We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
An Intelligent Facial Recognition System using Stacked Auto Encoder with Convolutional Neural Network (CNN) Approach.
- Authors
Mahendiran, N.
- Abstract
The act of identifying an emotional feeling or state is described as facial expression. It is one of the effective techniques for interperson communication. They serve as indications that regulate interactions with those around. As a result, they are crucial in creating effective relationships. The goal of the facial expression recognition system is to identify the expressions by evaluating the changes in facial characteristics and extracting features from facial images. This system is essential for enhancing computer-human interaction. The majority of facial emotion recognition research mainly relies on a reference face model and well-known facial landmarks. Due to the intricacy of the face musculature, finding the most noticeable facial landmarks can be difficult and requires physical intervention for improved accuracy. Model based approaches need to establish a reference model and complex functions for mapping which takes intense computation time. So, this research work provides a new dimension to deal with the above issues by proposing a Stacked Auto-Encoder with Convolutional Neural Network based approach that does not rely on the landmarks or a reference model. The proposed approach outperforms the existing techniques.
- Subjects
CONVOLUTIONAL neural networks; INTERPERSONAL communication; HUMAN facial recognition software; FEATURE extraction; HUMAN-computer interaction
- Publication
Mapana Journal of Sciences, 2023, Vol 22, p297
- ISSN
0975-3303
- Publication type
Article
- DOI
10.12723/mjs.sp2.17