• 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.

• Knowledge Management Research
• /
• v.23 no.2
• /
• pp.123-142
• /
• 2022

The non-face-to-face environment accelerated by COVID-19 has speeded up the dissemination of digital virtual ecosystems and metaverse. In order for the metaverse to be sustainable, digital twins that are compatible with the real world are key, and critical technology for that is AR (Augmented Reality). In this study, we examined research trends about AR, and will propose the directions for future AR research. We conducted LDA based topic modeling on 11,049 abstracts of published domestic and foreign AR related papers from 2009 to Mar 2022, and then looked into AR that was comprehensive research trends, comparison of domestic and foreign research trends, and research trends before and after the popularity of metaverse concepts. As a result, the topics of AR related research were deduced from 11 topics such as device, network communication, surgery, digital twin, education, serious game, camera/vision, color application, therapy, location accuracy, and interface design. After popularity of metaverse, 6 topics were deduced such as camera/vision, training, digital twin, surgical/surgical, interaction performance, and network communication. We will expect, through this study, to encourage active research on metaverse AR with convergent characteristics in multidisciplinary fields and contribute to giving useful implications to practitioners.

• Journal of the Korean Society of Safety
• /
• v.33 no.2
• /
• pp.52-60
• /
• 2018

This study compares the differences of the fit factor by the order of wearing preference between Particulate filtering facepiece respirators(PFFR) and glasses when participants wore simultaneously and a survey of physical and visual complaint. Recognition level about fit of respirators was investigated and the educational (before- and after-) effect of the fit factor. When participants wore PFFR and glasses, physical complaints were nose pressure, slipping, nose and ear pressure, ear pressure and rim loosen, the most highly physical complaints were nose pressure. Visual complaints were demister, blurry vision, dizziness, visual field, and lens dirty, the most highly visual complaints were demister. But, there was significant difference in physical complaint such as nose pressure(10.3%), slipping (23.0%), nose and ear pressure(14.3%), and rim loosen(16.2%), visual complaint such as visual field(13.8%) and lens dirty(32.4%). For the recognition of fit of respirators, respirators fitness, leak site, an initial point and an object, faulty factor, recognition level was higher. Fit factor was increased after education of proper wearing of respirator. Change of the fit factor was smaller compared to the normal breathing and after 6 actions in case of after education. Questionnaire consisted of general characteristics and physical/visual complaint, recognition of fit. Complaints were measured after the QNFT with multiple choices. Quantitative fit factor was measured by device and compared the result of (before- and after-) educational effect. Also, we selected to 6 actions (Normal breathing, Deep breathing, Bending over, Turning head side to side, Moving head up and down, Normal breathing) among 8 actions OSHA QNFT (Quantitative Fit testing) protocol to measure the fit factors. The fit factor was higher after the training (p=0.000). Descriptive statistics, paired t-test, and Wilcoxon analysis were performed to describe the result of questionnaire and fit test. (P=0.05) Therefore, it is necessary to investigate the quantitative research such as training program and glasses fitting factor about the wearing of PFFR and glasses simultaneously.

• Agricultural and Biosystems Engineering
• /
• v.4 no.1
• /
• pp.8-15
• /
• 2003

In Korea, quality evaluation of dried oak mushrooms are done first by classifying them into more than 10 different categories based on the state of opening of the cap, surface pattern, and colors. And mushrooms of each category are further classified into 3 or 4 groups based on its shape and size, resulting into total 30 to 40 different grades. Quality evaluation and sorting based on the external visual features are usually done manually. Since visual features of mushroom affecting quality grades are distributed over the entire surface of the mushroom, both front (cap) and back (stem and gill) surfaces should be inspected thoroughly. In fact, it is almost impossible for human to inspect every mushroom, especially when they are fed continuously via conveyor. In this paper, considering real time on-line system implementation, image processing algorithms utilizing artificial neural network have been developed for the quality grading of a mushroom. The neural network based image processing utilized the raw gray value image of fed mushrooms captured by the camera without any complex image processing such as feature enhancement and extraction to identify the feeding state and to grade the quality of a mushroom. Developed algorithms were implemented to the prototype on-line grading and sorting system. The prototype was developed to simplify the system requirement and the overall mechanism. The system was composed of automatic devices for mushroom feeding and handling, a set of computer vision system with lighting chamber, one chip microprocessor based controller, and pneumatic actuators. The proposed grading scheme was tested using the prototype. Network training for the feeding state recognition and grading was done using static images. 200 samples (20 grade levels and 10 per each grade) were used for training. 300 samples (20 grade levels and 15 per each grade) were used to validate the trained network. By changing orientation of each sample, 600 data sets were made for the test and the trained network showed around 91 % of the grading accuracy. Though image processing itself required approximately less than 0.3 second depending on a mushroom, because of the actuating device and control response, average 0.6 to 0.7 second was required for grading and sorting of a mushroom resulting into the processing capability of 5,000/hr to 6,000/hr.