• 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.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05a
• /
• pp.106-109
• /
• 2004

Many reported methods assume that the faces in an image or an image sequence have been identified and localization. Face detection from image is a challenging task because of variability in scale, location, orientation and pose. In this paper, we present an efficient linear discriminant for multi-view face detection. Our approaches are based on linear discriminant. We define training data with fisher linear discriminant to efficient learning method. Face detection is considerably difficult because it will be influenced by poses of human face and changes in illumination. This idea can solve the multi-view and scale face detection problem poses. Quickly and efficiently, which fits for detecting face automatically. In this paper, we extract face using fisher linear discriminant that is hierarchical models invariant pose and background. We estimation the pose in detected face and eye detect. The purpose of this paper is to classify face and non-face and efficient fisher linear discriminant..

• Transactions of Materials Processing
• /
• v.14 no.8 s.80
• /
• pp.718-724
• /
• 2005

An efficient finite element method has been introduced for analysis of metallic sandwich plates subject to bending moment. A full model 3-point bending FE-analysis shows that the plastic behavior of inner structures appears only at the load point. The unit structures of sandwich plates are defined to numerically calculate the bending stiffness and strength utilizing the recurrent boundary condition for pure bending analysis. The equivalent models with the same bending stiffness and strength of full models are then designed analytically. It is demonstrated that the results of both models are almost the same and the FE-analysis method incorporating the equivalent models can reduce the computation time effectively. The dominant collapse modes are face buckling and face yielding. Since the inner dimpled structures prevent face buckling, sandwich plates with inner dimpled shell structure can absorb more energy than other types of sandwich plates during the bending behavior.

• Geomechanics and Engineering
• /
• v.24 no.4
• /
• pp.399-406
• /
• 2021

It is a key issue in the tunnel design to evaluate the stability of the excavation face. Two efficient analytical models in the context of the limit equilibrium method (LEM) and the limit analysis method (LAM) are used to carry out the deterministic calculations of the safety factor. The safety factor obtained by these two models agrees well with that provided by the numerical modelling by FLAC 3D, but consuming less time. A simple probabilistic approach based on the Mote-Carlo Simulation technique which can quickly calculate the probability distribution of the safety factor was used to perform the probabilistic analysis on the tunnel face stability. Both the cumulative probabilistic distribution and the probability density function in terms of the safety factor were obtained. The obtained results show the effectiveness of this probabilistic approach in the tunnel design.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.402-410
• /
• 2017

For many years, researchers in face description area have been representing and recognizing faces based on different methods that include subspace discriminant analysis, statistical learning and non-statistics based approach etc. But still automatic face recognition remains an interesting but challenging problem. This paper presents a novel and efficient face image representation method based on Optimized Local Ternary Pattern (OLTP) texture features. The face image is divided into several regions from which the OLTP texture feature distributions are extracted and concatenated into a feature vector that can act as face descriptor. The recognition is performed using nearest neighbor classification method with Chi-square distance as a similarity measure. Extensive experimental results on Yale B, ORL and AR face databases show that OLTP consistently performs much better than other well recognized texture models for face recognition.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.6
• /
• pp.783-788
• /
• 2004

Many reported methods assume that the faces in an image or an image sequence have been identified and localization. Face detection from image is a challenging task because of the variability in scale, location, orientation and pose. The difficulties in visual detection and recognition are caused by the variations in viewpoint, viewing distance, illumination. In this paper, we present an efficient linear discriminant for multi-view face detection and face location. We define the training data by using the Fisher`s linear discriminant in an efficient learning method. Face detection is very difficult because it is influenced by the poses of the human face and changes in illumination. This idea can solve the multi-view and scale face detection problems. In this paper, we extract the face using the Fisher`s linear discriminant that has hierarchical models invariant size and background. The purpose of this paper is to classify face and non-face for efficient Fisher`s linear discriminant.

• Proceedings of the IEEK Conference
• /
• 2000.11d
• /
• pp.41-44
• /
• 2000

In this paper, we present an efficient face detection algorithm for locating vertical views of human faces in complex scenes. The algorithm models the distribution of human skin color in YCbCr color space and find various ace candidate regions. Face candidate regions are found by thresholding with predetermined thresholds. For each of these face candidate regions, The sobel edge operator is used to find edge regions. For each edge region, we used an ellipse detection algorithm which is similar to hough transform to refine the candidate region. Finally if a substantial number of he facial features (eye, mouth) are found successfully in the candidate region, we determine he ace candidate region as a face region. e show empirically that the presented algorithm an find the face region very well in the complex scenes.

• Journal of the korean Society of Automotive Engineers
• /
• v.15 no.3
• /
• pp.96-110
• /
• 1993

A procedure has been developed so that a die-face for stamping automobile outer panels can be design and modelled efficiently. The procedure is composed of four parts each of which corresponds to modeling major components of a die-face, i.e. tipped product, blankholder, draw beads, and step draw. The modeling techniques developed specifically for die-face design enable a designer to generate the shape of a die-face quickly with the minimum input, and the resulting models can be used in FEM analysis and NC tool path generation. This will lead to the reductions in lead time and manhours required for the design and manufacture of the stamping dies.

• Journal of Korean Society for Geospatial Information Science
• /
• v.16 no.1
• /
• pp.49-55
• /
• 2008

The face extraction is very important to provide the images of the roads and road sides without the problem of privacy. For face extraction form roadside images, we detected the skin color area by using HSI and YCrCb color models. Efficient skin color detection was achieved by using these two models. We used a connectivity and intensity difference for grouping, skin color regions further we applied shape conditions (rate, area, number and oval condition) and determined face candidate regions. We applied thresholds to region, and determined the region as the face if black part was over 5% of the whole regions. As the result of the experiment 28 faces has been extracted among 38 faces had problem of privacy. The reasons which the face was not extracted were the effect of shadow of the face, and the background objects. Also objects with the color similar to the face were falsely extracted. For improvement, we need to adjust the threshold.

• Journal of the Semiconductor & Display Technology
• /
• v.15 no.2
• /
• pp.61-65
• /
• 2016

Facial feature detection is a fundamental function in the field of computer vision such as security, bio-metrics, 3D modeling, and face recognition. There are many algorithms for the function, active shape model is one of the most popular local texture models. This paper addresses issues related to face detection, and implements an efficient extraction algorithm for extracting the facial feature points to use on iOS platform. In this paper, we extend the original ASM algorithm to improve its performance by four modifications. First, to detect a face and to initialize the shape model, we apply a face detection API provided from iOS CoreImage framework. Second, we construct a weighted local structure model for landmarks to utilize the edge points of the face contour. Third, we build a modified model definition and fitting more landmarks than the classical ASM. And last, we extend and build two-dimensional profile model for detecting faces within input images. The proposed algorithm is evaluated on experimental test set containing over 500 face images, and found to successfully extract facial feature points, clearly outperforming the original ASM.