Micro Expression With Deep Learning
Experimentation of deep learning on the subjects of micro-expression spotting and recognition.
Overview:
The DSSN-MERCode is a deep learning experiment focusing on micro-expression spotting and recognition. The project requires Ubuntu 16.04 as the platform and dependencies include Python 3.6, Keras 2.0.6, Opencv 3.1.0, pandas 0.19.2, and CuDNN 5110. The README file contains information on missing files, additional tools, and external resources related to optical flow and facial landmarks extraction.
Features:
- Deep Learning Experimentation: Utilizes deep learning techniques for micro-expression spotting and recognition.
- Platform Compatibility: Designed for Ubuntu 16.04 with Python 3.6 and specific dependency versions.
- External Tools: Includes scripts for optical flow feature extraction and tools for facial landmarks extraction.
Summary:
The DSSN-MERCode project provides a platform for experimenting with deep learning techniques for micro-expression analysis. With specific dependencies and tools for feature extraction, this project offers a detailed guide on setting up the environment and running the training scripts. By following the recommended installation steps and utilizing the provided parameters, researchers can leverage this project for their own micro-expression recognition works.