• 정보과학회 논문지
• /
• 제44권12호
• /
• pp.1313-1318
• /
• 2017

다수의 지역 특징들을 취합하여 하나의 벡터로 표현하는 것은 이미지 검색의 핵심 기술이다. 이 과정에서 경사도 기반 특징에 비해 수십 배 빠르게 추출되는 2진 특징이 활용된다면 이미지 검색의 고속화가 가능하다. 이를 위해서는 2진 특징들을 군집하여 2진 시각 단어를 생성하는 기법에 대한 연구가 선행되어야 한다. 기존의 경사도 기반 특징들을 군집하는 전통적인 방식으로는 2진 특징들을 군집할 수 없기 때문이다. 이를 위해 본 논문은 2진 특징들을 군집하여 2진 시각 단어를 생성하는 기법들에 대해 연구한다. 실험을 통해 2진 특징의 활용이 이미지 검색에 미치는 정확도와 연산효율 사이의 상충관계에 대해 분석한 후, 제안한 기법들을 비교한다. 본 연구는 고속 이미지 검색을 필요로 하는 모바일 응용, 리얼 타임 응용, 웹 스케일 응용 등에 활용될 것으로 기대된다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권7호
• /
• pp.911-921
• /
• 2004

지문영상으로부터 특징점을 정확하게 추출하는 것은 효과적인 지문인식 시스템의 구축에 매우 중요하다. 하지만 지문영상의 품질에 따라 특징점 추출의 정확도가 달라지기 때문에 지문인식 시스템에서의 영상 전처리 과정은 시스템의 성능에 크게 영향을 미친다. 본 논문에서는 지문영상으로부터 명암값의 평균 및 분산, 블록 방향성 차, 방향성 변화도, 융선과 골의 두께 비율 등의 5가지 특징을 추출하고 계층적 클러스터링 알고리즘으로 클러스터링하여 영상의 품질 특성을 분석한 후 습성(oily), 보통(neutral), 건성(dry)의 특성에 적합하게 영상을 개선하는 지식기반 전처리 방법을 제안한다. NIST DB 4와 인하대학교 데이타를 이용하여 실험한 결과, 클러스터링 기법이 영상의 특성을 제대로 구분함을 확인할 수 있었다. 또한 제안한 방법의 성능 평가를 위해 품질 지수와 블록 방향성 차이를 측정하여 일반적인 전처리 방법보다 지식기반 전처리 방법이 품질 지수와 블록 방향성 차이를 향상시킴을 확인할 수 있었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(4)
• /
• pp.195-198
• /
• 2000

Fractal image compression can reduce the size of image data by contractive mapping of original image. The mapping is affine transformation to find the block(called range block) which is the most similar to the original image. Fractal is very efficient way to reduce the data size. However, it has high distortion rate and requires long encoding time. In this paper, we present the simulation result of fractal and VQ hybrid systems which use different clustering algorithms, normal and improved competitive learning SOFM. The simulation results showed that the VQ hybrid fractal using improved competitive learning SOFM has better distortion rate than the VQ hybrid fractal using normal SOFM.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2000년도 추계학술대회 학술발표 논문집
• /
• pp.81-84
• /
• 2000

Fractal image compression can reduce the size of image data by contractive mapping of original image. The mapping is affine transformation to find the block(called range block) which is the most similar to the original image. Fractal is very efficient way to reduce the data size. However, it has high distortion rate and requires long encoding time. In this paper, we present the simulation result of fractal and VQ hybrid systems which use different clustering algorithms, normal and improved competitive learning SOFM. The simulation results showed that the VQ hybrid fractal using improved competitive learning SOFM has better distortion rate than the VQ hybrid fractal using normal SOFM.

• Journal of Biosystems Engineering
• /
• 제35권2호
• /
• pp.138-145
• /
• 2010

An on-line algorithm that discriminates brown rice kernels on their echelon feeder using color image processing is presented for quality inspection. A rapid color image segmentation algorithm based on Bayesian clustering method was developed by means of the look-up table which was made from the significant clusters selected by experts. A robust estimation method was presented to improve the stability of color clusters. Discriminant analysis of color distributions was employed to distinguish nine types of brown rice kernels. Discrimination accuracies of the on-line discrimination algorithm were ranged from 72% to 85% for the sound, cracked, green-transparent and green-opaque, greater than 93% for colored, red, and unhulled, about 92% for white-opaque and 67% for chalky, respectively.

• 전자공학회논문지B
• /
• 제28B권10호
• /
• pp.842-913
• /
• 1991

The automatic target detection which automatically identifies the location of the target with its input image is one of the significant subjects of image processing field. Then, there are some problems that should be solved to detect the target automatically from the input image. First of all, the ambiguity of the boundary between targets or between a target and background should be solved and the target should be searched adaptively. In other words, the target should be identified by the relative brightness to the background, not by the absolute brightness. In this paper, to solve these problems, a new algorithm which can identify the target automatically is proposed. This algorithm uses the set of fuzzy for solving the ambiguity between the boundaries, and using the weight according to the brightness of data in the input image, the target is identified adaptively by the relative brightness to the background. Applying this algorithm to real images, it is experimentally proved that it is can be effectively applied to the automatic target detection.

• 한국빅데이터학회지
• /
• 제1권1호
• /
• pp.19-22
• /
• 2016

최근 IT 기술을 활용하여 농작물의 병충해 조기 진단에 관한 연구가 활발히 진행되고 있다. 본 논문은 카메라 센서를 통해 받아온 작물의 잎사귀 이미지를 분석하여 병충해를 조기에 감지할 수 있는 이미지 프로세싱 기법에 대해 논한다. 본 논문은 개선된 K 평균 클러스터링 방법을 활용하여 잎사귀 질병 감염 여부를 진단하는 알고리즘을 제안한다. 잎사귀 감염 분류 실험을 통해, 제안한 알고리즘이 정성적인 평가에서 더 좋은 성능을 나타낸 것으로 분석되었다.

• 한국군사과학기술학회지
• /
• 제8권2호
• /
• pp.14-21
• /
• 2005

This paper describes the system for detecting the tank crew's(loader's) hand, arm, head and the upper half of the body in a danger area between the turret ceiling and the upper breech mechanism by computer vision-based method. This system informs danger of pressed to death to gunner and commander for the safety of operating mission. The camera mounted ort the top portion of the turret ceiling. The system sets search moving object from this image and detects by using change of image, laplacian operator and clustering algorithm in this area. It alarms the tank crews when it's judged that dangerous situation for operating mission. The result In this experiment shows that the detection rate maintains in $81{\sim}98$ percents.

• 융합신호처리학회논문지
• /
• 제16권1호
• /
• pp.9-14
• /
• 2015

Outlier detection and removal is a crucial step needed for various image processing applications such as image registration. Random Sample Consensus (RANSAC) is known to be the best algorithm so far for the outlier detection and removal. However RANSAC requires a cosiderable computation time. To drastically reduce the computation time while preserving the comparable quality, a outlier detection and removal method based on modified K-means is proposed. The original K-means was conducted first for matching point pairs and then cluster merging and member exclusion step are performed in the modification step. We applied the methods to various images with highly repetitive patterns under several geometric distortions and obtained successful results. We compared the proposed method with RANSAC and showed that the proposed method runs 3~10 times faster than RANSAC.

• 한국컴퓨터정보학회논문지
• /
• 제23권12호
• /
• pp.35-41
• /
• 2018

In this paper, we propose a swarm-based possibilistic c-means(PCM) algorithm in order to overcome the problems of PCM, which are sensitiveness of clustering performance due to initial cluster center's values and producing coincident or close clusters. To settle the former problem of PCM, we adopt a swam-based global optimization method which can be provided the optimal initial cluster centers. Furthermore, to settle the latter problem of PCM, we design an adaptive thresholding model based on the optimized cluster centers that yields preliminary clustered and un-clustered dataset. The preliminary clustered dataset plays a role of preventing coincident or close clusters and the un-clustered dataset is lastly clustered by PCM. From the experiment, the proposed method obtains a better performance than other PCM algorithms on a simulated magnetic resonance(MR) brain image dataset which is corrupted by various noises and bias-fields.