Download PDFOpen PDF in browser

Facial Recognition with Emotion Tracking Using CNN

EasyChair Preprint 10107

9 pagesDate: May 12, 2023

Abstract

Emotion detection technology is a related discipline that makes use of comparable gadget learning algorithms to apprehend and interpret the emotions displayed on someone's face. The generation can examine facial expressions, vocal tones, and other physiological signals to determine the emotional kingdom of an individual. This type of information may be used in a wide range of programs, inclusive of marketing, healthcare, and intellectual fitness. One of the primaries that make use of the emotion detection era is in advertising and marketing and advertising Groups can use the era to research the emotional responses of customers to different merchandise and commercials. These statistics can then be used to create extra powerful advertising campaigns that resonate with consumers to an emotional degree. Convolutional Neural Networks have proven notable effectiveness in facial popularity with emotion tracking due to their capability to research and extract features from picture records. CNNs have the capability to become aware of and come across different face features such as the eyes, nostrils, mouth, and eyebrows, and may then use these records to apprehend the emotion displayed in a facial expression. One of the primary benefits of the use of CNNs for facial popularity with emotion monitoring is their capacity to analyze huge datasets. This will allow the community to recognize a wide range of emotions, including diffused expressions that might be ignored by using a human observer.

Keyphrases: CNN, Emotion Detection, Facial Recognition, Machine Learning Algorithms, datasets

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@booklet{EasyChair:10107,
  author    = {Richa Sharma and Gaurav Mukherjee and Mogalapu Chinmai Siva Pavan},
  title     = {Facial Recognition with Emotion Tracking Using CNN},
  howpublished = {EasyChair Preprint 10107},
  year      = {EasyChair, 2023}}
Download PDFOpen PDF in browser