CNN-BLSTM Joint Technique on Dynamic Shape and Appearance of FACS
Nazmin Begum1, A Syed Mustafa2

1Mrs. Nazmin Begum*, Assistant Professor, Department of Computer Science & Engineering, Dayananda Sagar University, Bengaluru, Karnataka , India.
2Dr. Syed Mustafa, Professor and Head of the Department, Department of ISE, HKBK College of Engineering, Bengaluru, Karnataka , India.
Manuscript received on March 28, 2020. | Revised Manuscript received on April 25, 2020. | Manuscript published on April 30, 2020. | PP: 1754-1757 | Volume-9 Issue-4, April 2020. | Retrieval Number: D7308049420/2020©BEIESP | DOI: 10.35940/ijeat.D7308.049420
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Facial recognition is a process where we can identify or verify a person from digital image or videos and is used in ID verification services , protecting law enforcement ,preventing retail crime etc. Past work on automatic analysis of facial expression focuses on detecting the facial expression and exploiting the dependencies among AU’s. But, spontaneous detection of facial expression depending on various factors such as shape, appearance and dynamics is very difficult. Joint learning of shape , appearance and dynamics is done by a deep learning technique. This includes a convolutional neural networks and bidirectional long short term memory(CNN-BLSTM). This combination of CNN-BLSTM excels the modeling of temporal information. FERA2015 dataset achieves the state of art.
Keywords: Bidirectional LSTM, Convolutional Neural Networks, Face Recognition.