MINDAURA: An AI Emotion Detector
Keywords:
Convolutional neural network, machine learning multi-modal analysi, sentiment analysis, real-time recognition, mental health, customer serviceAbstract
ABSTRACT
MINDAURA an AI Emotion Detector is an effective form for communicating our affections, understanding, and determined with each one. It is a knowledgeable human-computer interplay science. Various studies have been attended to categorize facial verbalizations. Six fundamental worldwide emotions maybe articulated through first expressions: satisfaction, depression, anger, fearful, startled, and impartial. Our work proposed a CNN-located VGG16 construction for emotion discovery arrangements. A model would be prepared by utilizing the FER-2013 dataset. Then the concepts from the dataset are first pre-processed, that contains operations to a degree countenance scaling, changeful the colour manner, and so on. Following that, a CNN model accompanying diversified layers was founded. After that, the model hopeful trained accompanying the particularized dataset, developing in the .h5 file, which is a pre-prepared model file. Instead of many times training the model, the results maybe anticipated using this file. Based on recommendation, sympathy can be categorised as either they are satisfied, sad, irritated, afraid, startled, or neutral; and it is again directed on the real-period reasoning of people's questions and providing resolutions based on their sentiments; that is, it will automatically play a program-located solution when it detects if the woman is being depressed, furious, or afraid.
Downloads
References
1. Ning Zhou, Renyu Liang, and Wenqian Shi (2020), “A Lightweight Convolutional Neural Network for Real-Time Facial Expression Detection”, IEEE Access, vol. 9, pp. 5573-5584.
2. Aya Hassouneh, Mutawa A.M., and Murugappan M. (2020), “Development of a Real-Time Emotion Recognition System using Facial Expression and EEG based on machine learning and deep neural
network methods”, Science Direct on Informatics in Medicine Unlocked, vol. 20.
3. Yuanyuan Ding, Qin Zhao, Baoqing Li, and Xiaobing Yuan (2017), “Facial Expression Recognition from Image Sequence Based on LBP and Taylor Expansion”, IEEE Access, vol. 5, pp. 19409-19419.
4. Biao Yang, Jinmeng Cao, Rongrong Ni, and Yuyu Zhang (2017), “Facial Expression Recognition using Weighted Mixture Deep Neural Network Based on Double-Channel Facial Images”, IEEE Access, vol. 6, pp. 4630-4650.
5. [5]Ithaya Rani P., and Muneeswaran K. (2018), “Emotion Recognition based on facial components”, Indian Academy of Science.
6. Guihua Wen, Tianyuan Chang, Huihui Li, and Lijun Jiang (2020), “Dynamic Objectives Learning for Facial Expression Recognition”, IEEE Transactions on Multimedia, vol. 22, pp. 2914-2925.
7. Pawel Tarnowski, Marcin Kolodziej, Andrzej Majkowski, and Remigiusz J. Rak (2017), “Emotion recognition using facial expression”, Science Direct on Procedia Computer Science, vol. 108, pp. 1175- 1184.
8. Charvi Jain, Kshitij Sawant, Mohammed Rehman, and Rajesh Kumar (2018), “Emotion Detection and characterization using Facial Features”, 3rd International Conference and workshops on Recent Advance and Innovations in Engineering (ICRAIE).
9. Shivam Gupta (2018), “Facial emotion recognition in real-time and static images”, 2nd International Conference on Inventive System and Control (ICISC).
10. Leonid Ivanovsky, Vladimir Khryashchev, Anton Lebedev, and Igor Kosterin (2017), “Facial Expression Recognition Algorithm Based on Deep Convolution Neural Network”, 21st Conference of Open Innovations Association (FRUCT).
11. [11] Sanghyuk Kim, Gwon Hwan An, and Suk-Ju Kang (2017), “Facial Expression Recognition System using Machine Learning”, International SoC Design Conference (ISOCC).
12. Alaramzana Nujun Navaz, Serhani Mohamed Adel, and Sujith Samuel Mthew (2019), “Facial Image Pre-Processing and Emotion Classification: A Deep learning Approach”, IEEE/ACS 16th International Conference on Computer Systems and Applications (AICCSA).
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal for Research Publication and Seminar
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
