Micro-Facial Movement Detection Using Individualised Baselines and Histogram-Based Descriptors

Adrian K. Davison, Moi Hoon Yap, Cliff Lansley

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Detecting micro-facial movements in a video sequence is the first step in realising a system that can pick out rapid movements automatically as a person is being recorded. This paper proposes a new method of micro-movement detection by applying Histogram of Oriented Gradients as a feature descriptor on our in-house high-speed video dataset of spontaneous micro facial movements. Firstly the algorithm aligns and crops faces for each video using automatic facial point detection and affine transformation. Then a de-noising algorithm is applied to each video before splitting them into blocks where the Histogram of Oriented Gradient features are calculated for each frame in every video block. The Chi-Squared distance measure is then used to calculate dissimilarity in the spatial appearance between frames at a set interval. The final feature vector is calculated after normalisation of the raw distance values and peak detection is applied to 'spot' micro-facial movements. An individualised baseline threshold is used to determine the value a peak must exceed to be classed as a movement. The result is compared with a benchmark algorithm - feature difference analysis techniques for micro-facial movements using Local Binary Patterns. Results indicate the proposed method achieves higher Recall of 0.8429 and F1-measure of 0.7672.
Original languageEnglish
Title of host publication2015 IEEE International Conference on Systems, Man, and Cybernetics
Number of pages6
ISBN (Electronic)978-1-4799-8697-2
Publication statusPublished - 12 Oct 2015


Dive into the research topics of 'Micro-Facial Movement Detection Using Individualised Baselines and Histogram-Based Descriptors'. Together they form a unique fingerprint.

Cite this