binary image data, a neural network-based recognition algorithm, and the learning algorithm for the neural network. Another contribution of this paper is the method of generating the training patterns from only a few typical product samples in place of real images of all types of good products.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.99.2-99
• /
• 2002

Contents 1 In this paper a machine vision system for recognizing and classifying the patterns and marks engraved by die molding or laser marking on glass panel of computer monitor is suggested and evaluated experimentally. The vision system is equipped with a neural network based pattern classifier and searching process based on normalized grayscale correlation and adaptive binarization, which is applicable to the cases in which the segmentation of the pattern area from background using the ordinary blob coloring technique is quite difficult. Inspection process is accomplished via the way of NGC hypothesis and ANN verification. The proposed pattern recognition system is composed of three...