• 한국전자통신학회논문지
• /
• 제11권7호
• /
• pp.685-692
• /
• 2016

본 연구에서는 물체 인식 분야에서 잘 알려진 회전, 스케일, 조명의 변화에 강인한 특징치인 SIFT를 이용하여 지폐의 특징 벡터를 구하고 이를 ANN알고리즘에 의해 정합하여 다국적 지폐를 인식하는 방법에 관한 것으로 계층적 지폐인식 방법을 제안한다. 지폐마다 지니고 있는 특징치를 추출하여 국적 및 권종을 인식하기 위하여 자외선, 적외선, 및 백색 투과광 조명을 개발하고 조명 변화에 따라 촬영된 영상으로부터 SIFT특징치를 구하고 다국적 지폐의 국적과 권종을 인식하는 방법을 구현하였다. 한화, 달러화, 유로화에 관하여 회전 및 크기 변화가 있는 환경에서 제안한 알고리즘을 적용하였고 잘 작동하고 있음을 확인 하였다.

• 한국정보통신학회논문지
• /
• 제13권10호
• /
• pp.1997-2003
• /
• 2009

음악 연구에 따른 컴퓨터의 역할이 점차 중요한 비중을 차지함에 따라 효과적인 악보 인식과 효율적인 악보의 편집 및 수정 방법이 요구된다. 기존의 수동 입력 방식에서는 악보를 부정확하게 입력하여 수정하는 경우에는 작업시간이 많이 소요되며, 각 수정 프로그램에서 만든 악보는 특정 프로그램에서만 재수정이 가능하다는 단점이 있다. 본 논문에서는 이러한 단점을 보완하기 위하여 이미 작성 되어있는 악보들을 자동으로 인식하는 방법을 제안한다. 제안된 악보 인식 방법은 수평 히스토그램을 이용하여 악보 이미지의 오선을 제거한 후, 4 방향 윤곽선 추적 알고리즘을 적용하여 잡음을 제거하고 Grassfire 알고리즘을 적응하여 악보 구성 기호들을 추출한다. 추출된 악보 구성 기호들은 hierarchical ART2 알고리즘을 적용하여 인식된다. 제안된 악보 인식 방법 의 성능을 평가하기 위해 100장의 악보 영상을 대상으로 실험한 결과, 제시된 hierarchical ART2 알고리즘을 이용한 악보 영상의 인식 방법이 효율적임을 확인하였다.

• Smart Structures and Systems
• /
• 제8권1호
• /
• pp.69-92
• /
• 2011

This paper presents an emergent pattern recognition approach based on the immune network theory and hierarchical clustering algorithms. The immune network allows its components to change and learn patterns by changing the strength of connections between individual components. The presented immune-network-based approach achieves emergent pattern recognition by dynamically generating an internal image for the input data patterns. The members (feature vectors for each data pattern) of the internal image are produced by an immune network model to form a network of antibody memory cells. To classify antibody memory cells to different data patterns, hierarchical clustering algorithms are used to create an antibody memory cell clustering. In addition, evaluation graphs and L method are used to determine the best number of clusters for the antibody memory cell clustering. The presented immune-network-based emergent pattern recognition (INEPR) algorithm can automatically generate an internal image mapping to the input data patterns without the need of specifying the number of patterns in advance. The INEPR algorithm has been tested using a benchmark civil structure. The test results show that the INEPR algorithm is able to recognize new structural damage patterns.

• 한국지능시스템학회논문지
• /
• 제19권1호
• /
• pp.54-61
• /
• 2009

본 논문에서는 비전 패턴인식 알고리즘인 시공간적 계층 메모리 학습 알고리즘을 이용한 새로운 근전도 패턴인식 방법을 제시한다. 효율적인 근전도 신호의 학습과 분류를 위하여 단순화된 2 레벨의 공간적 집합, 시간적 집합, 그리고 관리 맵퍼를 이용한 수정된 시공간적 계층 메모리 학습 알고리즘을 제안한다. 인식 성능을 향상시키기 위해서 관리 맵퍼 학습뿐만 아니라 시간적 집합 학습에도 카테고리 정보를 사용한다. 실험을 통하여 열 가지 손동작이 성공적으로 인식됨을 검증한다.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권2호
• /
• pp.785-804
• /
• 2017

Due to various factors such as postures, facial expressions and illuminations, face recognition by videos often suffer from poor recognition accuracy and generalization ability, since the within-class scatter might even be higher than the between-class one. Herein we address this problem by proposing a hierarchical cascaded classifier for video face recognition, which is a multi-layer algorithm and accounts for the misclassified samples plus their similar samples. Specifically, it can be decomposed into single classifier construction and multi-layer classifier design stages. In single classifier construction stage, classifier is created by clustering and the number of classes is computed by analyzing distance tree. In multi-layer classifier design stage, the next layer is created for the misclassified samples and similar ones, then cascaded to a hierarchical classifier. The experiments on the database collected by ourselves show that the recognition accuracy of the proposed classifier outperforms the compared recognition algorithms, such as neural network and sparse representation.

• 정보처리학회논문지B
• /
• 제10B권4호
• /
• pp.443-450
• /
• 2003

본 논문은 영문 명함의 다해상도 영상을 이용한 계층적 영살 처리를 통해 문자를 추출하고 개선된 신경망 기법을 이용하여 문자를 인식하는 새로운 계층적 명함 인식 알고리즘을 제안하였다 계층적 인식 알고리즘은 명함 인식 과정을 구성하는 각 처리 단계별로 처리 시간을 단축함과 동시에 성능 향상을 위해 입력된 명함 영상을 해상도가 서로 다른 영상들로 분리하여 적용한다. 우선 1/3배 축소 영상에 가로 스미어링 기법을 적용하여 명함 영상 내에서 문자들을 포함하는 문자열 영역을 추출하고, 문자열 영역으로부터 개별 문자를 추출하기 위하여 1/2배 축소 영상에 새로 스미어링 및 윤곽선 추적 마스킹을 적용한다. 마지막으로 추출된 문자를 인식하기 위해서 문자의 형태학적 특성을 그대로 가지고 있는 원 영상을 사용하며, 다양한 형태를 가진 명함상의 문자를 인식하기 위해 ART1 기반의 개선된 RBF 네트워크를 제안하고 인식 과정에 적용하였다 제안된 인식 알고리즘을 실제 영문 명함 영상에 적용하여 실험한 결과, 기존의 방법과 비교하여 문자 추출 및 인식 성능이 크게 향상됨을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권3호
• /
• pp.1614-1632
• /
• 2017

Bag of visual words is a popular model in human action recognition, but usually suffers from loss of spatial and temporal configuration information of local features, and large quantization error in its feature coding procedure. In this paper, to overcome the two deficiencies, we combine sparse coding with spatio-temporal pyramid for human action recognition, and regard this method as the baseline. More importantly, which is also the focus of this paper, we find that there is a hierarchical structure in feature vector constructed by the baseline method. To exploit the hierarchical structure information for better recognition accuracy, we propose a tree regularized classifier to convey the hierarchical structure information. The main contributions of this paper can be summarized as: first, we introduce a tree regularized classifier to encode the hierarchical structure information in feature vector for human action recognition. Second, we present an optimization algorithm to learn the parameters of the proposed classifier. Third, the performance of the proposed classifier is evaluated on YouTube, Hollywood2, and UCF50 datasets, the experimental results show that the proposed tree regularized classifier obtains better performance than SVM and other popular classifiers, and achieves promising results on the three datasets.

• 전자공학회논문지A
• /
• 제31A권7호
• /
• pp.55-62
• /
• 1994

Interpattern association (IPA) model which the interconnection weight matrix(IWM) is constructed by the association between patterns is effective in similar pattern recognitions. But, if the number of reference patterns is increased, the ability of recognition is decreased. Using a hierarchical recognition algorithm which adopts the tree search strategy, we classified reference patterns into sub-groups by similarity. In IPA model, if input includes random noise we make it converge to reference pattern by means of input includes random noise we make it converge to reference pattern by means of increasing the number of pixels of prohibited state in IWM. In relation to reference patterns the pixel of prohibited state made partially prohibited state of no connected state using which is not included common and feature regions by each reference patterns.

• 한국멀티미디어학회논문지
• /
• 제23권12호
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.