Deep learning network for face detection

doi:10.1109/icct.2015.7399887

Paper

Deep learning network for face detection

Published 2015 · Y. Xue-yi, Xueting Chen, Huahua Chen

2015 IEEE 16th International Conference on Communication Technology (ICCT)

UNKNOWN SJR score

5

Citations

0

Influential Citations

Full text

Semantic Scholar

Abstract

By the multi-layer nonlinear mapping and the semantic feature extraction of the deep learning, a deep learning network is proposed for face detection to overcome the challenge of detecting faces accurately and rapidly in the non-ideal case. Key to this deep network is that, to better simulate the response for information in the human brain, the status probability of the neuron is used to model the status of the human brain neuron which is a continuous distribution from the most active to the least active. Moreover, the number of the hidden layer's neuron decreases layer-by-layer to eliminate the redundant information of the input data and accelerate the detection speed combining with the skin color detection. Experimental results show that, besides the fast detection speed and strong robustness to face rotation, the proposed method possesses lower false detection rate and lower missing detection rate.

Study Snapshot

Key takeawayThe proposed deep learning network for face detection accurately detects faces in non-ideal cases, with fast detection speed, strong robustness to face rotation, and lower false detection and missing detection rates.

PopulationOlder adults (50-71 years)

Sample size24

MethodsObservational

OutcomesBody Mass Index projections

ResultsSocial networks mitigate obesity in older groups.

Sign up to use Study Snapshot

Consensus is limited without an account. Create an account or sign in to get more searches and use the Study Snapshot.

Create an account

Paper

Deep learning network for face detection

Sign up to use Study Snapshot

References

Citations

Lightweight Deep Learning for Object Detection on Mobile Device

The Convolution Neural Networks (CNN) model in deep learning effectively detects faces in real-time on Android devices, reaching 97.97% accuracy in normal facial conditions and face masks.

A Novel Face Detection Method Based on Over-complete Incoherent Dictionary Learning

The proposed face detection method using incoherent dictionary learning achieves high accuracy rates compared to common classifiers like neural networks and support vector machines.

Facial freckles recognition using convolutional neural network

The proposed convolution neural network-based freckle recognition model achieves 98% accuracy in facial freckle detection and recognition in face images.

Facial Recognition Using Deep Learning Neural Network

This study proposes a facial recognition algorithm using Restricted Boltzmann Machines, deep learning, and deep belief networks, resulting in efficient and improved facial recognition.