• 대한전자공학회논문지SP
• /
• 제47권1호
• /
• pp.35-43
• /
• 2010

고유얼굴 기반 얼굴 인식 방법과 같은 얼굴 형태 기반 얼굴 인식 방법에 사용되는 1차원 PCA는 고차원의 얼굴 형태 데이터 벡터들의 처리로 인하여 부정확한 얼굴 표현과 과도한 계산량을 초래할 수 있다. 이에 개선 방안의 하나로 2차원 PCA 기반 얼굴 인식 방법이 개발되었다. 그러나 단순한 2차원 PCA 적용으로 얻어진 얼굴 표현 모델에는 얼굴 공통 특성 성분과 개인 식별 특성 성분이 모두 포함된다. 얼굴 공통 특성 성분은 오히려 개인 식별 능력을 방해할 수가 있고 또한 인식 처리 시간의 증가를 초래한다. 본 논문에서는 2차원 PCA 적용으로 얻어진 얼굴 특성 공간에서 얼굴 공통 특성 영향이 분리된 얼굴 고유 식별 특성 부분공간 모델을 개발하고 개발된 모델에 기반한 새로운 강인한 얼굴 인식 방법을 제안한다. 제안한 얼굴 고유식별 특성 부분공간 모델 기반 얼굴 인식 방법은 얼굴 고유 식별 특성에만 주로 의존하기 때문에 기존 1차원 PCA 및 2차원 PCA 기반 얼굴 인식 방법보다 얼굴 인식 성능 및 인식 속도에 대해서 더 우수한 성능을 보인다. 이는 다양한 조명 조건하에 다양한 얼굴 자세를 갖는 얼굴 이미지들로 구성된 Yale A 및 IMM 얼굴 데이터베이스를 이용한 실험을 통해 확인하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2001년도 춘계종합학술대회
• /
• pp.656-659
• /
• 2001

Human have a notable ability to recognize faces, which is one of the most common visual feature in our environment. In regarding face pattern, just like other natural object, a geometrical interpretation of face is difficult to achieve. In this paper, we present wavelet based approach to extract the face features. Proposed approach is similar to the feature based scheme, where the feature is derived from the intensity data without detecting any knowledge of the significant feature. Topological graphs are involved to represent some relations between facial features. In our experiments, proposed approach is less sensitive to the intensity variation.

• 한국정보통신학회논문지
• /
• 제5권2호
• /
• pp.349-355
• /
• 2001

Human have a notable ability to recognize faces, which is one of the most common visual feature in our environment. In regarding face pattern, just like other natural object, a geometrical interpretation of face is difficult to achieve. In this paper, we present wavelet based approach to extract the face features. Proposed approach is similar to the feature based scheme, where the feature is derived from the intensity data without detecting any knowledge of the significant feature. Topological graphs are involved to represent some relations between facial features. In our experiments, proposed approach is less sensitive to the intensity variation.

• 반도체디스플레이기술학회지
• /
• 제6권2호
• /
• pp.59-63
• /
• 2007

Radio Frequency Identification (RFID) is a common term for technologies using micro chips that are able to communicate over short-range radio and that can be used for identifying physical objects. RFID technology already has several application areas and more are being envisioned all the time. While it has the potential of becoming a really ubiquitous part of the information society over time, there are many security and privacy concerns related to RFID that need to be solved. This paper proposes a method which could protect private information and ensure RFID's identification effectively storing face feature information on RFID tag. This method improved linear discriminant analysis has reduced the dimension of feature information which has large size of data. Therefore, face feature information can be stored in small memory field of RFID tag. The proposed algorithm in comparison with other previous methods shows better stability and elevated detection rate and also can be applied to the entrance control management system, digital identification card and others.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1467-1472
• /
• 2018

For the problem that the face image of surveillance video cannot be accurately identified due to the low resolution, this paper proposes a low resolution face recognition solution based on convolutional neural network model. Convolutional Neural Networks (CNN) model for multi-scale input The CNN model for multi-scale input is an improvement over the existing "two-step method" in which low-resolution images are up-sampled using a simple bi-cubic interpolation method. Then, the up sampled image and the high-resolution image are mixed as a model training sample. The CNN model learns the common feature space of the high- and low-resolution images, and then measures the feature similarity through the cosine distance. Finally, the recognition result is given. The experiments on the CMU PIE and Extended Yale B datasets show that the accuracy of the model is better than other comparison methods. Compared with the CMDA_BGE algorithm with the highest recognition rate, the accuracy rate is 2.5%~9.9%.

• 한국멀티미디어학회논문지
• /
• 제15권5호
• /
• pp.606-614
• /
• 2012

AdaBoost 알고리즘을 이용한 얼굴 검출 방법은 가장 빠르고 신뢰성 있는 얼굴 검출 알고리즘의 하나로 이를 향상하거나 확장한 많은 알고리즘들이 제안되었다. 그러나 이전의 접근들은 대부분 정면 얼굴만을 다루고 있고 AdaBoot 알고리즘을 정면과 기울어진 얼굴에 동일한 특징으로 적용함으로써 기울어진 얼굴에 대한 분별 성능이 제한적이었다. 또한 회전된 얼굴을 검출하기 위하여 입력된 영상을 회전하여 정면 얼굴 검출 방법을 적용하거나 회전된 각도에 따라 다른 검출기를 적용하는 기존 기법들은 연산량이 많고 검출률이 저하되는 문제를 가지고 있다. 본 논문에서는 이러한 문제를 극복하기 위해 JointBoost를 이용한 기울어진 얼굴 검출 방법을 제안한다. JointBoost를 통해 클래스간의 공유된 feature들를 찾음으로써 연산량과 샘플 복잡도를 감소시켰다. 실험 결과를 통해 제안된 방법의 검출률이 동일한 반복 횟수를 가지는 학습에서 기존의 AdaBoost 기법에 비해 2% 이상 우수함을 보인다. 또한 제안된 방법은 얼굴의 존재를 검출할 뿐만 아니라 기울어진 방향에 대한 정보도 제공할 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권12호
• /
• pp.5464-5484
• /
• 2016

Few samples face recognition has become a highly challenging task due to the limitation of available labeled samples. As two popular paradigms in face image representation, sparse component analysis is highly robust while parts-based paradigm is particularly flexible. In this paper, we propose a probabilistic generative model to incorporate the strengths of the two paradigms for face representation. This model finds a common spatial partition for given images and simultaneously learns a sparse component analysis model for each part of the partition. The two procedures are built into a probabilistic generative model. Then we derive the score function (i.e. feature mapping) from the generative score space. A similarity measure is defined over the derived score function for few samples face recognition. This model is driven by data and specifically good at representing face images. The derived generative score function and similarity measure encode information hidden in the data distribution. To validate the effectiveness of the proposed method, we perform few samples face recognition on two face datasets. The results show its advantages.

• International Journal of Computer Science & Network Security
• /
• 제21권8호
• /
• pp.288-296
• /
• 2021

Automated face recognition in a runtime environment is gaining more and more important in the fields of surveillance and urban security. This is a difficult task keeping in mind the constantly volatile image landscape with varying features and attributes. For a system to be beneficial in industrial settings, it is pertinent that its efficiency isn't compromised when running on roads, intersections, and busy streets. However, recognition in such uncontrolled circumstances is a major problem in real-life applications. In this paper, the main problem of face recognition in which full face is not visible (Occlusion). This is a common occurrence as any person can change his features by wearing a scarf, sunglass or by merely growing a mustache or beard. Such types of discrepancies in facial appearance are frequently stumbled upon in an uncontrolled circumstance and possibly will be a reason to the security systems which are based upon face recognition. These types of variations are very common in a real-life environment. It has been analyzed that it has been studied less in literature but now researchers have a major focus on this type of variation. Existing state-of-the-art techniques suffer from several limitations. Most significant amongst them are low level of usability and poor response time in case of any calamity. In this paper, an improved face recognition system is developed to solve the problem of occlusion known as FRS-OCC. To build the FRS-OCC system, the color and texture features are used and then an incremental learning algorithm (Learn++) to select more informative features. Afterward, the trained stack-based autoencoder (SAE) deep learning algorithm is used to recognize a human face. Overall, the FRS-OCC system is used to introduce such algorithms which enhance the response time to guarantee a benchmark quality of service in any situation. To test and evaluate the performance of the proposed FRS-OCC system, the AR face dataset is utilized. On average, the FRS-OCC system is outperformed and achieved SE of 98.82%, SP of 98.49%, AC of 98.76% and AUC of 0.9995 compared to other state-of-the-art methods. The obtained results indicate that the FRS-OCC system can be used in any surveillance application.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2010년도 하계학술대회 논문집
• /
• pp.39-39
• /
• 2010

The authors have an extensive study of photoluminescences for Zn-polar and O-polar faces of single-crystalline ZnO bulks. In the photoluminescence (PL) spectra at 10 K, Zn-polar and O-polar faces show a common emission feature: neutral donor-bound excitons and their longitudinal-optical (LO) phonon replicas are strong, and free excitons are very weak. However, in the PL spectra at room temperature (RT), Zn-polar and O-polar faces show extremely different emission characteristics: the emission intensity of Zn-polar face is 30 times larger than that of O-polar face, and the band edge of Zn-polar face is 33 meV red-shifted from that of O-polar face. The temperature dependence of photoluminescence indicates that the PL spectra at RT are closely associated with free excitons and their phonon-assisted annihilation processes. As a result, it is found that the RT PL spectra of Zn-polar face is dominated by the first-order LO phonon replica of A free excitons, while that of O-polar face is determined by A free excitons. This is ascribed that Zn-polar face has larger exciton-phonon coupling strength than O-polar face.

• 대한가정학회지
• /
• 제47권2호
• /
• pp.15-26
• /
• 2009

The purpose of this study is to research development process of commedia dell'arte and Korean masque that have similar figure, grasp similarity and difference and find the meaning of masque and costume in both theatrical arts. Italian commedia dell'arte and Korean masque are performed by wearing standardized mask and costume depending on the role. As common points, first, the characters have unique names and possess unique features of character, costumes, masks and playing styles. Through the feature, the audiences can understand role of actor and the actors can devote themselves to their role by wearing masks and costumes. Second, although background plays an important role in commedia dell'arte, the role of costume is more important. Because masque speaks for poverties of general people indirectly, the costumes of general people were used as they are. As different point, first, most of Korean masks cover entire face, restricting speech of actor but masks of commedia dell'arte cover only upper part of face and expos mouth and chin of actor, enabling actors to express various emotions depending on the character. Second, priority is given to personality of actor and origin area and current silhouette, material and color that changed by century is reflected in the costume of commedia dell'arte but silhouette, material and color of the Age of Joseon Dynasty were adopted in Korean masque.