• 한국IT서비스학회지
• /
• 제6권2호
• /
• pp.161-175
• /
• 2007

Face recognition technology has lately attracted considerable attention because of its non-intrusiveness, usability and applicability. Related companies insist that their commercial products show the recognition rates more than 95% according to their self-testing. But, the rates cannot be admitted as official recognition rates. So, performance evaluation methods and tools are necessary to objectively measure the accuracy and performance of face recognition systems. In this paper, I propose a reference model for biometrics recognition evaluation tools, and implement an evaluation tool for the face recognition system based on the proposed reference model.

• 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%.

• 반도체디스플레이기술학회지
• /
• 제21권4호
• /
• pp.14-17
• /
• 2022

Due to the development of IT technology and the on-going Coronavirus disease, non-face-to-face services have been activated. To overcome the inconvenience of non-face-to-face service, service providers have adopted chatbots as a way to feel like a human being. As the increasing chatbot services, chatbot builders have emerged, which can help non-developers to build them. Although its popularity has increased, its performance evaluation has not been conducted on such chatbot builders. In this paper, we implement a prototype chatbot that classifies hospital departments in the medical field using Dialogflow and Rasa, which are popular chatbot builders. By measuring the accuracy of the chatbot's classification of medical subjects, we evaluated the level of accuracy that the most used chatbot builder can have when they are used to build a chatbot service. The simulation results showed that Dialogflow had 87%, 65%, and 60%, and Rasa did 64%, 70%, and 63% in surgery dermatology, and otolaryngology, respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권11호
• /
• pp.3658-3679
• /
• 2022

Classification of persons wearing and not wearing face masks in images has emerged as a new computer vision problem during the COVID-19 pandemic. In order to address this problem and scale up the research in this domain, in this paper a hybrid technique by employing ResNet-101 and multi-layer perceptron (MLP) classifier has been proposed. The proposed technique is tested and validated on a self-created face masks classification dataset and a standard dataset. On self-created dataset, the proposed technique achieved a classification accuracy of 97.3%. To embrace the proposed technique, six other state-of-the-art CNN feature extractors with six other classical machine learning classifiers have been tested and compared with the proposed technique. The proposed technique achieved better classification accuracy and 1-6% higher precision, recall, and F1 score as compared to other tested deep feature extractors and machine learning classifiers.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.387-388
• /
• 2006

In this paper, we propose an efficient algorithm based on PCA and LDA combining K-means clustering method, which has better accuracy of face recognition than Eigenface and Fisherface. In this algorithm, PCA is firstly used to reduce the dimensionality of original face image. Secondly, a truncated face image data are sub-clustered by K-means clustering method based on Euclidean distances, and all small subclusters are labeled in sequence. Then LDA method project data into low dimension feature space and group data easier to classify. Finally we use nearest neighborhood method to determine the label of test data. To show the recognition accuracy of the proposed algorithm, we performed several simulations using the Yale and ORL (Olivetti Research Laboratory) database. Simulation results show that proposed method achieves better performance in recognition accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권7호
• /
• pp.1705-1720
• /
• 2013

Human face gender recognition requires fast image processing with high accuracy. Existing face gender recognition methods used traditional local features and machine learning methods have shortcomings of low accuracy or slow speed. In this paper, a new framework for face gender recognition to reach fast face gender recognition is proposed, which is based on Local Ternary Pattern (LTP) and Extreme Learning Machine (ELM). LTP is a generalization of Local Binary Pattern (LBP) that is in the presence of monotonic illumination variations on a face image, and has high discriminative power for texture classification. It is also more discriminate and less sensitive to noise in uniform regions. On the other hand, ELM is a new learning algorithm for generalizing single hidden layer feed forward networks without tuning parameters. The main advantages of ELM are the less stringent optimization constraints, faster operations, easy implementation, and usually improved generalization performance. The experimental results on public databases show that, in comparisons with existing algorithms, the proposed method has higher precision and better generalization performance at extremely fast learning speed.

• 정보과학회 논문지
• /
• 제42권4호
• /
• pp.483-486
• /
• 2015

얼굴 인식기반의 사용자 보안 시스템은 접근이 허가된 사용자의 사진이나 비디오를 이용한 공격에 취약하다는 단점을 가지고 있다. 본 연구에서는 인증되지 않은 사용자가 비디오를 이용하여 시스템에 접근할 경우 해당 공격 시도를 검출하기 위한 위변조(Spoof) 검출 방법을 제안한다. 제안하는 방법은 연속된 3개의 Frame에서 푸리에 변환과 Dense-SIFT 구분자를 사용하여 400개의 실제 및 위변조 비디오 영상을 대상으로 실험한 결과 99%의 검출 정확도를 보였다.

• 한국산업정보학회논문지
• /
• 제25권1호
• /
• pp.13-23
• /
• 2020

본 논문에서는 얼굴 인식 정확도에 미치는 영향을 최소화하면서 효율적으로 깊이 얼굴 영상을 압축하기 위한 양자화 변수 결정 방법을 제안한다. H.264/AVC의 양자화를 적용하여 깊이 얼굴 영상을 압축 할 때 얼굴 특징을 최대한 유지할 수 있도록 타원체 모델링의 예측 정확도와 각각의 양자화 단위 블록의 얼굴 인식에서의 중요도를 이용하여 양자화 인자를 차등적으로 부여한다. 모의실험 결과 제안된 방법을 통해 같은 압축율에서 얼굴 인식 성공률이 최대 6% 개선되었다.

• Journal of Information Processing Systems
• /
• 제16권5호
• /
• pp.1145-1157
• /
• 2020

A convolution neural networks (CNNs) has demonstrated outstanding performance compared to other algorithms in the field of face recognition. Regarding the over-fitting problem of CNN, researchers have proposed a residual network to ease the training for recognition accuracy improvement. In this study, a novel face recognition model based on game theory for call-over in the classroom was proposed. In the proposed scheme, an image with multiple faces was used as input, and the residual network identified each face with a confidence score to form a list of student identities. Face tracking of the same identity or low confidence were determined to be the optimisation objective, with the game participants set formed from the student identity list. Game theory optimises the authentication strategy according to the confidence value and identity set to improve recognition accuracy. We observed that there exists an optimal mapping relation between face and identity to avoid multiple faces associated with one identity in the proposed scheme and that the proposed game-based scheme can reduce the error rate, as compared to the existing schemes with deeper neural network.

• International Journal of Computer Science & Network Security
• /
• 제21권8호
• /
• pp.127-136
• /
• 2021

Real-time human recognition is a challenging task, as the images are captured in an unconstrained environment with different poses, makeups, and styles. This limitation is addressed by generating several facial images with poses, makeup, and styles with a single reference image of a person using Generative Adversarial Networks (GAN). In this paper, we propose deep learning-based human recognition using integration of GAN and Spatial Domain Techniques. A novel concept of human recognition based on face depiction approach by generating several dissimilar face images from single reference face image using Domain Transfer Generative Adversarial Networks (DT-GAN) combined with feature extraction techniques such as Local Binary Pattern (LBP) and Histogram is deliberated. The Euclidean Distance (ED) is used in the matching section for comparison of features to test the performance of the method. A database of millions of people with a single reference face image per person, instead of multiple reference face images, is created and saved on the centralized server, which helps to reduce memory load on the centralized server. It is noticed that the recognition accuracy is 100% for smaller size datasets and a little less accuracy for larger size datasets and also, results are compared with present methods to show the superiority of proposed method.