• Journal of Biosystems Engineering
• /
• 제21권3호
• /
• pp.325-335
• /
• 1996

표고의 외관 특징들은 표고의 재배 시 생육상태의 정량적 측정을 위해서, 표고의 건조 시 건조 성능을 나타내는 정량적 지표로서, 그리고 건표고의 품질을 판정하는 요인으로서 중요한 역할을 한다. 본 논문에서는 컴퓨터 시각시스템 및 신경회로망 기술을 적용하여 표고의 갓 및 내피에 고루 분포되어 있는 외관특징을 정량적으로 추출하는 알고리즘을 개발하였다. 기존의 영상 처리 과정에서 유도되는 경험적 판정규칙 또는 명확한 수치적 판정조건에 의한 등급판정은 입력데이타의 결핍 또는 애매모호성에 따른 오차가 발생하기 쉽다. 신경회로망을 이용한 영상인식 기능을 도입함으로써 다양하고 애매모호한 표고의 외관 영상특징들을 효율적으로 처리하여 기존 영상처리 알고리즘에서 발생하는 오차를 개선하였다. 본 논문에서 제안하는 알고리즘은 표고의 갓과 내피면의 인식 및 특징 분할, 꼭지부의 검출, 제거 및 재생 등을 포함한다. 제안한 알고리즘에 의거하여 건표고의 등급판정에 주요한 품질인자들을 추출하고 정량화 하였다. 그리고 알고리즘의 개발은 흑백의 다치입력영상을 이용하여 수행하였다.

• 제어로봇시스템학회논문지
• /
• 제19권12호
• /
• pp.1099-1104
• /
• 2013

This paper presents a learning-based visual inspection method that addresses the need for an improved adaptability of a visual inspection system for parts verification in panorama sunroof assembly lines. It is essential to ensure that the many parts required (bolts and nuts, etc.) are properly installed in the PLC sunroof manufacturing process. Instead of human inspectors, a visual inspection system can automatically perform parts verification tasks to assure that parts are properly installed while rejecting any that are improperly assembled. The proposed visual inspection method is able to adapt to changing inspection tasks and environmental conditions through an efficient learning process. The proposed system consists of two major modules: learning mode and test mode. The SVM (Support Vector Machine) learning algorithm is employed to implement part learning and verification. The proposed method is very robust for changing environmental conditions, and various experimental results show the effectiveness of the proposed method.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1996년도 International Conference on Agricultural Machinery Engineering Proceedings
• /
• pp.773-779
• /
• 1996

Dried oak mushroom have complex and various visual features. Grading and sorting of dried oak mushrooms has been done by the human expert. Though actions involved in human grading looked simple, a decision making underneath the simple action comes from the result of the complex neural processing of the visual image. Through processing details involved in human visual recognition has not been fully investigated yet, it might say human can recognize objects via one of three ways such as extracting specific features or just image itself without extracting those features or in a combined manner. In most cases, extracting some special quantitative features from the camera image requires complex algorithms and processing of the gray level image requires the heavy computing load. This fact can be worse especially in dealing with nonuniform, irregular and fuzzy shaped agricultural products, resulting in poor performance because of the sensitiveness to the crisp criteria or specific ules set up by algorithms. Also restriction of the real time processing often forces to use binary segmentation but in that case some important information of the object can be lost. In this paper, the neuro net based real time recognition algorithm was proposed without extracting any visual feature but using only the directly captured raw gray images. Specially formated adaptable size of grids was proposed for the network input. The compensation of illumination was also done to accomodate the variable lighting environment. The proposed grading scheme showed very successful results.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2008년도 춘계학술대회 논문집
• /
• pp.19-20
• /
• 2008

• 정보교육학회논문지
• /
• 제6권2호
• /
• pp.179-186
• /
• 2002

자료구조 및 알고리즘 분야는 컴퓨터 프로그래밍 교육의 기반이 되는 과목이다. 그러나, 이제는 이 과목에서 활용되는 프로그래밍 방법이 비주얼 프로그래밍과 윈도우 프로그래밍에 적당하지 못하다고 해서 학생들로부터 외면당하고 있다. 따라서, 본 논문에서는 효과적으로 탐색 알고리즘을 교육할 수 있고, 비주얼 프로그래밍에 기반을 둔 소프트웨어 컴포넌트인 SCSA (Software Component for Search Algorithm)를 개발하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(4)
• /
• pp.230-233
• /
• 2000

In this paper, we proposed a wavelet-based digital watermarking algorithm using human visual system and subband-adaptive threshold. After the original image is transformed using discrete wavelet transform(DWT), the perceptually significant coefficients of the each subband excluding the lowest level subbands are utilized to embed the watermark. To select perceptually significant coefficients, we use subband-adaptive threshold. For the selected coefficients, the watermark is embedded by rising HVS. We tested the performance of the proposed algorithm compared with conventional watermarking algorithm by computer simulation. The experimental results show that the proposed algorithm is superior to the conventional algorithm.

• 한국컴퓨터산업학회논문지
• /
• 제3권12호
• /
• pp.1725-1736
• /
• 2002

에지 시그널의 세기가 갖는 특징적인 성질로서, 에지를 가로질러 엄격하게 단조적인 세기 변화가 나타남을 설명하고 이를 바탕으로 하는 새로운 에지 검출 알고리듬을 제안한다. 스케일링에 무관하고 비국소적인 확장된 방향미분을 픽셀 공간에서 도입하여, 본 알고리듬이 에지 폭의 다양한 변화에 적응성을 가지며 최적의 에지 검출 알고리듬으로서 적절함을 설명한다. 본 알고리듬의 산업적 응용으로서, 시각적 검사에 대한 간단한 컴퓨터 비전 프로시저의 한 예를 살펴본다.

• 반도체디스플레이기술학회지
• /
• 제8권4호
• /
• pp.95-100
• /
• 2009

This paper presents an efficient disparity matching, using sum of absolute difference (SAD) and dynamic programming (DP) algorithm. This algorithm makes use of one of area-based algorithm which is the absolute sum of the pixel difference corresponding to the window size. We use the information of the right eye brightness (B) and the left eye brightness to get an best matching results and apply the results to the left eye image using the window go by the brightness of the right eye image. This is that we can control the brightness. The major feature of this algorithm called SAD+DP+B is that although Root Mean Square (RMS) performance is slightly less than SAD+DP, due to comparing original image, its visual performance is increased drastically for matching the disparity map on account of its matching compared to SAD+DP. The simulation results demonstrate that the visual performance can be increased and the RMS is competitive with or slightly higher than SAD+DP.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.309-310
• /
• 2006

This paper presents an enhanced algorithm for compensating the visual quality in backlight image. Current cameras do not represent all details of scene into human's eye. Saturation and underexposure are common problems in backlight image. Retinex algorithm, derived from Land's theory on human visual perception is known to be effective in enhancing the contrast. However, its weaknesses are long processing time and low contrast of bright area in backlight scene because of compensating the details of dark area. In this paper, K-Retinex algorithm is proposed to reduce the processing time and enhance the contrast in both dark and bright area. To show the superiority of proposed algorithm, we compare the processing time and local variance of each area above.

• Journal of Positioning, Navigation, and Timing
• /
• 제2권1호
• /
• pp.81-89
• /
• 2013

Many of the current visual odometry algorithms suffer from some extreme limitations such as requiring a high amount of computation time, complex algorithms, and not working in urban environments. In this paper, we present an approach that can solve all the above problems using a single camera. Using a planar motion assumption and Ackermann's principle of motion, we construct the vehicle's motion model as a circular planar motion (2DOF). Then, we adopt a 1-point method to improve the Ransac algorithm and the relative motion estimation. In the Ransac algorithm, we use a 1-point method to generate the hypothesis and then adopt the Levenberg-Marquardt method to minimize the geometric error function and verify inliers. In motion estimation, we combine the 1-point method with a simple least-square minimization solution to handle cases in which only a few feature points are present. The 1-point method is the key to speed up our visual odometry application to real-time systems. Finally, a Bundle Adjustment algorithm is adopted to refine the pose estimation. The results on real datasets in urban dynamic environments demonstrate the effectiveness of our proposed algorithm.