• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.603-607
• /
• 2003

The judgment of forged passports plays an important role in the immigration control system, for which the automatic and accurate processing is required because of the rapid increase of travelers. So, as the preprocessing phase for the judgment of forged passports, this paper proposed the novel method for the recognition of passport based on the fuzzy binarization and the fuzzy RBF neural network newly proposed. first, for the extraction of individual codes being recognized, the paper extracts code sequence blocks including individual codes by applying the Sobel masking, the horizontal smearing and the contour tracking algorithm in turn to the passport image, binarizes the extracted blocks by using the fuzzy binarization based on the membership function of trapezoid type, and, as the last step, recovers and extracts individual codes from the binarized areas by applying the CDM masking and the vertical smearing. Next, the paper proposed the enhanced fuzzy RBF neural network that adapts the enhanced fuzzy ART network to the middle layer and applied to the recognition of individual codes. The results of the experiment for performance evaluation on the real passport images showed that the proposed method in the paper has the improved performance in the recognition of passport.

• 말소리와 음성과학
• /
• 제9권4호
• /
• pp.43-50
• /
• 2017

These days voice models of speech recognition software are sophisticated enough to process the natural speech of people without any previous training. However, not much research has reported on the use of speech recognition tools in the field of pronunciation education. This paper examined Google speech recognition of a short English paragraph produced by Korean college students in clear and casual speech styles in order to diagnose and resolve students' pronunciation problems. Thirty three Korean college students participated in the recording of the English paragraph. The Google soundwriter was employed to collect data on the word recognition rates of the paragraph. Results showed that the total word recognition rate was 73% with a standard deviation of 11.5%. The word recognition rate of clear speech was around 77.3% while that of casual speech amounted to 68.7%. The reasons for the low recognition rate of casual speech were attributed to both individual pronunciation errors and the software itself as shown in its fricative recognition. Various distributions of unrecognized words were observed depending on each participant and proficiency groups. From the results, the author concludes that the speech recognition software is useful to diagnose each individual or group's pronunciation problems. Further studies on progressive improvements of learners' erroneous pronunciations would be desirable.

• 음성과학
• /
• 제7권3호
• /
• pp.167-183
• /
• 2000

In this paper, we propose two kinds of chaos dimensions, the fuzzy correlation and fuzzy Lyapunov dimensions, for speaker recognition. The proposal is based on the point that chaos enables us to analyze the non-linear information contained in individual's speech signal and to obtain superior discrimination capability. We confirm that the proposed fuzzy chaos dimensions play an important role in enhancing speaker recognition ratio, by absorbing the variations of the reference and test pattern attractors. In order to evaluate the proposed fuzzy chaos dimensions, we suggest speaker recognition using the proposed dimensions. In other words, we investigate the validity of the speaker recognition parameters, by estimating the recognition error according to the discrimination error of an individual speaker from the reference pattern.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1473-1480
• /
• 2018

The extraction and recognition of human motion characteristics need to combine biometrics to determine and judge human behavior in the movement and distinguish individual identities. The so-called biometric technology, the specific operation is the use of the body's inherent biological characteristics of individual identity authentication, the most noteworthy feature is the invariance and uniqueness. In the past, the behavior recognition technology based on the single characteristic was too restrictive, in this paper, we proposed a mixed feature which combined global silhouette feature and local optical flow feature, and this combined representation was used for human action recognition. And we will use the KTH database to train and test the recognition system. Experiments have been very desirable results.

• 인지과학
• /
• 제20권3호
• /
• pp.357-381
• /
• 2009

이전의 연구들이 외부 피드백 정보에 대한 반응민감도에 성격특성적 개인차가 반영된다는 사실을 밝힌바 있지만, 재인기억과 관련한 의사결정에서 이러한 기질 혹은 특성적 개인차가 어떻게 관여하는지는 아직 알려진 바가 없다. 본 연구는 재인기억 과제에서 피드백에 근거한 의사결정 준거의 순응적 변화정도와 피드백에 대한 일반적 반응민감도의 개인차간 관계를 살펴보았다. 통제 조건인 실험 1에서는 올바른 피드백 조건이 의사결정 준거의 유동성에 영향을 미치지 않음을 보인 반면 피드백 조작이 이루어진 실험 2에서는 확신도가 높은 오기억 반응에만 선택적으로 편향된 피드백이 주어졌음에도 전반적인 Old/New 반응 범주의 결정준거 또한 순응적으로 이동함이 나타났다. 보다 중요하게 이 피드백에 근거한 의사결정 준거 학습에 나타나는 개별 피험자들의 반응민감도 차이가 강화 추구 혹은 불안 회피와 밀접하게 관련된 안정적 성격(Behavioral Activation System-BAS 혹은Behavioral Inhibition System-BIS)의 개인차에 의해 유의미하게 예측될 수 있음이 나타났다. 이러한 결과는 그동안 외현적인 재인 기억 의사 결정에 있어서 중요하게 여기지 않았던 점증적 강화학습 기제가 결정 준거의 설정에 관여할 수 있음을 보여준다는 데에서 중요한 의미를 찾을 수 있다.

• Journal of information and communication convergence engineering
• /
• 제6권4호
• /
• pp.444-447
• /
• 2008

In this paper, we proposed the recognition system of car license plates to mitigate traffic problems. The processing sequence of the proposed algorithm is as follows. At first, a license plate segment is extracted from an acquired car image using morphological features and color information, and noises are eliminated from the extracted license plate segment using line scan algorithm and Grassfire algorithm, and then individual codes are extracted from the license plate segment using edge tracking algorithm. Finally the extracted individual codes are recognized by an FCM algorithm. In order to evaluate performance of segment extraction and code recognition of the proposed method, we used 100 car images for experiment. In the results, we could verify the proposed method is more effective and recognition performance is improved in comparison with conventional car license plate recognition methods.

• 한국컴퓨터정보학회논문지
• /
• 제24권2호
• /
• pp.35-40
• /
• 2019

In this paper, we propose a technique to reconstruct the iris image from the iris code by analyzing the process of generating the iris code and calculating it inversely. Iris recognition is an authentication method for authenticating an individual's identity by using iris information of an eye having unique information of an individual. The iris recognition extracts the features of the iris from the iris image, creates the iris code, and determines whether to authenticate using the corresponding code. The iris recognition method using the iris code is a method proposed by Daugman for the first time and is widely used as a representative method of iris recognition technology currently used commercially. In this paper, we restore the iris image with only the iris code, and test whether the reconstructed image and the original image can be recognized, and analyze restoration vulnerability of Daugman's iris code.

• 한국정보통신학회논문지
• /
• 제3권2호
• /
• pp.321-327
• /
• 1999

본 연구는 스캐너로 입력한 사진을 법의학을 응용한 안면삼각법(facial triangle)과 사진분석법을 이용하여 수직각, 수평각 등을 측정한 각도에서 CCD 카메라로 두개골 영상을 입력받아 중첩시키기 위한 슈퍼임포즈 개인식별 영상시스템의 성능향상과 다양한 영상처리 응용 프로그램을 활용함으로서 자동식별을 위한 개인식별 능력을 향상하였다.

• 한국지능시스템학회논문지
• /
• 제13권4호
• /
• pp.474-479
• /
• 2003

In this paper, we proposed the novel method for the recognition of English calling cards by using the projection method and the enhanced RBF (Radial Basis Function) network. The recognition of calling cards consists of the extraction phase of character areas and the recognition phase of extracted characters. In the extraction phase, first of all, noises are removed from the images of calling cards, and the feature areas including character strings are separated from the calling card images by using the horizontal smearing method and the 8-directional contour tracking method. And using the image projection method, the feature areas are split into the areas of individual characters. We also proposed the enhanced RBF network that organizes the middle layer effectively by using the enhanced ART1 neural network adjusting the vigilance threshold dynamically according to the homogeneity between patterns. In the recognition phase, the proposed neural network is applied to recognize individual characters. Our experiment result showed that the proposed recognition algorithm has higher success rate of recognition and faster learning time than the existing neural network based recognition.

• 한국정보통신학회논문지
• /
• 제12권8호
• /
• pp.1456-1462
• /
• 2008

단일 생체인식 시스템의 인식률을 높이는 것은 생체인식 방법마다 취약점이 있기 때문에 그 한계가 있기 마련이다. 얼굴 인식의 경우 조명과 같은 환경적 요인으로 인식률이 저하될 수 있으며, 화자 확인의 경우도 잡음과 같은 환경적 요인으로 인식률이 크게 저하될 수 있다. 따라서 두 가지 이상의 생체특징을 결합하여 다중 생체인식 시스템을 구현함으로써 그 취약점을 보완하는 추세에 있다. 본 논문에서는 얼굴 인식과 화자 확인 시스템을 결합하여 다중 생체인식 시스템을 구현하였고, 일반적인 가중치합 알고리즘에 환경 변수를 적용하여 기존의 다중 생체 인식 시스템보다 인식률을 향상시켰다. 본 시스템은 비밀키 기반의 애플릿으로 구현되어 있으므로 웹 상의 사용자 인증을 필요로 하는 응용에 활용될 수 있다.