A comprehensive analysis of Local Binary Convolutional Neural Network for fast face recognition in surveillance video

Ferraz, Carolina Toledo; Saito, José Hiroki

doi:10.1145/3243082.3267444

Cited by 6 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Binarized networks have sparked many studies on binary deep models for fast FER tasks. For example, Ferraz et al [ 33 ] proposed a local binary CNN which reduced the number of parameters in the model and performed well during training. Kumawat et al [ 34 ] proposed a novel local binary volume CNN, which, however, ignored the relationships between facial expressions and muscle movements.…”

Section: Introductionmentioning

confidence: 99%

VaBTFER: An Effective Variant Binary Transformer for Facial Expression Recognition

Shen,

Jin

2023

Sensors

View full text Add to dashboard Cite

Existing Transformer-based models have achieved impressive success in facial expression recognition (FER) by modeling the long-range relationships among facial muscle movements. However, the size of pure Transformer-based models tends to be in the million-parameter level, which poses a challenge for deploying these models. Moreover, the lack of inductive bias in Transformer usually leads to the difficulty of training from scratch on limited FER datasets. To address these problems, we propose an effective and lightweight variant Transformer for FER called VaTFER. In VaTFER, we firstly construct action unit (AU) tokens by utilizing action unit-based regions and their histogram of oriented gradient (HOG) features. Then, we present a novel spatial-channel feature relevance Transformer (SCFRT) module, which incorporates multilayer channel reduction self-attention (MLCRSA) and a dynamic learnable information extraction (DLIE) mechanism. MLCRSA is utilized to model long-range dependencies among all tokens and decrease the number of parameters. DLIE’s goal is to alleviate the lack of inductive bias and improve the learning ability of the model. Furthermore, we use an excitation module to replace the vanilla multilayer perception (MLP) for accurate prediction. To further reduce computing and memory resources, we introduce a binary quantization mechanism, formulating a novel lightweight Transformer model called variant binary Transformer for FER (VaBTFER). We conduct extensive experiments on several commonly used facial expression datasets, and the results attest to the effectiveness of our methods.

show abstract

Section: Introductionmentioning

confidence: 99%

VaBTFER: An Effective Variant Binary Transformer for Facial Expression Recognition

Shen,

Jin

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Kegunaan dari penelitian ini adalah untuk mendeteksi wajah melalui kamera dan kemudian melakukan pengenalan wajah. Penelitian ini dapat dimanfaatkan di bidang lalu lintas untuk mengenali wajah pelanggar rambu lalu lintas [5] atau untuk penerapan keamanan di sebuah perusahaan dengan menggunakan pengenalan wajah.…”

unclassified

Implementasi Convolutional Neural Network untuk Facial Recognition

Setiawan¹,

Putra²,

Stefani³

et al. 2021

View full text Add to dashboard Cite

Facial recognition merupakan salah satu teknik biometrik. Teknik yang dapat disebut juga pengenalan wajah ini telah menjadi topik yang cukup diminati untuk diteliti. Pada peneitian ini dilakukan proses pengenalan wajah dengan menggunakan metode CNN (Convolutional Neural Network). Penelitian ini memiliki tujuan untuk mengimplementasikan metode CNN ke dalam pengenalan wajah dengan menggunakan library Tensorflow. Metode ini digunakan karena proses pembelajaran dilakukan dengan mendalam (deep learning). Metode CNN yang digunakan memiliki beberapa lapisan pada proses training yang dilakukan, yaitu lapisan Conv2D, MaxPooling2d, Flatten, dan Dense. Face recognition yang dihasilkan terdapat pendeteksi wajah menggunakan Haar Cascade dengan bantuan library Opencv di dalamnya. Jumlah dataset juga diketahui dapat mempengaruhi hasil pengenalan dan proses pengenalan wajah dengan CNN juga memerlukan dataset yang besar. Adapun jumlah citra wajah yang digunakan dalam penelitian ini sebanyak 90.000 gambar wajah yang berasal dari 36 himpunan gambar dan menghasilkan tingkat akurasi sebesar 97%.

show abstract