• NANDANI SHARMA
• Peeyush Kumar Pathak
• Deepali Verma

With the progress of Facial Expression Recognition (FER) from research laboratory- controlled to testing in-the-wild conditions and the new accomplishment of Deep learning strategies in different fields, deep neural Networks have progressively been utilized to learn discriminative portrayals for programmed FER. Ongoing Deep FER frameworks for the most part center on different significant issues and difficulties: Imbalance, intra-class varieties, Illumination and differentiation over-fitting, and so forth brought about by an absence of adequate preparing datasets like FRE2013, CK+, AffectNet, EmotioNet, MMI, and so on. In this overview paper, Firstly present the accessible datasets that are generally utilized in the writing and give acknowledged information determination and assessment standards for these datasets and then focused on the issues and challenges with FER and provide the solution with respect to issues and challenges and summarized with competitive performances based on the static and dynamic images.

Facial Expression Recognition, Deep Neural Networks, FER2013, CK+, AffectNet, EmotioNet, MMI , CNN, convolutional neural network

"A Survey Paper on Issues and Challenges in Facial Expression Recognition with solution.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 7, page no.f814-f824, July-2021, Available :http://www.jetir.org/papers/JETIR2106815.pdf

"A Survey Paper on Issues and Challenges in Facial Expression Recognition with solution.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 7, page no. ppf814-f824, July-2021, Available at : http://www.jetir.org/papers/JETIR2106815.pdf