Deep Stacked Autoencoder-Based Automatic Emotion Recognition Using an Efficient Hybrid Local Texture Descriptor | IGI Global Scientific Publishing
Welcome to the InfoSci Platform
Deep Stacked Autoencoder-Based Automatic Emotion Recognition Using an Efficient Hybrid Local Texture Descriptor

Deep Stacked Autoencoder-Based Automatic Emotion Recognition Using an Efficient Hybrid Local Texture Descriptor

Shanthi Pitchaiyan, Nickolas Savarimuthu
Copyright: © 2022 |Volume: 15 |Issue: 1 |Pages: 26
ISSN: 1938-7857|EISSN: 1938-7865|EISBN13: 9781683180340|DOI: 10.4018/JITR.2022010103
Cite Article Cite Article

MLA

Pitchaiyan, Shanthi, and Nickolas Savarimuthu. "Deep Stacked Autoencoder-Based Automatic Emotion Recognition Using an Efficient Hybrid Local Texture Descriptor." JITR vol.15, no.1 2022: pp.1-26. https://doi.org/10.4018/JITR.2022010103

APA

Pitchaiyan, S. & Savarimuthu, N. (2022). Deep Stacked Autoencoder-Based Automatic Emotion Recognition Using an Efficient Hybrid Local Texture Descriptor. Journal of Information Technology Research (JITR), 15(1), 1-26. https://doi.org/10.4018/JITR.2022010103

Chicago

Pitchaiyan, Shanthi, and Nickolas Savarimuthu. "Deep Stacked Autoencoder-Based Automatic Emotion Recognition Using an Efficient Hybrid Local Texture Descriptor," Journal of Information Technology Research (JITR) 15, no.1: 1-26. https://doi.org/10.4018/JITR.2022010103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Extracting an effective facial feature representation is the critical task for an automatic expression recognition system. Local Binary Pattern (LBP) is known to be a popular texture feature for facial expression recognition. However, only a few approaches utilize the relationship between local neighborhood pixels itself. This paper presents a Hybrid Local Texture Descriptor (HLTD) which is derived from the logical fusion of Local Neighborhood XNOR Patterns (LNXP) and LBP to investigate the potential of positional pixel relationship in automatic emotion recognition. The LNXP encodes texture information based on two nearest vertical and/or horizontal neighboring pixel of the current pixel whereas LBP encodes the center pixel relationship of the neighboring pixel. After logical feature fusion, the Deep Stacked Autoencoder (DSA) is established on the CK+, MMI and KDEF-dyn dataset and the results show that the proposed HLTD based approach outperforms many of the state of art methods with an average recognition rate of 97.5% for CK+, 94.1% for MMI and 88.5% for KDEF.