• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.1
• /
• pp.55-67
• /
• 2023

Lightweight face recognition models, as one of the most popular and long-standing topics in the field of computer vision, has achieved vigorous development and has been widely used in many real-world applications due to fewer number of parameters, lower floating-point operations, and smaller model size. However, few surveys reviewed lightweight models and reimplemented these lightweight models by using the same calculating resource and training dataset. In this survey article, we present a comprehensive review about the recent research advances on the end-to-end efficient lightweight face recognition models and reimplement several of the most popular models. To start with, we introduce the overview of face recognition with lightweight models. Then, based on the construction of models, we categorize the lightweight models into: (1) artificially designing lightweight FR models, (2) pruned models to face recognition, (3) efficient automatic neural network architecture design based on neural architecture searching, (4) Knowledge distillation and (5) low-rank decomposition. As an example, we also introduce the SqueezeFaceNet and EfficientFaceNet by pruning SqueezeNet and EfficientNet. Additionally, we reimplement and present a detailed performance comparison of different lightweight models on the nine different test benchmarks. At last, the challenges and future works are provided. There are three main contributions in our survey: firstly, the categorized lightweight models can be conveniently identified so that we can explore new lightweight models for face recognition; secondly, the comprehensive performance comparisons are carried out so that ones can choose models when a state-of-the-art end-to-end face recognition system is deployed on mobile devices; thirdly, the challenges and future trends are stated to inspire our future works.

• Journal of KIISE:Software and Applications
• /
• v.36 no.10
• /
• pp.816-824
• /
• 2009

In the face space, face images due to illumination and pose variations have a nonlinear distribution. Active Appearance Models (AAM) based on the linear model have limits to the nonlinear distribution of face images. In this paper, we assume that a few clusters of face images are given; we build local AAMs according to the clusters of face images, and then select a proper AAM model during the fitting phase. To solve the problem of updating fitting parameters among the models due to the model changing, we propose to build in advance relationships among the clusters in the parameter space from the training images. In addition, we suggest a gradual model changing to reduce improper model selections due to serious fitting failures. In our experiment, we apply the proposed model to Yale Face Database B and compare it with the previous method. The proposed method demonstrated successful fitting results with strongly illuminated face images of deep shadows.

• Smart Media Journal
• /
• v.12 no.2
• /
• pp.9-14
• /
• 2023

In this paper, we proposed a face recognition network which attempts to use more facial features awhile using smaller number of training sets. When combining the neural network together for face recognition, we want to use networks that use different part of the facial features. However, the network training chooses randomly where these facial features are obtained. Other hand, the judgment basis of the network model can be expressed as a saliency map through gradCAM. Therefore, in this paper, we use gradCAM to visualize where the trained face recognition model has made a observations and recognition judgments. Thus, the network combination can be constructed based on the different facial features used. Using this approach, we trained a network for small face recognition problem. In an simple toy face recognition example, the recognition network used in this paper improves the accuracy by 1.79% and reduces the equal error rate (EER) by 0.01788 compared to the conventional approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.4
• /
• pp.1824-1845
• /
• 2016

The GMM is a conventional approach which has been recently applied in many face recognition studies. However, the question about how to deal with illumination changes while ensuring high performance is still a challenge, especially with real-world databases. In this paper, we propose a Visual Observation Confidence (VOC) measure for robust face recognition for illumination changes. Our VOC value is a combined confidence value of three measurements: Flatness Measure (FM), Centrality Measure (CM), and Illumination Normality Measure (IM). While FM measures the discrimination ability of one face, IM represents the degree of illumination impact on that face. In addition, we introduce CM as a centrality measure to help FM to reduce some of the errors from unnecessary areas such as the hair, neck or background. The VOC then accompanies the feature vectors in the EM process to estimate the optimal models by modified-GMM training. In the experiments, we introduce a real-world database, called KoFace, besides applying some public databases such as the Yale and the ORL database. The KoFace database is composed of 106 face subjects under diverse illumination effects including shadows and highlights. The results show that our proposed approach gives a higher Face Recognition Rate (FRR) than the GMM baseline for indoor and outdoor datasets in the real-world KoFace database (94% and 85%, respectively) and in ORL, Yale databases (97% and 100% respectively).

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.151-154
• /
• 2003

In this paper, we propose a method to recognize a face image of the 3D using the LVQ network. LVQ network of the proposed method, We used the front view of a face image to get to a coded light to a training data, can group a face image including the side of various angle. For an usefulness authentication of this algorithm, Various experiment which classifies a face image of the angle was the low.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.2
• /
• pp.9-16
• /
• 2019

Computer-Assisted Pronunciation Training system is considered to be a useful tool for pronunciation learning for students who received elementary level English pronunciation education, especially for students who have difficulty in correcting their pronunciation in front of others or who are not able to receive face-to-face training. The conventional Computer-Assisted Pronunciation Training system shows the word to the user, the user pronounces the word, and then the system provides phoneme or audio feedback according to the pronunciation of the user. In this paper, we propose a Computer-Assisted Pronunciation Training system that can practice on the varying pronunciation according to positions of adjacent phonemes. To achieve this, the proposed system is implemented by recommending a series of words by focusing on adjacent phonemes for simplicity and clarity. Experimental results showed that word recommendation considering adjacent phonemes leads to improvement of pronunciation accuracy.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.577-582
• /
• 2021

Recently, with the development of AR, VR, and smart device technologies, the demand for services based on non-face-to-face environments is also increasing in the fitness industry. The non-face-to-face online home training service has the advantage of not being limited by time and place compared to the existing offline service. However, there are disadvantages including the absence of exercise equipment, difficulty in measuring the amount of exercise and chekcing whether the user maintains an accurate exercise posture or not. In this study, we develop a standard exercise program that can compensate for these shortcomings and propose a new non-face-to-face home training application by using a deep learning-based body posture estimation image processing algorithm. This application allows the user to directly watch and follow the trainer of the standard exercise program video, correct the user's own posture, and perform an accurate exercise. Furthermore, if the results of this study are customized according to their purpose, it will be possible to apply them to performances, films, club activities, and conferences

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.3
• /
• pp.67-73
• /
• 2023

Under the influence of COVID-19, as a measure of social distancing for about two years and one month, non-face-to-face services using ICT element technology are expanding not only to the education sector but to all fields. In particular, as educational programs using the Metaverse platform spread to various fields, educators, and learners have more learning experiences using Edutech, but problems through non-face-to-face learning such as reduced immersion or concentration in education are raising In this paper, to overcome the problems raised through non-face-to-face learning and develop metaverse immersive media digital contents to improve the educational environment, we utilize VR (Virtual Reality) based on an immersive metaverse to provide education / Training contents and the educational environment was established. In this paper, we presented a system to increase immersion and concentration in educational contents in a virtual environment using HMD (Head Mounted Display) for learners who are put into military education/training. Immersion was further improved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.4
• /
• pp.1486-1501
• /
• 2021

The removal of accessories from the face is one of the essential pre-processing stages in the field of face recognition. However, despite its importance, a robust solution has not yet been provided. This paper proposes a network and dataset construction methodology to remove only the glasses from facial images effectively. To obtain an image with the glasses removed from an image with glasses by the supervised learning method, a network that converts them and a set of paired data for training is required. To this end, we created a large number of synthetic images of glasses being worn using facial attribute transformation networks. We adopted the conditional GAN (cGAN) frameworks for training. The trained network converts the in-the-wild face image with glasses into an image without glasses and operates stably even in situations wherein the faces are of diverse races and ages and having different styles of glasses.

• Journal of KIISE:Software and Applications
• /
• v.31 no.7
• /
• pp.949-958
• /
• 2004

race detection using a boosting based algorithm requires a very large size of face and nonface data. In addition, the fact that there always occurs a need for adding additional training data for better detection rates demands an efficient incremental teaming algorithm. In the design of incremental teaming based classifiers, the final classifier should represent the characteristics of the entire training dataset. Conventional methods have a critical problem in combining intermediate classifiers that weight updates depend solely on the performance of individual dataset. In this paper, for the purpose of application to face detection, we present a new method to combine an intermediate classifier with previously acquired ones in an optimal manner. Our algorithm creates a validation set by incrementally adding sampled instances from each dataset to represent the entire training data. The weight of each classifier is determined based on its performance on the validation set. This approach guarantees that the resulting final classifier is teamed by the entire training dataset. Experimental results show that the classifier trained by the proposed algorithm performs better than by AdaBoost which operates in batch mode, as well as by ${Learn}^{++}$.