• Vaishali A Damor
• Prof. ShikhaMaan

Facial emotion recognition is one of the rational theory-practical study that takes attention in the field of both machine learning and deep learning. For many years multiple emotions have been labeled based on different datasets of different region’s faces. People infer the emotional states of other people, such as joy, sadness, and anger, using facial expressions and vocal tone. Many Hybrid techniques have been evaluated for better accuracy. The proposed research is aimed to detect 3 novel emotions. The algorithm is divided into 3 parts. The first phase of algorithm is to construct a unique representation of each emotion with firefly algorithmfor feature optimization, while the second phase is using a convolutional neural network (CNN) for feature extraction and 3rd phase is using PCA for feature selection. These methods were Trained on the posed-emotion dataset CK+, and to test their robustness. The results show that with more fine-tuning and depth, our proposed model can perform better than the other existing methods for emotion recognition. The parameters to prove our point will be accuracy, precision and recall.New emotion can be : confused & contempt,frustrated.

Modified firefly Algorithm, PCA, Deep learning approach, Facial expression Recognition

"Detection of Facial expression recognition using modified Firefly Algorithm with CNN for multi model optimization", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.160-166, May-2019, Available :http://www.jetir.org/papers/JETIR1905H27.pdf

"Detection of Facial expression recognition using modified Firefly Algorithm with CNN for multi model optimization", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp160-166, May-2019, Available at : http://www.jetir.org/papers/JETIR1905H27.pdf