Modified chess patterns: handcrafted feature descriptors for facial expression recognition

Abstract

Facial expressions are predominantly important in the social interaction as they convey the personal emotions of an individual. The main task in Facial Expression Recognition (FER) systems is to develop feature descriptors that could effectively classify the facial expressions into various categories. In this work, towards extracting distinctive features, Radial Cross Pattern (RCP), Chess Symmetric Pattern (CSP) and Radial Cross Symmetric Pattern (RCSP) feature descriptors have been proposed and are implemented in a 5 $$\times $$ × 5 overlapping neighborhood to overcome some of the limitations of the existing methods such as Chess Pattern (CP), Local Gradient Coding (LGC) and its variants. In a 5 $$\times $$ × 5 neighborhood, the 24 pixels surrounding the center pixel are arranged into two groups, namely Radial Cross Pattern (RCP), which extracts two feature values by comparing 16 pixels with the center pixel and Chess Symmetric Pattern (CSP) extracts one feature value from the remaining 8 pixels. The experiments are conducted using RCP and CSP independently and also with their fusion RCSP using different weights, on a variety of facial expression datasets to demonstrate the efficiency of the proposed methods. The results obtained from the experimental analysis demonstrate the efficiency of the proposed methods.

Facial emotion recognition with a reduced feature set for video game and metaverse avatars

“…Each accuracy is compared with up to 11 other accuracies from other research. 42,83,84,85,86,87,88,89,90,91 The research's accuracy of 92% on the CK+ dataset compares favourably with other research which varies from 50% to 99%. The Jaffe, ADFES and Oulu-Casia accuracies gained, do compare a little less favourably.…”

“…This benchmark covers four of the image datasets, CK+, Jaffe, ADFES and Oulu‐Casia, as these have been commonly used in other studies. Each accuracy is compared with up to 11 other accuracies from other research 42,83,84,85,86,87,88,89,90,91 …”