• 제어로봇시스템학회논문지
• /
• 제4권4호
• /
• pp.499-505
• /
• 1998

In developing an automated surface inspect algorithm, we have designed a hierarchical classifier using neural network. The defects which exist on the surface of cold mill strip have a scattering or singular distribution. We have considered three major problems, that is preprocessing, feature extraction and defect classification. In preprocessing, Top-hit transform, adaptive thresholding, thinning and noise rejection are used Especially, Top-hit transform using local minimax operation diminishes the effect of bad lighting. In feature extraction, geometric, moment, co-occurrence matrix, and histogram ratio features are calculated. The histogram ratio feature is taken from the gray-level image. For defect classification, we suggest a hierarchical structure of which nodes are multilayer neural network classifiers. The proposed algorithm reduced error rate by comparing to one-stage structure.

• ETRI Journal
• /
• 제20권3호
• /
• pp.272-283
• /
• 1998

In this paper, we propose efficient content-based image retrieval methods using the automatic extraction of the low-level visual features as image content. Two new feature extraction methods are presented. The first one os an advanced color feature extraction derived from the modification of Stricker's method. The second one is a texture feature extraction using some DCT coefficients which represent some dominant directions and gray level variations of the image. In the experiment with an image database of 200 natural images, the proposed methods show higher performance than other methods. They can be combined into an efficient hierarchical retrieval method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2824-2838
• /
• 2013

There has been a lot of attention paid recently to analyze dynamic human gestures that vary over time. Most attention to dynamic gestures concerns with spatio-temporal features, as compared to analyzing each frame of gestures separately. For accurate dynamic gesture recognition, motion feature extraction algorithms need to find representative features that uniquely identify time-varying gestures. This paper proposes a new feature-extraction algorithm using temporal self-similarity based on a hierarchical human model. Because a conventional temporal self-similarity method computes a whole movement among the continuous frames, the conventional temporal self-similarity method cannot recognize different gestures with the same amount of movement. The proposed model-based temporal self-similarity method groups body parts of a hierarchical model into several sets and calculates movements for each set. While recognition results can depend on how the sets are made, the best way to find optimal sets is to separate frequently used body parts from less-used body parts. Then, we apply a multiclass support vector machine whose optimization algorithm is based on structural support vector machines. In this paper, the effectiveness of the proposed feature extraction algorithm is demonstrated in an application for taebo gesture recognition. We show that the model-based temporal self-similarity method can overcome the shortcomings of the conventional temporal self-similarity method and the recognition results of the model-based method are superior to that of the conventional method.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.99-102
• /
• 2009

In this paper a hierarchical stereo matching algorithm based on feature extraction is proposed. The boundary (edge) as feature point in an image is first obtained by segmenting an image into red, green, blue and white regions. With the obtained boundary information, disparities are extracted by matching window on the image boundary, and the initial disparity map is generated when assigned the same disparity to neighbor pixels. The final disparity map is created with the initial disparity. The regions with the same initial disparity are classified into the regions with the same color and we search the disparity again in each region with the same color by changing block size and search range. The experiment results are evaluated on the Middlebury data set and it show that the proposed algorithm performed better than a phase based algorithm in the sense that only about 14% of the disparities for the entire image are inaccurate in the final disparity map. Furthermore, it was verified that the boundary of each region with the same disparity was clearly distinguished.

• 전자공학회논문지B
• /
• 제29B권11호
• /
• pp.102-110
• /
• 1992

In this paper, a new method of character recognition is proposed. It uses density information, in addition to positional and directional information generally used, to recognize a character. Four directional feature primitives are extracted from the thinning templates on the observation that the output of the templates have directional property in general. A simple and fast feature extraction scheme is possible. Features are organized from recursive nonary tree(N-tree) that corresponds to normalized character area. Each node of the N-tree has four directional features that are sum of the features of it's nine sub-nodes. Every feature primitive from the templates are added to the corresponding leaf and then summed to the upper nodes successively. Recognition can be accomplished by using appropriate feature level of N-tree. Also, effectiveness of each node's feature vector was tested by experiment. A method to implement the proposed feature vector organization algorithm into hardware is proposed as well. The third generation node, which is 4$\times$4, is used as a unit processing element to extract features, and it was implemented in hardware. As a result, we could observe that it is possible to extract feature vector for real-time processing.

• 대한전자공학회논문지SP
• /
• 제39권1호
• /
• pp.9-16
• /
• 2002

본 논문에서는 변이-움직임의 관계와 특징점을 이용하여 계층적으로 3차원 모델을 만드는 새로운 방법을 제안한다. 일반적으로 실제 영상으로부터 3차원 모델을 만들기 위해서는 두 영상 전체의 대응 정보를 이용해서 모델의 노드에 해당하는 부분의 깊이 정보를 구해야 한다. 그러나, 이 작업은 시간이 많이 소요될 뿐만 아니라 정확한 깊이 정보를 얻기가 어렵다. 이러한 문제점을 개선하기 위해 제안하는 방법에서는 전 영상의 대응 정보 없이 특징점에 대한 대응 정보만으로 모델을 구한다. 제안한 방법은 객체의 추출, 추출된 객체 내에서의 특징점 추출, 추출된 특징점을 이용한 계층적 3차원 모델 생성의 세 부분으로 구성되며, 제안한 방법은 3차원 모델 생성시 적은 연산이 소요될 뿐만 아니라 임의의 시각 관점 영상의 생성과 평탄 영역의 평탄성과 경계 영역의 선명성 표현에도 효과적이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권6호
• /
• pp.1657-1673
• /
• 2023

With the advancement of information technology, criminals employ multiple cyberspaces to promote cybercrime. To combat cybercrime and cyber dangers, banks and financial institutions use artificial intelligence (AI). AI technologies assist the banking sector to develop and grow in many ways. Transparency and explanation of AI's ability are required to preserve trust. Deep learning protects client behavior and interest data. Deep learning techniques may anticipate cyber-attack behavior, allowing for secure banking transactions. This proposed approach is based on a user-centric design that safeguards people's private data over banking. Here, initially, the attack data can be generated over banking transactions. Routing is done for the configuration of the nodes. Then, the obtained data can be preprocessed for removing the errors. Followed by hierarchical network feature extraction can be used to identify the abnormal features related to the attack. Finally, the user data can be protected and the malicious attack in the transmission route can be identified by using the Wrapper stepwise ResNet classifier. The proposed work outperforms other techniques in terms of attack detection and accuracy, and the findings are depicted in the graphical format by employing the Python tool.

• 전기전자학회논문지
• /
• 제4권2호
• /
• pp.288-294
• /
• 2000

본 논문에서는 동영상 압축 기법을 향상시키기 위하여 효율적인 detail 추출 기법을 제안한다. 기존의 top-hat 변환을 이용한 기법은 고립되어 있고 시각적으로 중요한 detail의 추출에는 효율적이지만, 영역의 경계에서는 비효율적이다. 제안된 기법은 수리형태학적 Laplacian 연산의 영역경계 정보추출의 성질을 이용하여 압축을 향상시키고 저비트율을 제공한다. 실험결과를 통해서 제안된 기법이 기존 기법보다 효율적임을 보이고 수리형태학적 Laplacian 연산 적용의 타당성을 설명한다.

• 디지털정책학회지
• /
• 제1권2호
• /
• pp.53-59
• /
• 2022

본 논문에서는 단일 영상을 기반으로 초해상도를 생성하는 과정에서 계층 구조를 거쳐 추출된 보조 경계 특징을 이용한 방법을 제안하였다. 초해상도의 품질을 향상시키기 위해서는 영상 내 경계 영역을 선명하게 표현하면서도 각 영역의 형태를 명확하게 구분하여야 한다. 제안하는 방법은 초해상도 과정에서 품질을 결정하는 중요한 요인인 경계 영역을 입력 영상의 구조적 형태를 유지하면서 개선된 초해상도 결과를 생성하기 위해 딥러닝 기반의 초해상도 방법에서 영상의 경계 영역 정보를 보조적으로 활용하는 구조를 사용하였다. 딥러닝 기반의 초해상도를 수행하기 위한 그룹 컨볼루션 구조에 더해 보조 경계 추출을 위한 고주파 대역의 정보를 기반으로 별도의 계층적 구조의 경계 누적 추출 과정을 수행하여 이를 보조 특징으로써 활용하는 방법을 제안하였다. 실험 결과 기존 초해상도 대비 PSNR과 SSIM에서 약 1%의 성능 향상을 보였다.

• 제어로봇시스템학회논문지
• /
• 제13권6호
• /
• pp.513-518
• /
• 2007

In this paper, we propose a fault diagnosis scheme tor induction motor by adopting a hierarchical classifier consisting of k-Nearest Neighbors(k-NN) and Support Vector Machine(SVM). First, some motor conditions are classified by a simple k-NN classifier in advance. And then, more complicated classes are distinguished by SVM. To obtain the normal and fault data, we established an experimental unit with induction motor system and data acquisition module. Feature extraction is performed by Principal Component Analysis(PCA). To show its effectiveness, the proposed fault diagnostic system has been intensively tested with various data acquired under the different electrical and mechanical faults with varying load.