A Computational Intelligence Approach to Emotion Recognition from the Lip-Contour of a Subject

Halder, Arijit; Shaw, Srishti; Orea, Kanika; Bhowmik, Pavel; Chakraborty, Aruna; Konar, Amit

doi:10.1007/978-3-642-30621-1_15

Cited by 1 publication

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results reported in (Halder et al ., ) by the research group that developed this database at Jadavpur University showed an average accuracy of 85.11%, whereas the method proposed in this work could achieve an average accuracy of 89.63%. This experimentation further validates the usefulness of the proposed method.…”

Section: Experiments and Resultsmentioning

confidence: 70%

“…Zhang et al showed that the generalized feature extraction plus selection strategy can outperform geometry-based regional features, specially formulated for emotion recognition. For further validation of this observation, experiments have also been performed on the facial emotion database developed by the Robot Vision Lab in the ETCE Department of Jadavpur University, Kolkata, India (Halder et al, 2013). This database consists of five different emotions (Anger, Happy, Disgust, Fear and Sad) and one Neutral expression with 10 instances of each of the six expressions per person.…”

Section: End For End For Until (T = T) Endmentioning

confidence: 99%

“…The algorithm finally performs the classification task, based on the extracted features, by utilising the popular back propagation-based artificial neural network (ANN) algorithm. The proposed method is evaluated on the standard Japanese Female Facial Expression (JAFFE) database (Michael, 1997) and also on facial expression database developed at the Electronics and Telecommunication Engineering (ETCE) Department of Jadavpur University (Halder et al, 2013). A detailed comparison with several state-of-the-art, competing algorithms that exist for similar emotion recognition problems comprehensively prove that our algorithm could significantly outperform these algorithms.…”

Section: Introductionmentioning

confidence: 99%

“…However, depending on the nature of the features extracted, the processes can be of mainly two types. The first approach deals with local features concentrating on those facial regions (usually the lips and the eyes), which are more expressive to emotion variation (Youssif & Asker, 2011;Halder et al, 2013). Thus, the features extracted in this approach generally have higher discriminating characteristics but require involved feature extraction procedures (like contour detections of lips and/or eyes, etc.).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automated emotion recognition employing a novel modified binary quantum‐behaved gravitational search algorithm with differential mutation

et al. 2015

Self Cite

View full text Add to dashboard Cite

The present paper proposes a supervised learning based automated human facial emotion recognition strategy with a feature selection scheme employing a novel variation of the gravitational search algorithm (GSA). The initial feature set is generated from the facial images by using the 2-D discrete cosine transform (DCT) and then the proposed modified binary quantum GSA with differential mutation (MBQGSA-DM) is utilized to select a sub-set of features with high discriminative power. This is achieved by minimising the cost function formulated as the ratio of the within class and interclass distances. The overall system performs its final classification task based on selected feature inputs, utilising a back propagation based artificial neural network (ANN). Extensive experimental evaluations are carried out utilising a standard, benchmark emotion database, that is, Japanese Female Facial Expresssion (JAFFE) database and the results clearly indicate that the proposed method outperforms several existing techniques, already known in literature for solving similar problems. Further validation has also been carried out on a facial expression database developed at Jadavpur University, Kolkata, India and the results obtained further strengthen the notion of superiority of the proposed method.Keywords: discrete cosine transform (DCT), gravitational search algorithm (GSA), modified binary quantum gravitational search algorithm with differential mutation (MBQGSA-DM), artificial neural network (ANN)

show abstract

Section: Experiments and Resultsmentioning

confidence: 70%

Section: End For End For Until (T = T) Endmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations