• Home
  • Search
  • A Fast and Accurate Face Alignment Method Based on Deep Learning on Mobile Device
  • https://doi.org/10.1109/icccbda49378.2020.9095563Copy DOI Icon

A Fast and Accurate Face Alignment Method Based on Deep Learning on Mobile Device

  • Apr 1, 2020
  • Huaping Liu
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Face alignment is a crucial prerequisite for many face analysis applications. Hence, the algorithm with high speed, high precision and small model becomes very important for applications on mobile devices. Addressing this issue, we propose a new lightweight face alignment method which could run fast on mobile devices by coarse-to-fine deep convolution network. For a given face image, our method firstly detects face landmarks by a global convolutional network to predict initial local landmarks with rich texture and accurate residue landmarks. Then the second local network is used to adjust the accuracy of local landmarks according to the initial locations. Simultaneously, for video-based face alignment, we proposed a simple but effective tracking method by using LK optical flow to ensure the accuracy and stability of facial landmark in video.

Similar Papers
  • Book Chapter

Face Alignment by Coarse-to-Fine Deep Convolution Network on Mobile Device

  • Jul 21, 2020
  • Huaping Liu
  • Research Article
  • Citations22

Face alignment using a deep neural network with local feature learning and recurrent regression

  • Jul 13, 2017
  • Expert Systems with Applications
  • Byung-Hwa Park +2
  • PDF
  • Research Article
  • Citations6

Multi-feature shape regression for face alignment

  • Aug 02, 2018
  • EURASIP Journal on Advances in Signal Processing
  • Wei-Jong Yang +3
  • Conference Article
  • Citations83

Convolutional aggregation of local evidence for large pose face alignment

  • Jan 01, 2016
  • Adrian Bulat +1
  • Book Chapter
  • Citations4

Advances and Trends in Video Face Alignment

  • Dec 15, 2018
  • Gang Zhang +3
  • Conference Article

A Survey for Conventional Regression- and Deep Learning-based Face Alignment Methods

  • Feb 19, 2021
  • 2021 International Symposium on Electrical, Electronics and Information Engineering
  • Tongxuan Gao
  • Conference Article

Low Dimensional Deep Features for facial landmark alignment

  • Mar 01, 2017
  • Ankit Jalan +3
  • Conference Article
  • Citations370

Deep Alignment Network: A Convolutional Neural Network for Robust Face Alignment

  • Jul 01, 2017
  • Marek Kowalski +2
  • Conference Article
  • Citations11

ACR Loss: Adaptive Coordinate-based Regression Loss for Face Alignment

  • Aug 21, 2022
  • Ali Pourramezan Fard +1
  • Conference Article
  • Citations3

An approach to face detection and alignment using hough transformation with convolution neural network

  • Sep 01, 2016
  • Oshin Misra +1
  • Research Article
  • Citations50

Learning Deep Sharable and Structural Detectors for Face Alignment.

  • Jan 23, 2017
  • IEEE Transactions on Image Processing
  • Hao Liu +3
  • Conference Article
  • Citations139

FacePoseNet: Making a Case for Landmark-Free Face Alignment

  • Oct 01, 2017
  • Feng-Ju Chang +5
  • Conference Article
  • Citations154

LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood

  • Jun 01, 2020
  • Abhinav Kumar +8
  • Conference Article
  • Citations11

Joint Head Pose Estimation with Multi-task Cascaded Convolutional Networks for Face Alignment

  • Aug 01, 2018
  • Zhenni Cai +3
  • Conference Article

Illumination Invariant and Component Based Approach for Face Alignment

  • Apr 17, 2006
  • F Kahraman +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.