• 대한의용생체공학회:의공학회지
• /
• 제10권3호
• /
• pp.331-342
• /
• 1989

This paper presents a new algorithm that extracts lung region in X-Rays and enhance.j the region. Comparing to prior algorithms that enhance whole X-Ray image, this algorithm leads more effective results. For this algorithm extracts lung region first, and enhances the lung region excluding parameters of other region. For choosing optimal threshold, we compare OTSU's mothod with the proposed method. We obtain lung boundary using contour following algorithm and Rray level searching method in gray level rescaled image. We Process histogram equalization in lung region and obtain enhanced lung image. By using the proposed algorithm, we obtain lung region effectively in chest X-Ray that need in medical image diagnostic system.

• 전자공학회논문지SC
• /
• 제45권3호
• /
• pp.42-50
• /
• 2008

본 논문은 다양한 제품의 불량 검사를 위한 비전 검사시스템을 개발하였다. 대부분의 기존 검사 시스템은 하나의 제품에 대하여 검사가 가능하도록 설계되었다. 그래서 동일한 검사시스템에서 다른 제품을 검사하기 위해서는 비용과 시간을 들여 시스템을 업데이트하거나 교체를 해야 했다. 본 논문에서는 추가적인 작업이 없어도 적은 비용으로 다양한 제품을 검사할 수 있는 유연한 검사시스템을 제안하였다. 이를 위해 사용하기 편리한 사용자 인터페이스와 특별한 변경 없어도 다양한 제품에 적용 가능한 영상처리 알고리즘을 제안하였다. 제안한 알고리즘은 히스토그램의 형태에 따라 제한된 범위 내에서 임계값을 변경하면서 정상제품 이미지와 불량제품 샘플 이미지간의 상관계수를 구하고 구한 상관계수에서 가장 작은 것을 해당 제품의 검사에 사용할 임계값으로 결정한다. 시스템을 검증하기 위해 핸드폰 케이스 불량 검사에 적용하여 Otsu의 방법과 비교하였다.

• 한국지능시스템학회논문지
• /
• 제21권6호
• /
• pp.705-711
• /
• 2011

본 논문은 산업응용을 목표로 효과적인 차량 번호판 인식 알고리즘을 제안한다. 자동차 이미지를 얻은뒤 캐니 에지 추출(Canny Edge Detecting) 알고리즘을 이용하여 연결된 사각형을 찾아 번호판을 추출한다. 추출된 번호판의 색상 정보를 이용하여 흰색/녹색 번호판을 구분하고, 각 번호판을 OTSU 이진화와 주변 전경 픽셀 전파 알고리즘인 CLNF (CCLUF with NFPP)을 통해 문자를 제외한 잡음을 제거하고 레이블링하여 숫자 및 문자 영역을 분리한다. 분리된 문자 영역은 메쉬 방법 및 세선화 후 X-Y 투영 방법으로 특징 벡터를 추출한다. 추출된 특징 벡터는 역전파 신경망으로 미리 학습된 가중치 값과 비교되며, 최종 문자 인식을 수행한다. 제안된 차량 번호판 인식 알고리즘의 효과적 동작은 실험을 통해 확인하였다.

• 대한의용생체공학회:의공학회지
• /
• 제38권6호
• /
• pp.295-301
• /
• 2017

In this study, We subtracted the calcification blooming artifact from MDCT images of coronary atherosclerosis patients and verified their accuracy and usefulness. We performed coronary artery calcification stenosis phantom and a program to subtract calcification blooming artifact by applying 8 different image segmentation method (Otsu, Sobel, Prewitt, Canny, DoG, Region Growing, Gaussian+K-mean clustering, Otsu+DoG). As a result, In the coronary artery calcification stenosis phantom with the lumen region 5 mm the calcification blooming artifact was subtracted in the application of the mixture of Gaussian filtering and K- Clustering algorithm, and the value was close to the actual calcification region. These results may help to accurately diagnose coronary artery calcification stenosis.

• Journal of Biosystems Engineering
• /
• 제38권2호
• /
• pp.149-162
• /
• 2013

Purpose: In image segmentation via thresholding, Otsu and Kapur methods have been widely used because of their effectiveness and robustness. However, computational complexity of these methods grows exponentially as the number of thresholds increases due to the exhaustive search characteristics. Methods: Particle swarm optimization (PSO) and genetic algorithms (GAs) can accelerate the computation. Both methods, however, also have some drawbacks including slow convergence and ease of being trapped in a local optimum instead of a global optimum. To overcome these difficulties, we proposed two new multi-level thresholding methods based on Bacteria Foraging PSO (BFPSO) and real-coded GA algorithms for fast segmentation. Results: The results from BFPSO and real-coded GA methods were compared with each other and also compared with the results obtained from the Otsu and Kapur methods. Conclusions: The proposed methods were computationally efficient and showed the excellent accuracy and stability. Results of the proposed methods were demonstrated using four real images.

• 전자공학회논문지B
• /
• 제33B권4호
• /
• pp.101-110
• /
• 1996

Color image quantization is a process of selecting a set of colors to display an image with some representative colors without noticeable perceived difference. It is very important in many applications to display a true color image in a low cost color monitor or printer. the basic problem is how to display 224 colors with 256 or less colors, called color palette. In this paper, we propose an algorithm to design the 256 or less size color palette by using spatial maskin geffect of HVS and subjective distortion measure weighted by color palette by using spatial masking effect of HVS and subjective distortion measure weighted by color activity in 4*4 local region in any color image. The proposed algorithm consists of octal prequantization and subdivision quantization processing step using the distortion measure and modified Otsu's between class variance maximization method. The experimental results show that the proposed algorithm has higher visual quality and needs less consuming time than conventional algorithms.

• 한국멀티미디어학회논문지
• /
• 제7권9호
• /
• pp.1240-1245
• /
• 2004

본 논문에서는 움직임 영역의 추적 및 움직임 물체의 추출을 위한 알고리즘을 제안한다. 제안한 알고리즘에서는 카메라의 움직임이 고정되어있는 감시카메라나 비디오폰과 같은, 배경이 고정된 시스템으로 가정하였다. 제안된 움직임 영역검색 알고리즘을 이용하여 움직임부분을 먼저 찾은 후, 움직임영역 안에서 다시 움직임 물체만을 분할하는 기법을 제안하였다. 제안한 알고리즘은 노이즈에 대해 보다 강인한 특성을 가지며 움직임영역의 추적 및 추출이 효율적으로 수행되었다.

• 한국멀티미디어학회논문지
• /
• 제20권6호
• /
• pp.845-852
• /
• 2017

In this paper, we propose a binarization algorithm using LVQ-Merge clustering method for fast and accurate extraction of cells from cell images. The proposed method clusters pixel data of a given image by using LVQ to remove noise and divides the result into two clusters by applying a hierarchical clustering algorithm to improve the accuracy of binarization. As a result, the execution speed is somewhat slower than that of the conventional LVQ or Otsu algorithm. However, the results of the binarization have very good quality and are almost identical to those judged by the human eye. Especially, the bigger and the more complex the image, the better the binarization quality. This suggests that the proposed method is a useful method for medical image processing field where high-resolution and huge medical images must be processed in real time. In addition, this method is possible to have many clusters instead of two cluster, so it can be used as a method to complement a hierarchical clustering algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4866-4888
• /
• 2020

One major and time-consuming task in fish production is obtaining an accurate estimate of the number of fish produced. In most Nigerian farms, fish counting is performed manually. Digital image processing (DIP) is an inexpensive solution, but its accuracy is affected by noise, overlapping fish, and interfering objects. This study developed a catfish recognition and counting algorithm that introduces detection before counting and consists of six steps: image acquisition, pre-processing, segmentation, feature extraction, recognition, and counting. Images were acquired and pre-processed. The segmentation was performed by applying three methods: image binarization using Otsu thresholding, morphological operations using fill hole, dilation, and opening operations, and boundary segmentation using edge detection. The boundary features were extracted using a chain code algorithm and Fourier descriptors (CH-FD), which were used to train an artificial neural network (ANN) to perform the recognition. The new counting approach, based on the geometry of the fish, was applied to determine the number of fish and was found to be suitable for counting fish of any size and handling overlap. The accuracies of the segmentation algorithm, boundary pixel and Fourier descriptors (BD-FD), and the proposed CH-FD method were 90.34%, 96.6%, and 100% respectively. The proposed counting algorithm demonstrated 100% accuracy.

• Journal of the Optical Society of Korea
• /
• 제17권2호
• /
• pp.188-199
• /
• 2013

This paper presents a novel algorithm for nighttime detection of the lane markers painted on a road at night. First of all, the proposed algorithm uses neighborhood average filtering, 8-directional Sobel operator and thresholding segmentation based on OTSU's to handle raw lane images taken from a digital CCD camera. Secondly, combining intensity map and gradient map, we analyze the distribution features of pixels on boundaries of lanes in the nighttime and construct 4 feature sets for these points, which are helpful to supply with sufficient data related to lane boundaries to detect lane markers much more robustly. Then, the searching method in multiple directions- horizontal, vertical and diagonal directions, is conducted to eliminate the noise points on lane boundaries. Adapted Hough transformation is utilized to obtain the feature parameters related to the lane edge. The proposed algorithm can not only significantly improve detection performance for the lane marker, but it requires less computational power. Finally, the algorithm is proved to be reliable and robust in lane detection in a nighttime scenario.