20230037782. METHOD FOR TRAINING ASYMMETRIC GENERATIVE ADVERSARIAL NETWORK TO GENERATE IMAGE AND ELECTRIC APPARATUS USING THE SAME simplified abstract (PHISON ELECTRONICS CORP.)
Contents
- 1 METHOD FOR TRAINING ASYMMETRIC GENERATIVE ADVERSARIAL NETWORK TO GENERATE IMAGE AND ELECTRIC APPARATUS USING THE SAME
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 METHOD FOR TRAINING ASYMMETRIC GENERATIVE ADVERSARIAL NETWORK TO GENERATE IMAGE AND ELECTRIC APPARATUS USING THE SAME - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Original Abstract Submitted
METHOD FOR TRAINING ASYMMETRIC GENERATIVE ADVERSARIAL NETWORK TO GENERATE IMAGE AND ELECTRIC APPARATUS USING THE SAME
Organization Name
Inventor(s)
Yi-Hsiang Ma of New Taipei City (TW)
Szu-Wei Chen of New Taipei City (TW)
Yu-Hung Lin of Miaoli County (TW)
An-Cheng Liu of Taipei City (TW)
METHOD FOR TRAINING ASYMMETRIC GENERATIVE ADVERSARIAL NETWORK TO GENERATE IMAGE AND ELECTRIC APPARATUS USING THE SAME - A simplified explanation of the abstract
This abstract first appeared for US patent application 20230037782 titled 'METHOD FOR TRAINING ASYMMETRIC GENERATIVE ADVERSARIAL NETWORK TO GENERATE IMAGE AND ELECTRIC APPARATUS USING THE SAME
Simplified Explanation
The abstract describes a method for training an asymmetric generative adversarial network (GAN) to generate images, and an electronic apparatus that uses the same. The method involves inputting real images belonging to different categories into the GAN for training. The GAN consists of generators and discriminators. Once trained, the GAN can generate defect images based on input from a specific category.
- A method for training an asymmetric generative adversarial network (GAN) to generate images is provided.
- The GAN includes generators and discriminators.
- Real images from different categories are inputted into the GAN for training.
- The trained GAN can generate defect images based on input from a specific category.
Potential Applications
- Image generation for various purposes such as art, design, or entertainment.
- Automated defect detection in images for quality control in manufacturing processes.
- Data augmentation for training machine learning models.
Problems Solved
- The method provides a way to train a GAN to generate images based on specific categories.
- It allows for the generation of defect images for various applications.
- The GAN can assist in automating the detection of defects in images.
Benefits
- The method enables the generation of images without the need for manual creation.
- It can enhance the efficiency and accuracy of defect detection in images.
- The GAN can be used to augment datasets for machine learning, improving model performance.
Original Abstract Submitted
a method for training an asymmetric generative adversarial network to generate an image and an electronic apparatus using the same are provided. the method includes the following. a first real image belonging to a first category, a second real image belonging to a second category and a third real image belonging to a third category are input to an asymmetric generative adversarial network for training the asymmetric generative adversarial network, and the asymmetric generative adversarial network includes a first generator, a second generator, a first discriminator and a second discriminator. a fourth real image belonging to the second category is input to the first generator in the trained asymmetric generative adversarial network to generate a defect image.
