• 정보학연구
• /
• 제12권4호
• /
• pp.25-32
• /
• 2009

Iris recognition is a biometric technology which can identify a person using the iris pattern. It is important for the iris recognition system to extract the feature which is invariant to changes in iris patterns. Those changes can be occurred by the influence of lights, changes in the size of the pupil, and head tilting. This paper is appropriate for the embedded environment using local gradient histogram embedded system using iris feature extraction methods have implement. The proposed method enables high-speed feature extraction and feature comparison because it requires no additional processing to obtain the rotation invariance, and shows comparable performance to the well-known previous methods.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2003년도 춘계학술대회
• /
• pp.304-309
• /
• 2003

In this study, natural flaws in welding parts are classified using the signal pattern classification method. The storage digital oscilloscope including FFT function and enveloped waveform generator is used and the signal pattern recognition procedure is made up the digital signal processing, feature extraction, feature selection and classifier design. It is composed with and discussed using the distance classifier that is based on euclidean distance the empirical Bayesian classifier. Feature extraction is performed using the class-mean scatter criteria. The signal pattern classification method is applied to the signal pattern recognition of natural flaws.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.672-675
• /
• 1999

In this paper, we propose a MLP neural network architecture and feature extraction for Korean syllable recognition. In the proposed syllable recognition system, firstly onset is classified by onset classification neural network. And the results information of onset classification neural network are used for feature selection of imput patterns vector. The feature extraction of Korean syllables is based on sonority. Using the threshold rate separate the syllable. The results of separation are used for feature of onset. nucleus and coda. ETRI's SAMDORI has been used by speech DB. The recognition rate is 96% in the speaker dependent and 93.3% in the speaker independent.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권2호
• /
• pp.102-106
• /
• 2003

This paper describes a new pattern classifier neural network to extract the feature from a letter. The proposed pattern classifier is based on relative distance, which is measure between an input datum and the center of cluster group. So, the proposed classifier neural network is called relative neural network(RNN). According to definitions of the distance and the learning rule, the structure of RNN is designed and the pseudo code of the algorithm is described. In feature extraction of letter, RNN, in spite of deletion of learning rate, resulted in the identical performance with those of winner-take-all(WTA), and self-organizing-map(SOM) neural network. Thus, it is shown that RNN is suitable to extract the feature of a letter.

• 한국정보통신학회논문지
• /
• 제10권7호
• /
• pp.1307-1311
• /
• 2006

본 연구에서는 행렬 분해 (Matrix Factorization)를 이용하여 음성 스펙트럼의 부분적 특정을 나타낼 수 있는 새로운 음성 파라마터를 제안한다. 제안된 파라미터는 행렬내의 모든 원소가 음수가 아니라는 조건에서 행렬분해 과정을 거치게 되고 고차원의 데이터가 효과적으로 축소되어 나타남을 알 수 있다. 차원 축소된 데이터는 입력 데이터의 부분적인 특성을 표현한다. 음성 특징 추출 과정에서 일반적으로 사용되는 멜 필터뱅크 (Mel-Filter Bank)의 출력 을 Non-Negative 행렬 분해(NMF:Non-Negative Matrix Factorization) 알고리즘의 입 력으로 사용하고, 알고리즘을 통해 차원 축소된 데이터를 음성인식기의 입력으로 사용하여 멜 주파수 캡스트럼 계수 (MFCC: Mel Frequency Cepstral Coefficient)의 인식결과와 비교해 보았다. 인식결과를 통하여 일반적으로 음성인식기의 성능평가를 위해 사용되는 MFCC에 비하여 제안된 특정 파라미터가 인식 성능이 뛰어남을 알 수 있었다.

• 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.

• 응용통계연구
• /
• 제26권1호
• /
• pp.131-139
• /
• 2013

지지벡터기계는 잡음변수가 존재하는 경우에 성능이 저하될 수 있다. 또한 최종 분류기에서 각 변수들의 중요도를 알리 어려운 단점이 있다. 따라서 변수선택은 지지벡터기계의 해석력과 정확도를 높일 수 있다. 기존의 문헌상의 대부분의 연구는 선형 지지벡터기계에서 성근 해를 주는 벌점함수를 통해 변수를 선택에 관한 것이다. 실제로는 분류의 정확도를 높이기 위해 비선형 커널을 사용하는 경우가 일반적이다. 따라서 변수선택은 비선형 지지벡터기계에서도 마찬가지로 필요하다. 본 논문에서는 모의실험 및 실제자료를 통하여 비선형 지지벡터의 대표적인 변수선택법인 COSSO(component selection and smoothing operator)와 KNIFE(kernel iterative feature extraction)의 성능을 비교한다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 춘계학술대회 논문집
• /
• pp.455-459
• /
• 1997

A methodology which supports the feature used from design to manufacturing for sculptured pocket is newly devlored and present. The information contents in a feature can be easily conveyed from one application to another in the manufacturing domain. However, the feature generated in one application may not be directly suitable for another whitout being modified with more information. Theobjective of the paper is to parsent the methodology of decomposing a bulky feature of sculptured pocket to be removed into compact features to be efficiently machined. In particular, the paper focuses on the two task: 1) to segment horizontally a bulky feature into intermediate features by determining the adequate depth of cut and cutter size and to generate the temporal precedence graph of the intermediate features and 2)to further decompose each intermediate feature vertical into smaller manufacturing features and to apply the variable feed rate to each small feature. The proposed method will provid better efficiency in machining time and cost than the classical method which uses a long string of NC codes necessary to remove a bulky fecture.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.547-550
• /
• 2009

The object recognition mechanism of human being is not well understood yet. On research of animal experiment using an ape, however, neurons that respond to simple shape (e.g. circle, triangle, square and so on) were found. And Hypothesis has been set up as human being may recognize object as combination of such simple shapes. That mechanism is called Figure Alphabet Hypothesis, and those simple shapes are called Figure Alphabet. As one way to research object recognition algorithm, we focused attention to this Figure Alphabet Hypothesis. Getting idea from it, we proposed the feature extraction algorithm for object recognition. In this paper, we described recognition of binarized images of multifont alphabet characters by the recognition model which combined three-layered neural network in the feature extraction algorithm. First of all, we calculated the difference between the learning image data set and the template by the feature extraction algorithm. The computed finite difference is a feature quantity of the feature extraction algorithm. We had it input the feature quantity to the neural network model and learn by backpropagation (BP method). We had the recognition model recognize the unknown image data set and found the correct answer rate. To estimate the performance of the contriving recognition model, we had the unknown image data set recognized by a conventional neural network. As a result, the contriving recognition model showed a higher correct answer rate than a conventional neural network model. Therefore the validity of the contriving recognition model could be proved. We'll plan the research a recognition of natural image by the contriving recognition model in the future.

• 한국IT서비스학회지
• /
• 제18권2호
• /
• pp.143-159
• /
• 2019

Machine learning (ML) is a method of fitting given data to a mathematical model to derive insights or to predict. In the age of big data, where the amount of available data increases exponentially due to the development of information technology and smart devices, ML shows high prediction performance due to pattern detection without bias. The feature engineering that generates the features that can explain the problem to be solved in the ML process has a great influence on the performance and its importance is continuously emphasized. Despite this importance, however, it is still considered a difficult task as it requires a thorough understanding of the domain characteristics as well as an understanding of source data and the iterative procedure. Therefore, we propose methods to apply deep learning for solving the complexity and difficulty of feature extraction and improving the performance of ML model. Unlike other techniques, the most common reason for the superior performance of deep learning techniques in complex unstructured data processing is that it is possible to extract features from the source data itself. In order to apply these advantages to the business problems, we propose deep learning based methods that can automatically extract features from transaction data or directly predict and classify target variables. In particular, we applied techniques that show high performance in existing text processing based on the structural similarity between transaction data and text data. And we also verified the suitability of each method according to the characteristics of transaction data. Through our study, it is possible not only to search for the possibility of automated feature extraction but also to obtain a benchmark model that shows a certain level of performance before performing the feature extraction task by a human. In addition, it is expected that it will be able to provide guidelines for choosing a suitable deep learning model based on the business problem and the data characteristics.