• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.709-714
• /
• 2002

This paper discussed and analyzed results of different classification algorithms for land use classification in arid and semiarid areas using CBERS-1 image, which in case of our study is Shihezi Municipality, Xinjiang Province. Three types of classifiers are included in our experiment, including the Maximum Likelihood classifier, BP neural network classifier and Fuzzy-ARTMAP neural network classifier. The classification results showed that the classification accuracy of Fuzzy-ARTMAP was the best among three classifiers, increased by 10.69% and 6.84% than Maximum likelihood and BP neural network, respectively. Meanwhile, the result also confirmed the practicability of CBERS-1 image in land use survey.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권5호
• /
• pp.2607-2627
• /
• 2017

Nonnegative matrix factorization (NMF) has received considerable attention due to its effectiveness of reducing high dimensional data and importance of producing a parts-based image representation. Most of existing NMF variants attempt to address the assertion that the observed data distribute on a nonlinear low-dimensional manifold. However, recent research results showed that not only the observed data but also the features lie on the low-dimensional manifolds. In addition, a few hard priori label information is available and thus helps to uncover the intrinsic geometrical and discriminative structures of the data space. Motivated by the two aspects above mentioned, we propose a novel algorithm to enhance the effectiveness of image representation, called Dual graph-regularized Constrained Nonnegative Matrix Factorization (DCNMF). The underlying philosophy of the proposed method is that it not only considers the geometric structures of the data manifold and the feature manifold simultaneously, but also mines valuable information from a few known labeled examples. These schemes will improve the performance of image representation and thus enhance the effectiveness of image classification. Extensive experiments on common benchmarks demonstrated that DCNMF has its superiority in image classification compared with state-of-the-art methods.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2003년도 추계 학술발표회 논문집
• /
• pp.155-159
• /
• 2003

최근 들어 SVM(support vector machines)은 기계학습의 분야에서 많은 응용이 이루어지고 있으며 특히 분류(classification)나 회귀(regression)분석의 영역에서 많은 연구가 진행중이다. 본 논문에서는 SVM을 이용하여 입력영상자료(image data)를 분류하고자 한다. RGB 컬러 영상자료가 입력되면 이미지 크기에 관계없이 이미지 자체를 입력패턴으로 인식하고 SVM을 통한 훈련(training)을 거친 결과(weight 들과 bias 추정치)를 이용하여 입력영상자료가 사람인가를 분류할 수 있는 문제를 다룬다. 제안된 방법의 타당성은 152개의 영상자료에 적용하여 분석되었다.

• 한국농공학회논문집
• /
• 제57권6호
• /
• pp.91-97
• /
• 2015

The Unmanned Aerial Vehicles (UAVs) have several advantages over conventional RS techniques. They can acquire high-resolution images quickly and repeatedly. And with a comparatively lower flight altitude i.e. 80~400 m, they can obtain good quality images even in cloudy weather. Therefore, they are ideal for acquiring spatial data in cases of small agricultural field with mixed crop, abundant in South Korea. This paper discuss the use of low cost UAV based remote sensing for classifying crops. The study area, Gochang is produced by several crops such as red pepper, radish, Chinese cabbage, rubus coreanus, welsh onion, bean in South Korea. This study acquired images using fixed wing UAV on September 23, 2014. An object-based technique is used for classification of crops. The results showed that scale 250, shape 0.1, color 0.9, compactness 0.5 and smoothness 0.5 were the optimum parameter values in image segmentation. As a result, the kappa coefficient was 0.82 and the overall accuracy of classification was 85.0 %. The result of the present study validate our attempts for crop classification using high resolution UAV image as well as established the possibility of using such remote sensing techniques widely to resolve the difficulty of remote sensing data acquisition in agricultural sector.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권7호
• /
• pp.3172-3193
• /
• 2018

Recently, several studies have shown that linear representation based approaches are very effective and efficient for image classification. One of these linear-representation-based approaches is the Collaborative representation (CR) method. The existing algorithms based on CR have two major problems that degrade their classification performance. First problem arises due to the limited number of available training samples. The large variations, caused by illumintion and expression changes, among query and training samples leads to poor classification performance. Second problem occurs when an image is partially noised (contiguous occlusion), as some part of the given image become corrupt the classification performance also degrades. We aim to extend the collaborative representation framework under limited training samples face recognition problem. Our proposed solution will generate virtual samples and intra-class variations from training data to model the variations effectively between query and training samples. For robust classification, the image patches have been utilized to compute representation to address partial occlusion as it leads to more accurate classification results. The proposed method computes representation based on local regions in the images as opposed to CR, which computes representation based on global solution involving entire images. Furthermore, the proposed solution also integrates the locality structure into CR, using Euclidian distance between the query and training samples. Intuitively, if the query sample can be represented by selecting its nearest neighbours, lie on a same linear subspace then the resulting representation will be more discriminate and accurately classify the query sample. Hence our proposed framework model the limited sample face recognition problem into sufficient training samples problem using virtual samples and intra-class variations, generated from training samples that will result in improved classification accuracy as evident from experimental results. Moreover, it compute representation based on local image patches for robust classification and is expected to greatly increase the classification performance for face recognition task.

• Communications for Statistical Applications and Methods
• /
• 제29권2호
• /
• pp.161-176
• /
• 2022

There has been active research in image classification using deep learning convolutional neural network (CNN) models. ImageNet large-scale visual recognition challenge (ILSVRC) (2010-2017) was one of the most important competitions that boosted the development of efficient deep learning algorithms. This paper introduces and compares six monumental models that achieved high prediction accuracy in ILSVRC. First, we provide a review of the models to illustrate their unique structure and characteristics of the models. We then compare those models under a unified framework. For this reason, additional devices that are not crucial to the structure are excluded. Four popular data sets with different characteristics are then considered to measure the prediction accuracy. By investigating the characteristics of the data sets and the models being compared, we provide some insight into the architectural features of the models.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제36권8호
• /
• pp.664-672
• /
• 2009

최근 영상 데이터의 효율적인 표현 및 처리를 위해 텐서를 사용하는 연구가 관심을 모으고 있다. 본 연구에서는 2차 텐서로 표현된 데이터를 효과적으로 분류하기 위한 시스템을 개발하는 것을 목적으로 한다. 이를 위해 먼저 일반적인 벡터 데이터에 대해 개발되어진 클래스 요인과 환경 요인으로 이루어진 데이터 생성 모델을 확장하여 2차 텐서로 표현된 영상에 적합한 데이터 생성 모델을 정의하고, 이에 적합한 유사도 함수를 제안하였다. 제안하는 유사도 함수는 행렬정규분포를 이용하여 환경 요인의 확률분포를 추정함으로써 얻을 수 있다. 여러 벤치마크 데이터들을 이용하여 실험한 결과 2차 텐서를 사용함으로써 벡터 형태의 표현방식을 사용하는 것에 비해 분류율이 향상되었음을 확인하였다. 또한 제안하는 유사도 함수가 다른 기존의 유사도 함수에 비해 영상 데이터에 적합함을 확인할 수 있었다.

• 대한원격탐사학회지
• /
• 제19권4호
• /
• pp.329-339
• /
• 2003

본 연구에서는 무감독 영상분류를 위하여 특성이 다른 센서로 수집된 영상들에 대한 의사결정 수준의 영상 융합기법을 제안하였다. 제안된 기법은 공간 확장 분할에 근거한 무감독 계층군집 영상분류기법을 개개의 센서에서 수집된 영상에 독립적으로 적용한 후 그 결과로 생성되는 분할지역의 퍼지 클래스 벡터(fuzzy class vector)를 이용하여 각 센서의 분류 결과를 융합한다. 퍼지 클래스벡터는 분할지역이 각 클래스에 속할 확률을 표시하는 지시(indicator) 벡터로 간주되며 기대 최대화 (EM: Expected Maximization) 추정 법에 의해 관련 변수의 최대 우도 추정치가 반복적으로 계산되어진다. 본 연구에서는 같은 특성의 센서 혹은 밴드 별로 분할과 분류를 수행한 후 분할지역의 분류결과를 퍼지 클래스 벡터를 이용하여 합성하는 접근법을 사용하고 있으므로 일반적으로 다중센서의 영상의 분류기법에 사용하는 화소수준의 영상융합기법에서처럼 서로 다른 센서로부터 수집된 영상의 화소간의 공간적 일치에 대한 높은 정확도를 요구하지 않는다. 본 연구는 한반도 전라북도 북서지역에서 관측된 다중분광 SPOT 영상자료와 AIRSAR 영상자료에 적용한 결과 제안된 영상 융합기법에 의한 피복 분류는 확장 벡터의 접근법에 의한 영상 융합보다 서로 다른 센서로부터 얻어지는 정보를 더욱 적합하게 융합한다는 것을 보여주고 있다.

• 소성∙가공
• /
• 제31권4호
• /
• pp.229-239
• /
• 2022

Convolution Neural Network(CNN) is a class of deep learning algorithms and can be used for image analysis. In particular, it has excellent performance in finding the pattern of images. Therefore, CNN is commonly applied for recognizing, learning and classifying images. In this study, the surface defect classification performance of Al 6061 extruded material using CNN-based algorithms were compared and evaluated. First, the data collection criteria were suggested and a total of 2,024 datasets were prepared. And they were randomly classified into 1,417 learning data and 607 evaluation data. After that, the size and quality of the training data set were improved using data augmentation techniques to increase the performance of deep learning. The CNN-based algorithms used in this study were VGGNet-16, VGGNet-19, ResNet-50 and DenseNet-121. The evaluation of the defect classification performance was made by comparing the accuracy, loss, and learning speed using verification data. The DenseNet-121 algorithm showed better performance than other algorithms with an accuracy of 99.13% and a loss value of 0.037. This was due to the structural characteristics of the DenseNet model, and the information loss was reduced by acquiring information from all previous layers for image identification in this algorithm. Based on the above results, the possibility of machine vision application of CNN-based model for the surface defect classification of Al extruded materials was also discussed.

• Spatial Information Research
• /
• 제11권2호
• /
• pp.101-117
• /
• 2003

고해상도 위성영상분석은 국지적 규모의 토지피복 변화 및 대기 상태의 모니터링을 위한 효과적인 기술로 인식되어 왔다. 본 연구에서는 고해상도 영상인 IKONOS 영상과 기존에 작성된 토지이용도를 이용하여 국지적 규모의 토지피복도를 새로 작성하였다. 토지피복 분류기법으로는 퍼지분류 기법을 사용하였으며, 소속함수의 결합방법으로 minimum 연산자를 이용하였다. 분리도 분석에서는 모든 밴드에서 분리도가 높지 않은데, 원인은 계절적 영향에 따른 분광반사율의 차이 때문이다. 토지피복도 작성결과 육상에서는 침엽수림과 경지가, 해양에서는 간석지 및 해빈의 변화가 가장 크다. 분류의 전체정확도는 95.0%, kappa 계수는 0.94%로 나타나 높은 분류정확도를 보였다. 분류항목별 정확도에서는 대부분의 분류항목이 90% 이상의 분류정확도를 보였다. 그러나 혼합림과 하천 및 저수지 등은 낮은 분류정확도를 보였다. 이들 원인은 농경지 담수로 인하여 수역으로 분류항목이 변하거나 유사한 분광패턴으로 분류항목이 혼재된 결과이다. 이들 분류항목의 분류정확도를 높이기 위해서는 계절적 요인을 반드시 고려하여야 할 것이다. 결론적으로 IKONOS 영상은 토지이용도 작성 및 수정이 가능하며, 추후 GIS 공간자료와 통합하여 토지피복도를 작성한다면 보다 정확한 의사결정 보조 자료로서 유용하게 활용될 수 있을 것이다.