The Indian Spontaneous Expression Database for Emotion Recognition

Abstract

Abstract-Automatic recognition of spontaneous facial expressions is a major challenge in the field of affective computing. Head rotation, face pose, illumination variation, occlusion etc. are the attributes that increase the complexity of recognition of spontaneous expressions in practical applications. Effective recognition of expressions depends significantly on the quality of the database used. Most well-known facial expression databases consist of posed expressions. However, currently there is a huge demand for spontaneous expression databases for the pragmatic implementation of the facial expression recognition algorithms. In this paper, we propose and establish a new facial expression database containing spontaneous expressions of both male and female participants of Indian origin. The database consists of 428 segmented video clips of the spontaneous facial expressions of 50 participants. In our experiment, emotions were induced among the participants by using emotional videos and simultaneously their self-ratings were collected for each experienced emotion. Facial expression clips were annotated carefully by four trained decoders, which were further validated by the nature of stimuli used and self-report of emotions. An extensive analysis was carried out on the database using several machine learning algorithms and the results are provided for future reference. Such a spontaneous database will help in the development and validation of algorithms for recognition of spontaneous expressions.

Local directional-structural pattern for person-independent facial expression recognition

“…Representative results are shown in Table 1 (see the results in the "Without Noise ( 110 × 150)" column), where we observe better accuracy of the proposed LDSP than other descriptors. We note that the given personindependent results in this table are different from the results presented in the base paper [24], which were produced without ensuring the person-independence.…”

“…The Indian Spontaneous Expression Database (ISED) [24] provides near-frontal spontaneous expressive images with the emotion level for the peak expression frames of all videos. The given peak expression faces of 50 subjects from all the video clips are used in the baseline experiment.…”

“…We test LDSP in the ISED dataset for person-independent facial expression recognition against different descriptions, under our considerations, such as LBP, LDP, LDN, LPTP, and PTP. We use the peak images for this experiment, as done in the baseline method [24], and generate the results for all these descriptors.…”

I Know How You Feel: Emotion Recognition with Facial Landmarks

“…For testing, we use CK+ [10], JAFFE [14] and [11] datasets with face images of over 180 individuals of different genders and ethnic background.…”

“…This simple modification allows our method, dubbed EmotionalDAN, to exploit the location of facial landmarks and incorporate this information into the classification process. By training both terms jointly, we obtain state-of-the-art results on two challenging datasets for facial emotion recognition: CK+ [10] and ISED [11].…”