• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2003년도 하계학술대회 논문집
• /
• pp.94-97
• /
• 2003

본 논문에서는, 웨이브렛 변환과 잡음 섞인 숫자 영상에 대한 최적화 인식 훈련기법을 사용한 다계층 신경망을 제안하고, 이 시스템을 아라비아숫자 인식에 적용한다. 웨이브렛 변환을 이용해 원 영상 정보의 중요한 부분은 최대한 보존하면서 입력벡터의 크기를 줄임으로써 신경망의 노드 수와 학습 수렴시간이 줄어들도록 하였고, 최적화 인식 훈련기법은 데이터의 잡음을 점차적으로 높여가면서 훈련벡터에 적용, 인식률의 변화에 대해 살펴보았다. 잡음이 섞인 숫자 영상의 인식율을 높이기 위해 원 영상에 0, 10, 20, 30, 40, 50㏈의 잡음을 섞은 영상을 훈련에 함께 사용하였다. 테스트 영상에 잡음이 30∼50㏈정도 섞였을 경우에는 원 영상만을 훈련에 이용했을 패와 잡음이 섞인 영상을 이용하여 훈련시켰을 경우에 인식율의 차이가 별로 없지만, 0∼20㏈정도 섞인 영상을 테스트에 사용할때에는 0, 10, 20, 30, 40 , 50㏈의 잡음이 있는 영상을 훈련에 사용했을 때가 원 영상만을 훈련에 이용했을 경우에 비해 인식율이 9% 향상된다.

• 기본간호학회지
• /
• 제24권2호
• /
• pp.157-166
• /
• 2017

Purpose: This study was done to explore recognition of accreditation for nursing education, job satisfaction and intention to change teaching area for faculty in Fundamentals of Nursing. Methods: Participants were 104 faculty members teaching Fundamentals of Nursing. Each participant responded to a questionnaire. Data were collected from June 25 to October 25, 2016, and analyzed using SPSS 23.0 for descriptive statistics, t-test, ANOVA, and Pearson correlation coefficient. Results: The participants' recognition of accreditation in nursing education was $3.45{\pm}0.81$ out of 5 and in the sub-items, the score for quality improvement in professors in Fundamentals of Nursing was lowest at $3.21{\pm}1.03$. Job satisfaction was $3.30{\pm}5.30$, and intention to change teaching area was $2.62{\pm}1.00$. Attributes related to practice appear to be major reasons why participants intended to change their teaching area and scores for intention to change teaching area were medium or higher. Conclusion: Results indicate that it is necessary to develop strategies to improve job satisfaction and reduce intention to change teaching area for faculty with less experience in Fundamentals of Nursing education. Development of strategies, management and support are needed to improve young professors' job satisfaction and reduce intention to change teaching area.

• 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.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1031-1033
• /
• 2005

This paper presents a system of handwritten numerals recognition, which is based on Ant-miner algorithm (data mining based on Ant colony optimization). At the beginning, three distinct fractures (also called attributes) of each numeral are extracted. The attributes are Loop zones, End points, and Feature codes. After these data are extracted, the attributes are in the form of attribute = value (eg. End point10 = true). The extraction is started by dividing the numeral into 12 zones. The numbers 1-12 are referenced for each zone. The possible values of Loop zone attribute in each zone are "true" and "false". The meaning of "true" is that the zone contains the loop of the numeral. The Endpoint attribute being "true" means that this zone contains the end point of the numeral. There are 24 attributes now. The Feature code attribute tells us how many lines of a numeral are passed by the referenced line. There are 7 referenced lines used in this experiment. The total attributes are 31. All attributes are used for construction of the classification rules by the Ant-miner algorithm in order to classify 10 numerals. The Ant-miner algorithm is adapted with a little change in this experiment for a better recognition rate. The results showed the system can recognize all of the training set (a thousand items of data from 50 people). When the unseen data is tested from 10 people, the recognition rate is 98 %.

• 제어로봇시스템학회논문지
• /
• 제13권2호
• /
• pp.179-186
• /
• 2007

This paper presents new ignition method and ignition recognition logic for a microturbine. New ignition method is designed by constant speed control of a microturbine with pre-determined time during a ignition period. It make more accurate air-fuel ratio as well as give enough time to ignition system to have full performance under cold temperature. And ignition recognition logic is designed by observing output current change of inverter by generating output torque of a microturbine in the instant of ignition. For filtering a output torque current of inverter with high frequency, we applied a moving average method. So far, ignition recognition is usually implemented by measuring of exhausted gas temperature(EGT) of microturbine. The proposed logic can give more accurate judgement of ignition as well as keep a good working of starting system under out of order a temperature measuring system and biased initial value of EGT sensor. Finally, the two proposed logics are proved by field operating a microturbine under various conditions.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.695-698
• /
• 2009

Three-dimensional (3D) shape recognition and distance recognition methods utilizing monocular camera systems have been required for field of virtual-reality, computer graphics, measurement technology and robot technology. There have been many studies regarding 3D shape and distance recognition based on geometric and optical information, and it is now possible to accurately measure the geometric information of an object at short range distances. However, these methods cannot currently be applied to long range objects. In the field of virtual-reality, all visual objects must be presented at widely varying ranges, even though some objects will be hazed over. In order to achieve distance recognition from a landscape image, we focused on the use of aerial perspective to simulate a type of depth perception and investigated the relationship between distance and color perception. The applicability of our proposed method was demonstrated in experimental results.

• 한국정보통신학회논문지
• /
• 제14권12호
• /
• pp.2622-2627
• /
• 2010

24시간 무인 감시 시스템에서 정확한 얼굴 인식은 절대적으로 필요한 요소이다. 그러나 얼굴 인식은 얼굴 영상의 왜곡, 조명, 얼굴의 크기, 얼굴 표정, 배경 영상 등의 변화로 인해 많은 제약이 있다. 본 연구에서는 얼굴 인식의 성능 향상을 위하여 혼합형 신경회로망을 제안한다. 제안한 방식은 신경회로망의 비지도학습 방식인 SOM과 LVQ 알고리즘을 이용하여 구성한다. 제안한 방식의 유용성을 확인하기 위하여 고유얼굴 방식, 은닉 마코프 모델 방식, 다층 신경회로망 방식과 비교한다.

• 한국통신학회논문지
• /
• 제16권1호
• /
• pp.23-34
• /
• 1991

본 논문에서는 fuzzy 추론에 의한 중복물체인식에 관해 연구하였다. 영상은 다각형 근사방법을 이용하여 선형선소들의 집합으로 변환되었으며 각 선형선소는 물체의 경계점으로부터 추출된 국부특징점으로 구성되었다. 또한 추출된 특징량을 정보의 불확실성을 나타내는 fuzzy 개념과 대응시킨 fuzzy화 데이터로 나타내었으며, 미지영상에 있어서 모델의 인식은 모델영상으로 부터 생성된 생성규칙을 이용하여 fuzzy 추론에 의해 이루어졌다. 실험을 통하여 불확실성의 정도 변화에 따른 인식 결과의 변화를 고찰하였으며, 120개의 모델이 포함되어 있는 30개의 미지영상에 대해 92.5%의 인식률을 얻었다.

• 전자공학회논문지
• /
• 제52권7호
• /
• pp.86-92
• /
• 2015

본 논문에서는 지역적인 에지의 방향 정보와 반응 크기, 주변 화소와의 밝기값 차이를 LDP 코드에 포함함으로써 얼굴 표정 인식률을 향상시킨다. 기존 LDP 코드를 사용하면 LBP에 비해서 영상의 밝기 변화에 덜 민감하고 잡음에 강한 장점을 가진다. 하지만, 밝기 변화가 없는 매끄러운 영역의 정보를 표현하기 어렵고, 배경에 얼굴과 유사한 에지 패턴이 존재하는 경우에는 인식률이 저하되는 문제점이 있다. 따라서 에지 방향 정보를 기반으로 에지 강도 및 밝기값을 추가할 수 있도록 LDP 코드를 개선하고, 인식률을 측정한다.

• 로봇학회논문지
• /
• 제16권3호
• /
• pp.276-282
• /
• 2021

The system for recognizing text in natural scenes has been applied in various industries. However, due to the change in brightness that occurs in nature such as light reflection and shadow, the text recognition performance significantly decreases. To solve this problem, we propose an adversarial shadow generation and training algorithm that is robust to shadow changes. The adversarial shadow generation and training algorithm divides the entire image into a total of 9 grids, and adjusts the brightness with 4 trainable parameters for each grid. Finally, training is conducted in a adversarial relationship between the text recognition model and the shaded image generator. As the training progresses, more and more difficult shaded grid combinations occur. When training with this curriculum-learning attitude, we not only showed a performance improvement of more than 3% in the ICDAR2015 public benchmark dataset, but also confirmed that the performance improved when applied to our's android application text recognition dataset.