Welcome to the InfoSci Platform
Reference Hub3
Compound Facial Expression Recognition and Pain Intensity Measurement Using Optimized Deep Neuro Fuzzy Network

Compound Facial Expression Recognition and Pain Intensity Measurement Using Optimized Deep Neuro Fuzzy Network

Rohan Appasaheb Borgalli, Sunil Surve
Copyright: © 2022 |Volume: 13 |Issue: 1 |Pages: 27
ISSN: 1947-9263|EISSN: 1947-9271|EISBN13: 9781683181514|DOI: 10.4018/IJSIR.304721
Cite Article Cite Article

MLA

Borgalli, Rohan Appasaheb, and Sunil Surve. "Compound Facial Expression Recognition and Pain Intensity Measurement Using Optimized Deep Neuro Fuzzy Network." IJSIR vol.13, no.1 2022: pp.1-27. http://doi.org/10.4018/IJSIR.304721

APA

Borgalli, R. A. & Surve, S. (2022). Compound Facial Expression Recognition and Pain Intensity Measurement Using Optimized Deep Neuro Fuzzy Network. International Journal of Swarm Intelligence Research (IJSIR), 13(1), 1-27. http://doi.org/10.4018/IJSIR.304721

Chicago

Borgalli, Rohan Appasaheb, and Sunil Surve. "Compound Facial Expression Recognition and Pain Intensity Measurement Using Optimized Deep Neuro Fuzzy Network," International Journal of Swarm Intelligence Research (IJSIR) 13, no.1: 1-27. http://doi.org/10.4018/IJSIR.304721

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

The automatic measurement of pain intensity from facial expressions, mainly from face images describes the patient’s health. Hence, a robust technique, named Water Cycle Henry Gas Solubility Optimization-based Deep Neuro Fuzzy Network (WCHGSO-DNFN) is designed for compound FER and pain intensity measurement. However, the proposed WCHGSO is the incorporation of Water Cycle Algorithm (WCA) with Henry Gas Solubility Optimization (HGSO). Here, Compound Facial Expressions of Emotion Database (dataset-2) is made to perform compound FER, whereas the input image from UNBC pain intensity dataset (dataset-1) is utilized to measure the pain intensity, and the processes are performed separately. The developed technique achieved better performance with respect to testing accuracy, sensitivity, and specificity with the highest values of 0.814, 0.819, and 0.806 using dataset-1, whereas maximum values of 0.815, 0.758 and 0.848 is achieved using dataset-2.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.