A Novel Approach on Motion Estimation for Micro-Expression Recognition Using Phase Only Correlation with All Block Search (POC-ABS)

Abstract

Micro-expression is an expression when a person tries to held or hidden, but the leak of this emotion still occurs in one or two areas of the face or maybe a short expression that across in the whole-face. Not more than 500ms, micro-expressions can be difficult to recognize and detect where the leakage area is located. This study presents a new method to recognize and detect the subtle motion on the facial components area using Phase Only Correlation algorithm with All Block Search (POC-ABS) to estimate the motion of all block areas. This block matching method is proposed by comparing each block in the two frames to determine whether there is movement or not. If the two blocks are identical, then the motion vector value is not displayed, whereas if the blocks are non-identical, the motion vector value of the POC is displayed. The motion vector, which is as a motion feature, estimates whether or not there are movements in the same block. In order to further confirm the reliability of the proposed method, two different classifiers were used for the micro-expression recognition of the CASME II dataset. The highest performance results are for SVM at 94.3 percent and for KNN at 95.6 percent. Finally, this algorithm detects leaks of motion based on the ratio of the motion vectors. The left and right eyebrows are dominant when expressing disgust, sadness, and surprise. Meanwhile, the movements of the right eye and left eye were the most dominant when the happiness expression.

Perbandingan Fase Ekspresi Menggunakan Local Binary Pattern Histogram Untuk Pengenalan Ekspresi Mikro

“…The proposed study contribution is the reduction of the observation area and the comparative analysis of the expression phases, i.e., the onset to offset phase ("fullOAO") and only the onset, apex, and offset phase (OAO). The components of the facial area are the left eyebrow, right eyebrow, right eye, left eye, and mouth [21], [20]. By employing the LBPH method in the feature extraction process, local features in the motion of selected facial areas can be represented.…”

“…The dominant movements are found in two parts of the face, namely in the eyebrow and mouth areas [20]. Meanwhile, according to other studies, observing facial microexpressions in certain areas requires a shorter computation time, and it is more accurate compared to observing the entire face [21]. Detection of facial component areas can be carried out in various ways, one of which is adopting the landmark point method in the formation of facial component areas [22].…”

“…The selected facial areas for microexpression recognition are the left eyebrow, right eyebrow, right eye, left eye, and mouth. Based on previous studies [21], [20], these areas were selected as facial areas for feature extraction. The application of limited facial areas is expected to speed up the recognition process and produce representative feature extraction data for the classification process.…”