Depression Scale Recognition over Fusion of Visual and Vocal Expression using Artificial Intellectual Method
Pratibha Gayke1, Rohini S Kulkarni2

1Pratibha Gayke Shinde*, Assistant Professor, Department of Information Technology, Dr. Vithalrao Vikhe Patil College of Engineering, Ahmednagar, India.
2Rohini S Kulkarni, Department of Computer Science and Engineering, K.L.E. Institute of Technology, Hubli, Visvesvaraya Technological University, Karnataka, India.
Manuscript received on August 25, 2021. | Revised Manuscript received on August 31, 2021. | Manuscript published on September 30, 2021. | PP: 31-35 | Volume-10, Issue-3, September 2021. | Retrieval Number: 100.1/ijrte.C64020910321 | DOI: 10.35940/ijrte.B6402.0910321
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Now a day’s supported visual and audio cues for automatic depression assessment may be a fast emerging research subject. This comprehensive evaluation of existing methodologies focuses on machine learning (ML) algorithm and image processing (IP) algorithm, as documented in over sixty articles over the last ten years. There is a visual indicator of depression, several data collection procedures are used, and finally examined the previous year or existing datasets. In this article describes techniques and algorithms as well as methods for dimensionality reduction, visual feature extraction, regression approaches, and classification decision procedures, and also various fusion tactics. A significant meta-analysis of published data is given, based on performance indicators that are robust to chance, to identify general trends and important pressing concerns for further research using visual and verbal cues alone or in combination with signals for automated depression evaluation The suggested work also used deep learning and natural language processing to estimate depression levels based on current video data.
Keywords: Image Processing, Artificial Intelligence (AI), Machine Learning, Classification Rule, Convolution Neural Networks (CNN), and Natural Language Processing (NLP), etc.