US Patent Application 17636074. FEATURE CONVERSION LEARNING DEVICE, AUTHENTICATION DEVICE, FEATURE CONVERSION LEARNING METHOD, AUTHENTICATION METHOD, AND RECORDING MEDIUM simplified abstract
FEATURE CONVERSION LEARNING DEVICE, AUTHENTICATION DEVICE, FEATURE CONVERSION LEARNING METHOD, AUTHENTICATION METHOD, AND RECORDING MEDIUM
Organization Name
Inventor(s)
Masatsugu Ichino of Chofu-shi (JP)
Daisuke Uenoyama of Chofu-shi (JP)
Tsubasa Boura of Chofu-shi (JP)
Takahiro Toizumi of Tokyo (JP)
FEATURE CONVERSION LEARNING DEVICE, AUTHENTICATION DEVICE, FEATURE CONVERSION LEARNING METHOD, AUTHENTICATION METHOD, AND RECORDING MEDIUM - A simplified explanation of the abstract
This abstract first appeared for US patent application 17636074 titled 'FEATURE CONVERSION LEARNING DEVICE, AUTHENTICATION DEVICE, FEATURE CONVERSION LEARNING METHOD, AUTHENTICATION METHOD, AND RECORDING MEDIUM
Simplified Explanation
The abstract describes a device that learns a feature conversion method based on comparing features extracted from images.
- Acquires a high-resolution image and reduces it to a lower resolution image.
- Enlarges the lower resolution image back to the original resolution.
- Extracts features from the original and enlarged images.
- Converts one of the extracted features into a different feature.
- Learns a method for converting features based on comparing the original and converted features.
Original Abstract Submitted
A feature conversion learning device is configured to acquire a first image, reduce the first image to a second image having lower resolution than the first image, enlarge the second image to a third image having the same resolution as the first image, extract a first feature that is a feature of the first image and a second feature, convert the second feature into a third feature, and learn a feature conversion method based on a result of comparing the first feature with the third feature.