Face verification using convolutional neural networks with Siamese architecture

Bukovcikova, Zuzana; Sopiak, Dominik; Oravec, Milos; Pavlovičová, Jarmila

doi:10.23919/elmar.2017.8124469

Cited by 14 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And the number of convolution kernels of each layer is 64, 128, 128, 256 and the size of the output is 256. Reference [26] used a simple multi-layer perceptron classifier to replace the original cost function and achieved a good face recognition effect. The training process is shown in Fig.…”

Section: E Imiscnn Compared With Classic Arithmeticmentioning

confidence: 99%

“…Meanwhile, this network had a very good generalization ability. Bukovcikova et al [26] used a simple multi-layer perceptron classifier to replace the original cost function and achieved a good face recognition effect.…”

Section: Introductionmentioning

confidence: 99%

“…FIGURE 14.Comparison results of paper[26], original SNN[33], and IMISCNN and partial enlargement of the results.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Research on Inception Module Incorporated Siamese Convolutional Neural Networks to Realize Face Recognition

Zhang

Duan

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Face recognition is an active research subject of biometrics due to its significant research and application prospects. The performance of face recognition can be affected by a series of uncontrollable factors, such as illumination, expression, posture and occlusion, which restricts its real-world applications. Therefore, improving the robustness of face recognition to environmental changes became an urgent problem. In this paper, a simplified deep convolutional neural network structure having high robustness under unlimited conditions is designed for face recognition. This structure can improve training speed and face recognition accuracy, and be suitable for small-scale data sets. Inception Module Incorporated Siamese Convolutional Neural Networks (IMISCNN) is developed based on effective reduction of external interference and better features extraction by adopting the Siamese network structure. A cyclical learning rate strategy is also introduced in IMISCNN for better model convergence. Compared to classical face recognition algorithms, such as PCA, PCA and SVM, CNN, PCANet, and the original SNN et al. The accuracy of IMISCNN in CASIA-webface and Extended Yale B standard face database is 99.36% and 99.21%, respectively. Its feasibility and effectiveness have been verified in our experiments. INDEX TERMS Cyclical learning rate, face recognition, inception module, Siamese convolutional neural networks.

show abstract

Section: E Imiscnn Compared With Classic Arithmeticmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Research on Inception Module Incorporated Siamese Convolutional Neural Networks to Realize Face Recognition

Zhang

Duan

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…To utilize the client identity information for face liveness detection, we use the Siamese network, which is proposed in [10] and modified for face verification in [11] [13]. Siamese Network is a class of neural network architectures that contain two or more subnetworks.…”

Section: B Siamese Networkmentioning

confidence: 99%

Face Liveness Detection Based on Client Identity Using Siamese Network

Hao

Pei

Zhao

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Face liveness detection is an essential prerequisite for face recognition applications. Previous face liveness detection methods usually train a binary classifier to differentiate between a fake face and a real face before face recognition. The client identity information is not utilized in previous face liveness detection methods. However, in practical face recognition applications, face spoofing attacks are always aimed at a specific client, and the client identity information can provide useful clues for face liveness detection. In this paper, we propose a face liveness detection method based on the client identity using Siamese network. We detect face liveness after face recognition instead of before face recognition, that is, we detect face liveness with the client identity information. We train a Siamese network with image pairs. Each image pair consists of two real face images or one real and one fake face images. The face images in each pair come from a same client. Given a test face image, the face image is firstly recognized by face recognition system, then the real face image of the identified client is retrieved to help the face liveness detection. Experiment results demonstrate the effectiveness of our method.

show abstract

“…The best accuracy obtained is 90.61% using a dataset of 150,000. Researchers in [13] conducted other studies using SCNN to do face verification using celebA dataset which consists of 202,599 face images. An accuracy of 85.78% is obtained.…”

Section: Introductionmentioning

confidence: 99%

Implementation of Siamese Convolutional Neural Network from Cell Images for Malaria Disease Identification

Devani¹

2020

IJATCSE

View full text Add to dashboard Cite

Malaria is contagious and transmitted through Anopheles mosquito. This disease caused about 435,000 people died in 2017. Therefore, it is considered as a dangerous disease. This research aims to implement Siamese Convolutional Neural Network (SCNN) to identify malaria using a collection ofhuman cell images. SCNN is an architecture that uses two convolutional neural networks with the same configurations. Input data for this network are two paired images, where the first is the reference image and the second one is a test image and will produce a similarity score consisting of the numbers 0-1.The data uses in this research is consisted of two classes, namely, parasitized and uninfected. Based on trials that have been carried out, we decide to create SCNNmodel whichis utilizing a pre-trained ImageNet VGG16and a fully connected network with a single hidden layer. Hyperparameter and parameter used are fixed and not all hyperparameter are used. Testing is done by changing the number of reference images and the number of training images. The best accuracy result obtained by using siamese convolutional neural network model is 94.35%.

show abstract

Face verification using convolutional neural networks with Siamese architecture

Cited by 14 publications

References 9 publications

Research on Inception Module Incorporated Siamese Convolutional Neural Networks to Realize Face Recognition

Research on Inception Module Incorporated Siamese Convolutional Neural Networks to Realize Face Recognition

Face Liveness Detection Based on Client Identity Using Siamese Network

Implementation of Siamese Convolutional Neural Network from Cell Images for Malaria Disease Identification

Contact Info

Product

Resources

About