首页|Dr. Vishwanath Karad MIT World Peace University Researchers Describe New Finding s in Artificial Intelligence (FER-BHARAT: a lightweight deep learning network fo r efficient unimodal facial emotion recognition in Indian context)
Dr. Vishwanath Karad MIT World Peace University Researchers Describe New Finding s in Artificial Intelligence (FER-BHARAT: a lightweight deep learning network fo r efficient unimodal facial emotion recognition in Indian context)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators discuss new findings in artificial intelligence. According to news originating from Dr. Vishwanath Karad MIT World Peace University by NewsRx editors, the research stated, “Humans’ abi lity to manage their emotions has a big impact on their ability to plan and make decisions.” Our news reporters obtained a quote from the research from Dr. Vishwanath Karad MIT World Peace University: “In order to better understand people and improve hu man-machine interaction, researchers in affective computing and artificial intel ligence are investigating the detection and recognition of emotions. However, di fferent cultures have distinct ways of expressing emotions, and the existing emo tion recognition datasets and models may not effectively capture the nuances of the Indian population. To address this gap, this study proposes custom-built lig htweight Convolutional Neural Network (CNN) models that are optimized for accura cy and computational efficiency. These models are trained and evaluated on two I ndian emotion datasets: The Indian Spontaneous Expression Dataset (ISED) and the Indian Semi Acted Facial Expression Database (iSAFE). The proposed CNN model wi th manual feature extraction provides remarkable accuracy improvement of 11.14% for ISED and 4.72% for iSAFE datasets as compared to baseline, whi le reducing the training time. The proposed model also surpasses the accuracy pr oduced by pre-trained ResNet-50 model by 0.27% ISED and by 0.24% for the iSAFE dataset with significant improvement in training time of approxima tely 320 s for ISED and 60 s for iSAFE dataset.”
Dr. Vishwanath Karad MIT World Peace Uni versityArtificial IntelligenceMachine Learning
NETL
NSTL
