• 대한원격탐사학회지
• /
• 제16권2호
• /
• pp.145-156
• /
• 2000

Clustering is the process of partitioning a data set into meaningful clusters. As the data to process increase, a laster algorithm is required than ever. In this paper, we propose a clustering algorithm to partition a multispectral remotely sensed image data set into several clusters using a hash search algorithm. The processing time of our algorithm is compared with that of clusters algorithm using other speed-up concepts. The experiment results are compared with respect to the number of bands, the number of clusters and the size of data. It is also showed that the processing time of our algorithm is shorter than that of cluster algorithms using other speed-up concepts when the size of data is relatively large.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제27권2호
• /
• pp.146-159
• /
• 2023

This paper proposes a hybrid algorithm combining K-means clustering and watershed algorithms for flower segmentation and counting. We use the K-means clustering algorithm to obtain the main colors in a complex background according to the cluster centers and then take a color space transformation to extract pixel values for the hue, saturation, and value of flower color. Next, we apply the threshold segmentation technique to segment flowers precisely and obtain the binary image of flowers. Based on this, we take the Euclidean distance transformation to obtain the distance map and apply it to find the local maxima of the connected components. Afterward, the proposed algorithm adaptively determines a minimum distance between each peak and apply it to label connected components using the watershed segmentation with eight-connectivity. On a dataset of 30 images, the test results reveal that the proposed method is more efficient and precise for the counting of overlapped flowers ignoring the degree of overlap, number of overlap, and relatively irregular shape.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권1호
• /
• pp.288-307
• /
• 2016

Image distortions are typically characterized by degradations of structures. Dictionaries learned from natural images can capture the underlying structures in images, which are important for image quality assessment (IQA). This paper presents a general-purpose no-reference image quality metric using a GRadient-Induced Dictionary (GRID). A dictionary is first constructed based on gradients of natural images using K-means clustering. Then image features are extracted using the dictionary based on Euclidean-norm coding and max-pooling. A distortion classification model and several distortion-specific quality regression models are trained using the support vector machine (SVM) by combining image features with distortion types and subjective scores, respectively. To evaluate the quality of a test image, the distortion classification model is used to determine the probabilities that the image belongs to different kinds of distortions, while the regression models are used to predict the corresponding distortion-specific quality scores. Finally, an overall quality score is computed as the probability-weighted distortion-specific quality scores. The proposed metric can evaluate image quality accurately and efficiently using a small dictionary. The performance of the proposed method is verified on public image quality databases. Experimental results demonstrate that the proposed metric can generate quality scores highly consistent with human perception, and it outperforms the state-of-the-arts.

• 한국멀티미디어학회논문지
• /
• 제13권1호
• /
• pp.47-57
• /
• 2010

객체 검출은 영상에서 객체의 식별, 위치정보, 상황인식 등을 위해서 필수적이다. 본 논문에서는 강인한 객체 검출 시스템을 제안한다. Principal Component Analysis (PCA)를 이용하여 배경 영상에서 수집한 학습데이터를 주성분으로 선형변환 한다. 객체와 배경에 대하여 판별 능력이 우수한 주성분을 선별하여 Eigen-background를 구성한다. Fuzzy-C-Means (FCM)은 Eigen-background의 정보를 입력 차원으로 하여 영상을 Clustering하고 객체와 배경으로 분류한다. 고정된 카메라에서 배경변화에 적용 가능한 시스템을 구현하기 위해 동일한 시점에서 움직이는 객체가 포함된 영상을 학습데이터로 사용하였다. 제안하는 시스템은 인위적인 한 프레임을 배경으로 정의하여 사용하는 과정이 필요 없이 입력 영상에서 잡음이 제거된 객체와 배경으로 분류하였고, 또한 객체의 부분적인 움직임도 효과적으로 검출하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.681-684
• /
• 2021

In this paper, we study image clustering without labeling using machine learning techniques. We proposed an unsupervised machine learning technique to design an image clustering model that automatically categorizes images into groups. Our experiment focused on inception convolutional neural networks (inception V3) with k-mean methods to cluster images. For this, we collect the public datasets containing Food-K5, Flowers, Handwritten Digit, Cats-dogs, and our dataset Rice Germination, and the owner dataset Palm print. Our experiment can expand into three-part; First, format all the images to un-label and move to whole datasets. Second, load dataset into the inception V3 extraction image features and transferred to the k-mean cluster group hold on six classes. Lastly, evaluate modeling accuracy using the confusion matrix base on precision, recall, F1 to analyze. In this our methods, we can get the results as 1) Handwritten Digit (precision = 1.000, recall = 1.000, F1 = 1.00), 2) Food-K5 (precision = 0.975, recall = 0.945, F1 = 0.96), 3) Palm print (precision = 1.000, recall = 0.999, F1 = 1.00), 4) Cats-dogs (precision = 0.997, recall = 0.475, F1 = 0.64), 5) Flowers (precision = 0.610, recall = 0.982, F1 = 0.75), and our dataset 6) Rice Germination (precision = 0.997, recall = 0.943, F1 = 0.97). Our experiment showed that modeling could get an accuracy rate of 0.8908; the outcomes state that the proposed model is strongest enough to differentiate the different images and classify them into clusters.

• 한국식품영양과학회지
• /
• 제46권3호
• /
• pp.374-380
• /
• 2017

본 연구에서는 건해삼의 수화도에 따른 등급 분류를 확립하고자 하였다. 건해삼은 영상분석을 통하여 건해삼의 길이, 너비, 부피, 겉넓이의 형태학적 특징을 추출하였다. 측정된 data를 이용하여 k-mean clustering을 실시, 95개의 건해삼을 3개의 등급으로 분류하여 $30^{\circ}C$에서 40시간 수화실험을 실시하였다. 건해삼의 k-mean clustering을 실시한 결과 건해삼의 부피와 겉넓이는 건해삼의 등급을 가장 잘 나타낼 수 있는 인자였다. 등급별 수분 함량은 grade1은 71.23%, grade2는 75.60%, grade3는 85.62%를 확인하였다. 본 수화속도의 차이는 등급별 해삼이 동일한 수화 flux를 갖는 것을 고려하였을 때, 해삼의 수화는 겉넓이에 지배적임을 확인할 수 있다. 해삼의 수화는 물의 물질전달을 통해 이루어지며 Fick의 확산법칙에 따라 겉넓이가 커질수록 물질전달 속도가 증가함을 본 연구의 수화실험 결과에서도 확인할 수 있었다. 본 연구에서는 건해삼의 등급을 분류하여 최적의 수분 함량(75%)을 충족하기 위한 등급별 수화시간을 도출하였다. 본 연구에서 도출된 건해삼의 등급판별은 "수화도에 따른 건해삼의 품질 변화"에 대한 추가적인 연구를 통해 등급별 최적의 수화시간의 도출이 가능하다.

• 전기전자학회논문지
• /
• 제12권3호
• /
• pp.158-166
• /
• 2008

의용 초음파 장비는 X-Ray, CT, MRI 등 다른 의료 장비보다 휴대성과 안전성면에서는 장점이 있지만 진단 시 해상도와 화질 저하를 유발하는 스펙클이 생기는 단점이 있다. 그러나 단순한 스펙클 잡음의 제거는 경계선 정보의 손실을 발생시킬 수도 있다. 이에 본 논문에서는 효과적인 스펙클 제거와 손실 없는 경계선 검출을 위해 뉴럴네트워크와 퍼지 클러스터링을 이용한 뉴로-퍼지 스펙클 제거 방법을 제안하였다. 제안된 방법은 입력된 의용 초음파 영상에 대해 먼저 퍼지 클러스터링을 적용하여 세 영역으로 나누고 이후 각 영역별로 별도의 뉴럴 네트워크를 적용하는 방법이다. 실제 실험 및 기존 방법들과의 정성적?정량적 비교 분석을 통해 제안 방법의 유용성을 검증하였다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권4호
• /
• pp.246-253
• /
• 2016

Infrared (IR) imaging has been researched for various applications such as surveillance. IR radiation has the capability to detect thermal characteristics of objects under low-light conditions. However, automatic segmentation for finding the object of interest would be challenging since the IR detector often provides the low spatial and contrast resolution image without color and texture information. Another hindrance is that the image can be degraded by noise and clutters. This paper proposes multi-level segmentation for extracting regions of interest (ROIs) and objects of interest (OOIs) in the IR scene. Each level of the multi-level segmentation is composed of a k-means clustering algorithm, an expectation-maximization (EM) algorithm, and a decision process. The k-means clustering initializes the parameters of the Gaussian mixture model (GMM), and the EM algorithm estimates those parameters iteratively. During the multi-level segmentation, the area extracted at one level becomes the input to the next level segmentation. Thus, the segmentation is consecutively performed narrowing the area to be processed. The foreground objects are individually extracted from the final ROI windows. In the experiments, the effectiveness of the proposed method is demonstrated using several IR images, in which human subjects are captured at a long distance. The average probability of error is shown to be lower than that obtained from other conventional methods such as Gonzalez, Otsu, k-means, and EM methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권11호
• /
• pp.5692-5716
• /
• 2019

One of the best means to safeguard the confidentiality, security, and privacy of an image within the IoT-Cloud is through encryption. However, looking through encrypted data is a difficult process. Several techniques for searching encrypted data have been devised, but certain security solutions may not be used in IoT-Cloud because such solutions are not lightweight. We propose a lightweight scheme that can perform a content-based search of encrypted images, namely EEIRI. In this scheme, the images are represented using local features. We develop and validate a secure scheme for measuring the Euclidean distance between two descriptor sets. To improve the search efficiency, we employ the k-means clustering technique to construct a searchable tree-based index. Our index construction process ensures the privacy of the stored data and search requests. When compared with more familiar techniques of searching images over plaintexts, EEIRI is considered to be more efficient, demonstrating a higher search cost of 7% and a decrease in search accuracy of 1.7%. Numerous empirical investigations are carried out in relation to real image collections so as to evidence our work.

• 방송공학회논문지
• /
• 제3권1호
• /
• pp.50-60
• /
• 1998

본 논문에서는 콤팩트한 동영상 표현과 객체기반의 generic한 동영상압축을 위한 파라미터릭 움직임 모델의 파라미터 추정과 세그맨테이션 기법에 관해서 기술한다. 동영상의 optical flow와 같은 국소적 움직임 정보와 파라미터 움직임 모델의 특징을 이용해서 영상의 콤팩트한 구조적 표현을 추출하기 위해, 본 논문에서는 2 스템의 과정 즉, 초기영역을 추출하는 과정과, 파라미터릭 움직임 파라미터의 추정과 세그맨테이션을 동시에 수행하는 과정으로 구성된 새로운 알고리즘을 제안한다. 혼합 모델이 ML 추정에 의거한 확률적 클러스터링에 의해 움직임 물체의 움직임과 형상을 반영한 초기영역을 추출하고, 파라미터릭 움직임 모델을 사용해서 각각의 초기 영역마다 움직임 파라미터를 추정하고 세그맨테이션을 수행한다. 또한, CIF 표준 동영상을 사용한 모의 실험을 통해 본 제안 알고리즘의 유효성을 평가한다.