• Journal of the Korean Society of Industry Convergence
• /
• v.3 no.4
• /
• pp.361-367
• /
• 2000

This paper proposes an efficient feature extraction of the image data using nonlinear principal component analysis neural networks of a new learning algorithm. The proposed method is a learning algorithm with momentum for reflecting the past trends. It is to get the better performance by restraining an oscillation due to converge the global optimum. The proposed algorithm has been applied to the cancer image of $256{\times}256$ pixels and the coin image of $128{\times}128$ pixels respectively. The simulation results show that the proposed algorithm has better performances of the convergence and the nonlinear feature extraction, in comparison with those using the backpropagation and the conventional nonlinear PCA neural networks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.9
• /
• pp.3177-3195
• /
• 2014

In many moving object detection problems of an aerial video, accurate and robust stabilization is of critical importance. In this paper, a novel accurate image alignment algorithm for aerial electronic image stabilization (EIS) is described. The feature points are first selected using optimal derivative filters based Harris detector, which can improve differentiation accuracy and obtain the precise coordinates of feature points. Then we choose the Delaunay Triangulation edges to find the matching pairs between feature points in overlapping images. The most "useful" matching points that belong to the background are used to find the global transformation parameters using the projective invariant. Finally, intentional motion of the camera is accumulated for correction by Sage-Husa adaptive filtering. Experiment results illustrate that the proposed algorithm is applied to the aerial captured video sequences with various dynamic scenes for performance demonstrations.

• Korean Journal of Remote Sensing
• /
• v.20 no.3
• /
• pp.207-214
• /
• 2004

This study focused on providing a methodology to utilize temporal information obtained from remotely sensed data for monitoring a wide variety of targets on the earth's surface. Generally, a methodology in understanding of global changes is composed of mapping, quantifying, and monitoring changes in the physical characteristics of land cover. The selected processing and analysis technique affects the quality of the obtained information. In this research, feature extraction methodology is proposed based on segmentation. It requires a series of processing of multitempotal images: preprocessing of geometric and radiometric correction, image subtraction/thresholding technique, and segmentation/thresholding. It results in the mapping of the change-detected areas. Here, the appropriate methods are studied for each step and especially, in segmentation process, a method to delineate the exact boundaries of features is investigated in multiresolution framework to reduce computational complexity for multitemporal images of large size.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2003.11a
• /
• pp.201-206
• /
• 2003

In clinical practice, CT Angiography is a powerful technique for the visualziation of blood flow in arterial vessels throughout the body. However CT Angiography images of blood vessels anywhere in the body may be fuzzy if the patient moves during the exam. In this paper, we propose a novel technique for removing global motion artifacts in the 3D space. The proposed methods are based on the two key ideas as follows. First, the method involves the extraction of a set of feature points by using a 3D edge detection technique based on image gradient of the mask volume where enhanced vessels cannot be expected to appear, Second, the corresponding set of feature points in the contrast volume are determined by correlation-based registration. The proposed method has been successfully applied to pre- and post-contrast CTA brain dataset. Since the registration for motion correction estimates correlation between feature points extracted from skull area in mask and contrast volume, it offers an accelerated technique to accurately visualize blood vessels of the brain.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.5
• /
• pp.960-966
• /
• 2017

In this paper, we proposed an algorithm that can extract lesion by inputting a medical image. Feature points are extracted using SIFT algorithm to extract genetic training of medical image. To increase the intensity of the feature points, the input image and that raining image are matched using vector similarity and the lesion is extracted. The vector similarity match can quickly lead to lesions. Since the direction vector is generated from the local feature point pair, the direction itself only shows the local feature, but it has the advantage of comparing the similarity between the other vectors existing between the two images and expanding to the global feature. The experimental results show that the lesion matching error rate is 1.02% and the processing speed is improved by about 40% compared to the case of not using the feature point intensity information.

• Korea Trade Review
• /
• v.44 no.2
• /
• pp.269-282
• /
• 2019

This study analyzes the effects of participation in the global production network on the income inequality using panel data from 2005 to 2016 for 63 countries. In this study were used fixed effects model with autocorrelation, random effect model with autocorrelation and the GLS method. Results are as follows: First, the economic development level supports the Kuznets hypothesis. And then, the forward participation in global value chains increased income inequality, and the backward participation decreased income inequality. In order to derive more detailed estimation results, we analyzed OECD countries and non-OECD countries. First, OECD countries featured decreased, but increased beyond a certain level as a U-shaped curve, that did not support the Kuznets hypothesis. In contrast, non-OECD countries followed the Kuznets U-curve. Second, participation in the global production network showed that both OECD and non-OECD countries featured increased income inequality. In contrast, backward participation appears to mitigate income inequality both in OECD and non-OECD countries. Finally, the ratio of labor and capital is significant in mitigating income inequality in non-OECD countries in which they feature backward participation in production networks. This can be interpreted as developing economies participate in the global production network due to increased capital accumulation and increased the labor productivity.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1
• /
• pp.13-21
• /
• 1995

In this paper, we improve an image classifier algorithm based on neural network learning. It consists of two steps. The first is input pattern generation and the second, the global neural network implementation using an improved back-propagation algorithm. The feature vector for pattern recognition consists of the codebook data obtained from self-organization feature map learning. It decreases the input neuron number as well as the computational cost. The global neural network algorithm which is used in classifier inserts a control part and an address memory part to the back-propagation algorithm to control weights and unit-offsets. The simulation results show that it does not fall into the local minima and can implement easily the large-scale neural network. And it decreases largely the learning time.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.406-412
• /
• 2022

Scene classification of very high-resolution (VHR) imagery can attribute semantics to land cover in a variety of domains. Real-world application requirements have not been addressed by conventional techniques for remote sensing image classification. Recent research has demonstrated that deep convolutional neural networks (CNNs) are effective at extracting features due to their strong feature extraction capabilities. In order to improve classification performance, these approaches rely primarily on semantic information. Since the abstract and global semantic information makes it difficult for the network to correctly classify scene images with similar structures and high interclass similarity, it achieves a low classification accuracy. We propose a VHR remote sensing image classification model that uses extracts the global feature from the original VHR image using an EfficientNet-V2L CNN pre-trained to detect similar classes. The image is then classified using a multilayer perceptron (MLP). This method was evaluated using two benchmark remote sensing datasets: the 21-class UC Merced, and the 38-class PatternNet. As compared to other state-of-the-art models, the proposed model significantly improves performance.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.443-446
• /
• 2005

본 논문에서는 패턴 분류문제에서 특징의 분포와 빈도를 고려하는 FMM(Fuzzy Min-Max) 신경망 구조와 이를 이용한 특징 분석 기법을 소개한다. 이는 기존의 모델에서 균일한 가중치를 고려했을때 비정상적 학습데이터에 학습 효과가 민감하게 왜곡되는 현상을 방지한다. 또한 학습된 신경망으로부터 각 특징의 중요도를 분석할 수 있게 한다. 본 연구에서는 제안된 모델의 특성을 소개하고 특징 값과 하이퍼박스 간의 관계로부터 특징의 연관도 요소, 중요도 평가 및 특징의 서열화 기법을 제시한다. 이는 패턴 분류 신경망의 노드수를 최적화 함으로써 학습 및 분류 과정에서 연산의 효율성을 증대시킨다.

• Journal of the Korean Society for Precision Engineering
• /
• v.25 no.4
• /
• pp.69-76
• /
• 2008

The self-organizing feature map(SOFM) among a number of neural network uses a randomized small valued initial weight vectors, selects the neuron whose weight vector best matches input as the winning neuron, and trains the weight vectors such that neurons within the activity bubble are moved toward the input vector. On the other hand, the modified method in this research uses a predetermined initial weight vectors of the 1-dimensional string, gives the systematic input vector whose position best matches obstacles, and trains the weight vectors such that neurons within the activity bubble are move toward the opposite direction of input vector. According to simulation results one can conclude that the method using string and the modified neural network is useful tool to mobile robot for the global path planning.