Faculty Publications

Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736

Publications by NITK Faculty

Browse

Filters

20232

Settings

Author: search.filters.author.Adyapady R, R.Subject: search.filters.subject.Ensemble models

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Micro Expression Recognition Using Delaunay Triangulation and Voronoi Tessellation
    (Taylor and Francis Ltd., 2023) Adyapady R, R.; Annappa, B.
    Facial Expression Recognition is a visual cue used for conveying emotions and intentions between human beings. The micro-expressions (MEs) are not visible to the human eye, making it challenging to capture the minute changes in the facial areas as the expressions change. As a result, automating the detection of ME is a challenging task. This work utilizes Delaunay Triangulation and Voronoi Diagram properties to segment Region of Interest (ROI) based on Action Unit indexes. The ROI-based feature extraction aided in improving the performance of the Micro-Expression Recognition (MER) system. The Cross-Database Evaluation (CDE) and Holdout Database Evaluation (HDE) are performed on three publicly available datasets CASMEII, SAMM, and SMIC (HS). The proposed approach resulted in an improved Unweighted Average Recall (UAR) and Unweighted F1 (UF1) scores by 6.09% and 4.36%, respectively. The results obtained with CDE and HDE demonstrate that the proposed model is robust compared to earlier studies. © 2023 IETE.
  • No Thumbnail Available
    Item
    An ensemble approach using a frequency-based and stacking classifiers for effective facial expression recognition
    (Springer, 2023) Adyapady R, R.; Annappa, B.
    Facial Expression Recognition is an essential aspect of human behavior to communicate effectively. A more profound understanding of human behavior, accurate analysis, and interpretation of the emotional content is essential. Hence, facial features play a crucial role as they contain beneficial information about facial expressions. A baseline architecture belonging to the EfficientNet family of models is explored for feature extraction. In this work, two novel strategies, the ensemble model using the frequency-based voting approach (FV-EffNet) and the stacking classifier (SC-EffNet), are proposed to enhance classification results’ performance. The proposed system deals with both profile and frontal pose variations. The combination of deep learning models with a stacking classifier gave the best results of 98.35% and 98.06%, and the frequency-based approach used with the ensemble classifier achieved superior performance of 98.71% and 98.56% on Oulu-CASIA and RaFD datasets, respectively. The experiment results with the proposed methodology showed better performance than previous studies on Oulu-CASIA and RaFD datasets, making it more robust to pose variations. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.