Suggestive GAN for supporting Dysgraphic drawing skills
Abstract
The squat competence of dysgraphia affected students in drawing graphics on paper may deter the normal pace of learning skills of children. Convolutional neural network may tend to extract and stabilize the actionmotion disorder by reconstructing features and inferences on natural drawings. The work in this context is to devise a scalable Generative Adversarial Network system that allows training and compilation of image generation using real time generated images and Google QuickDraw dataset to use quick and accurate modalities to provide feedback to empower the guiding software as an apt substitute for human tutor. The training loss accuracy of both discriminator and generator networks is also compared for the SGAN optimizer.
Keywords
Autoencoder; Dysgraphia generative adversarial; Networks; infoGAN; Suggestive GAN
Full Text:
PDFDOI: http://doi.org/10.11591/ijai.v8.i2.pp132-143
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
IAES International Journal of Artificial Intelligence (IJ-AI)
ISSN/e-ISSN 2089-4872/2252-8938
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).