• 로봇학회논문지
• /
• 제15권1호
• /
• pp.62-69
• /
• 2020

This paper proposes a pattern recognition and classification algorithm based on a circular structure that can reflect the characteristics of the sEMG (surface electromyogram) signal measured in the arm without putting the placement limitation of electrodes. In order to recognize the same pattern at all times despite the electrode locations, the data acquisition of the circular structure is proposed so that all sEMG channels can be connected to one another. For the performance verification of the sEMG pattern recognition and classification using the developed algorithm, several experiments are conducted. First, although there are no differences in the sEMG signals themselves, the similar patterns are much better identified in the case of the circular structure algorithm than that of conventional linear ones. Second, a comparative analysis is shown with the supervised learning schemes such as MLP, CNN, and LSTM. In the results, the classification recognition accuracy of the circular structure is above 98% in all postures. It is much higher than the results obtained when the linear structure is used. The recognition difference between the circular and linear structures was the biggest with about 4% when the MLP network was used.

• 한국멀티미디어학회논문지
• /
• 제13권11호
• /
• pp.1586-1593
• /
• 2010

확률적 패턴 매칭과 동적 패턴 매칭의 어휘 인식 오류 보정 방법에서는 핵심어를 기반으로 문장을 의미론적으로 분석하므로 형태론적 변형에 따른 핵심어 분석이 어려운 문제점을 가지고 있다. 이를 해결하기 위해 본 연구에서는 음절 복원 알고리즘에서 형태소 분석을 이용하여 인식된 음소 열을 의미 분석 과정을 통해 음소의 의미를 파악하고 형태론적 분석으로 문장을 복원하여 어휘 오인식률을 감소하였다. 시스템 분석을 위해 음소 유사률과 신뢰도를 이용하여 오류 보정률을 구하였으며, 어휘 인식 과정에서 오류로 판명된 어휘에 대하여 오류 보정을 수행하였다. 에러 패턴 학습을 이용한 방법과 오류 패턴 매칭 기반 방법, 어휘 의미 패턴 기반 방법의 성능 평가 결과 2.0%의 인식 향상률을 보였다.

• 전자공학회논문지CI
• /
• 제40권2호
• /
• pp.9-16
• /
• 2003

본 논문에서는 개선된 SOFM(Self Organizing Feature Map)방식을 이용한 근전도 패턴인식으로 가상 로봇 팔을 제어하는 방식을 제안한다. 개선된 SOFM 방식은 근전도 신호의 전처리기를 사용하는 대신에 근전도 신호 자체를 SOFM에 입력으로 사용하고, 퍼지논리시스템을 이용하여 SOFM의 이웃반경과 학습율을 자동 조절하는 간단한 방식으로 입력 패턴을 더욱 빠르고 신뢰성있게 분류한다. 개선된 방식의 성능을 확인하기 위하여 어깨, 손목, 팔꿈치의 여섯 가지 동작의 근전도 패턴인식을 실험한 결과 기존의 일반적인 SOFM방식보다 제안한 SOFM방식의 인식율이 21.7% 향상되고, 평균학습 수도 절반이하로 감소되었으며, 인식한 근전도 신호를 이용하여 컴퓨터 상의 가상 로봇 팔을 정확하게 제어하였다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1994년도 추계학술대회 논문집
• /
• pp.481-486
• /
• 1994

An image processing and pattern recognition program was developed in order to recognize the nummerinc displays on gas flow meters. the testing process of the accuracy of gas flow meters are to be automated, using the developed software. There are already many known pattern recognition algorithms for recognition of the letters. To upgrade the recognization accuracy, four different algorithms are applied in sequentially in the software. An calculation method to assign the weighting factors for the result of each algorithm was developed. It showed 98% accuracy by the pattern recognition of displaying numbers of gas mwters of 33 differnt types. This pattern recognition system is to be integrated in a industry.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.345-350
• /
• 2002

In this study, researchers classifying the artificial flaws in semiconductor packages are performed by pattern recognition technology. For this purposes, image pattern recognition package including the user made software was developed and total procedure including ultrasonic image acquisition, equalization filtration, binary process, edge detection and classifier design is treated by Backpropagation Neural Network. Specially, it is compared with various weights of Backpropagation Neural Network and it is compared with threshold level of edge detection in preprocessing method fur entrance into Multi-Layer Perceptron(Backpropagation Neural network). Also, the pattern recognition techniques is applied to the classification problem of defects in semiconductor packages as normal, crack, delamination. According to this results, it is possible to acquire the recognition rate of 100% for Backpropagation Neural Network.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권2호
• /
• pp.103-110
• /
• 2004

This paper proposes a new method on the EMG AR(autoregressive) modeling in pattern recognition for various head motions. The proper electrode placement in applying AR or cepstral coefficients for EMG signature discrimination is investigated. EMG signals are measured for different 10 motions with two electrode arrangements simultaneously. Electrode pairs are located separately on dominant muscles(S-type arrangement), because the bandwidth of signals obtained from S-type placement is wider than that from C-type(closely in the region between muscles). From the result of EMG pattern recognition test, the proposed mIAR(modified integrated mean autoregressive model) technique improves the recognitions rate around 17-21％ compared with other the AR and cepstral methods.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 추계학술대회 논문집
• /
• pp.721-726
• /
• 2005

In this study, researchers classifying the artificial flaws in semiconductor. packages are performed by pattern recognition technology. For this purposes, image pattern recognition package including the user made software was developed and total procedure including ultrasonic image acquisition, equalization filtration, binary process, edge detection and classifier design is treated by Backpropagation Neural Network. Specially, it is compared with various weights of Backpropagation Neural Network and it is compared with threshold level of edge detection in preprocessing method for entrance into Multi-Layer Perceptron(Backpropagation Neural network). Also, the pattern recognition techniques is applied to the classification problem of defects in semiconductor packages as normal, crack, delamination. According to this results, it is possible to acquire the recognition rate of 100% for Backpropagation Neural Network.

• Journal of Multimedia Information System
• /
• 제5권4호
• /
• pp.221-228
• /
• 2018

Skin-color information is not sufficient for palmprint segmentation in complex scenes, including mobile environments. Traditional active shape model (ASM) combines gray information and shape information, but its performance is not good in complex scenes. An improved ASM method is developed for palmprint segmentation, in which Perux method normalizes the shape of the palm. Then the shape model of the palm is calculated with principal component analysis. Finally, the color likelihood degree is used to replace the gray information for target fitting. The improved ASM method reduces the complexity, while improves the accuracy and robustness.

• Asian Pacific Journal of Cancer Prevention
• /
• 제14권9호
• /
• pp.5409-5413
• /
• 2013

Background: To assess the accuracy of ultrasound in differentiating endometrioma from ovarian cancer and to describe pattern recognition for atypical endometriomas mimicking ovarian cancers. Materials and Methods: Patients scheduled for elective surgery for adnexal masses were sonographically evaluated for endometrioma within 24 hours of surgery. All examinations were performed by the same experienced sonographer, who had no any information of the patients, to differentiate between endometriomas and non-endometriomas using a simple rule (classic ground-glass appearance) and subjective impression (pattern recognition). The final diagnosis as a gold standard relied on either pathological or post-operative findings. Results: Of 638 patients available for analysis, 146 were proven to be endometriomas. Of them, the simple rule and subjective impression could sonographically detect endometriomas with sensitivities of 64.4% (94/146) and 89.7% (131/146), respectively. Of 52 endometriomas with false negative tests by the simple rule, 13 were predicted as benign masses and 39 were mistaken for malignancy. Solid masses and papillary projections were the most common forms mimicking ovarian cancer, consisting of 38.5% of the missed diagnoses. However, with pattern recognition (subjective impression), 32 from 39 cases mimicking ovarian cancer were correctly predicted for endometriomas. All endometriomas subjectively predicted for ovarian malignancy were associated with high vascularization in the solid masses. Conclusions: Pattern recognition of endometriomas by subjective assessment had a higher sensitivity than the simple rule in characterization of endometriomas. Most endometriomas mimicking ovarian malignancy could be correctly predicted by subjective impression based on familiarity of pattern recognition.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2011년도 춘계학술발표대회
• /
• pp.346-349
• /
• 2011

In this paper, we design a perceptually invisible dot pattern layout and its recognition scheme, and we apply the recognition scheme into a smart self learning aid for interactive learning aid. To increase maximum information capacity and also increase robustness to the noises, we design a ECC (error correcting code) based dot pattern with directional vector indicator. To make a smart self-learning aid, we embed the micro dot pattern (20 information bit + 15 ECC bits + 9 layout information bit) using K ink (CMYK) and extract the dot pattern using IR (infrared) LED and IR filter based camera, which is embedded in the smart pen. The reason we use K ink is that K ink is a carbon based ink in nature, and carbon is easily recognized with IR even without light. After acquiring IR camera images for the dot patterns, we perform layout adjustment using the 9 layout information bit, and extract 20 information bits from 35 data bits which is composed of 20 information bits and 15 ECC bits. To embed and extract information bits, we use topology based dot pattern recognition scheme which is robust to geometric distortion which is very usual in camera based recognition scheme. Topology based pattern recognition traces next information bit symbols using topological distance measurement from the pivot information bit. We implemented and experimented with sample patterns, and it shows that we can achieve almost 99% recognition for our embedding patterns.