Deep Learning For Smile Recognition

@article{Glauner2016DeepLF,
  title={Deep Learning For Smile Recognition},
  author={Patrick O. Glauner},
  journal={ArXiv},
  year={2016},
  volume={abs/1602.00172}
}
Inspired by recent successes of deep learning in computer vision, we propose a novel application of deep convolutional neural networks to facial expression recognition, in particular smile recognition. A smile recognition test accuracy of 99.45% is achieved for the Denver Intensity of Spontaneous Facial Action (DISFA) database, significantly outperforming existing approaches based on hand-crafted features with accuracies ranging from 65.55% to 79.67%. The novelty of this approach includes a… 
2 Citations

Figures and Tables from this paper

Emotion Recognition of Facial Expression Using Convolutional Neural Network

This paper is going to train the machine to recognize different types of emotions through human facial expressions using the Convolutional Neural Network, and has used sequential forward selection algorithms and softmax activation function.

Holographic Visualisation of Radiology Data and Automated Machine Learning-based Medical Image Segmentation

Within this thesis we propose a platform for combining Augmented Reality (AR) hardware with machine learning in a user-oriented pipeline, offering to the medical staff an intuitive 3D visualization

References

SHOWING 1-9 OF 9 REFERENCES

Deep learning based FACS Action Unit occurrence and intensity estimation

A novel application of a deep convolutional neural network (CNN) to recognize AUs as part of FERA 2015 challenge is proposed and two different networks are trained for the selected tasks, allowing a single network architecture that could simultaneously be trained to produce binary and continuous classification output.

DISFA: A Spontaneous Facial Action Intensity Database

To meet the need for publicly available corpora of well-labeled video, the Denver intensity of spontaneous facial action database is collected, ground-truthed, and prepared for distribution.

Deep Neural Networks for Acoustic Modeling in Speech Recognition

This paper provides an overview of this progress and repres nts the shared views of four research groups who have had recent successes in using deep neural networks for a coustic modeling in speech recognition.

Dropout: a simple way to prevent neural networks from overfitting

It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.

Rectified Linear Units Improve Restricted Boltzmann Machines

Restricted Boltzmann machines were developed using binary stochastic hidden units that learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset.

LeNet-5, convolutional neural networks. http://yann

  • lecun.com/exdb/lenet/. Retrieved: April
  • 2015

Lasagne

  • IEEE Signal Processing Magazine