Intrinsic two-dimensional local structures for micro-expression recognition

An elapsed facial emotion involves changes of facial contour due to the motions (such as contraction or stretch) of facial muscles located at the eyes, nose, lips and etc. Thus, the important information such as corners of facial contours that are located in various regions of the face are crucial t...

Full description

Bibliographic Details
Main Authors: Oh, Y., Le Ngo, A., Phari, R., See, J., Ling, Huo Chong
Format: Conference Paper
Published: 2016
Online Access:http://hdl.handle.net/20.500.11937/47726
_version_ 1848757913145835520
author Oh, Y.
Le Ngo, A.
Phari, R.
See, J.
Ling, Huo Chong
author_facet Oh, Y.
Le Ngo, A.
Phari, R.
See, J.
Ling, Huo Chong
author_sort Oh, Y.
building Curtin Institutional Repository
collection Online Access
description An elapsed facial emotion involves changes of facial contour due to the motions (such as contraction or stretch) of facial muscles located at the eyes, nose, lips and etc. Thus, the important information such as corners of facial contours that are located in various regions of the face are crucial to the recognition of facial expressions, and even more apparent for micro-expressions. In this paper, we propose the first known notion of employing intrinsic two-dimensional (i2D) local structures to represent these features for micro-expression recognition. To retrieve i2D local structures such as phase and orientation, higher order Riesz transforms are employed by means of monogenic curvature tensors. Experiments performed on micro-expression datasets show the effectiveness of i2D local structures in recognizing micro-expressions.
first_indexed 2025-11-14T09:35:38Z
format Conference Paper
id curtin-20.500.11937-47726
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:35:38Z
publishDate 2016
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-477262017-09-13T14:16:26Z Intrinsic two-dimensional local structures for micro-expression recognition Oh, Y. Le Ngo, A. Phari, R. See, J. Ling, Huo Chong An elapsed facial emotion involves changes of facial contour due to the motions (such as contraction or stretch) of facial muscles located at the eyes, nose, lips and etc. Thus, the important information such as corners of facial contours that are located in various regions of the face are crucial to the recognition of facial expressions, and even more apparent for micro-expressions. In this paper, we propose the first known notion of employing intrinsic two-dimensional (i2D) local structures to represent these features for micro-expression recognition. To retrieve i2D local structures such as phase and orientation, higher order Riesz transforms are employed by means of monogenic curvature tensors. Experiments performed on micro-expression datasets show the effectiveness of i2D local structures in recognizing micro-expressions. 2016 Conference Paper http://hdl.handle.net/20.500.11937/47726 10.1109/ICASSP.2016.7471997 restricted
spellingShingle Oh, Y.
Le Ngo, A.
Phari, R.
See, J.
Ling, Huo Chong
Intrinsic two-dimensional local structures for micro-expression recognition
title Intrinsic two-dimensional local structures for micro-expression recognition
title_full Intrinsic two-dimensional local structures for micro-expression recognition
title_fullStr Intrinsic two-dimensional local structures for micro-expression recognition
title_full_unstemmed Intrinsic two-dimensional local structures for micro-expression recognition
title_short Intrinsic two-dimensional local structures for micro-expression recognition
title_sort intrinsic two-dimensional local structures for micro-expression recognition
url http://hdl.handle.net/20.500.11937/47726