Facial expression analysis with facial expression deformation

Shin, Jongju; Kim, Daijin

doi:10.1109/icpr.2008.4761398

Cited by 13 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the first part, experimental results for the face images from the extended Yale face database B are described. Then, in the second part, for face images which are processed by different illumination compensation methods, we perform the feature point localization by Active Appearance Model (AAM) [18].…”

Section: Experimental Results and Analysismentioning

confidence: 99%

Illumination compensation for facial feature point localization in a single 2D face image

Mao

Chen

et al. 2016

Neurocomputing

View full text Add to dashboard Cite

Section: Experimental Results and Analysismentioning

confidence: 99%

Illumination compensation for facial feature point localization in a single 2D face image

Mao

Chen

et al. 2016

Neurocomputing

View full text Add to dashboard Cite

“…The accuracy looks to be better than the ResNet algorithm in our research. However, the mean error in our proposed work appears to be larger, which must be reduced (Park, Shin, and Kim 2008)…”

mentioning

confidence: 78%

An Efficient Facial Expression Recognition System Using Novel Image Classification by Comparing CNN over Res Net

2022

pnr

View full text Add to dashboard Cite

The aim of this research article is classification of facial expression recognition Convolutional Neural Network (CNN) compared with ResNet yielded better accuracy. Materials and Methods: The data of the facial expressions is taken from the FER2013 available on kaggle.The convolutional neural network (CNN) is the most widely used algorithm for image analysis with best accuracy and ResNet is also an algorithm used here to compare the accuracy of Novel image classification. Results: The Convolution neural network (CNN) produces 82.14% accuracy in predicting facial expressions on the dataset,whereas ResNet produces 78.01% accuracy. Convolutional neural network (CNN) is better than ResNet. With (p<0.05), there is a statistically significant difference between the research groups. Conclusion : Convolutional Neural Network provides better outcomes in accuracy rate when compared to ResNet for predicting facial expressions.

show abstract

“…Currently, many researchers have proposed a number of extraction methods, but deformable models applied for locating the unknown face image are very efficiently to overcome multiple influences. The statistics based parameterized model, especially ASM (Active Shape models) and AAM (Active Appearance models) [14][15] proposed by Cootes, the two classical algorithms have obtained more and more applications especial for features extraction. The two models' advantages include: for one thing, the deformable models can extract object's features precisely.…”

Section: Literature Surveymentioning

confidence: 99%