US Patent Application 17638900. LEARNING SYSTEM, AUTHENTICATION SYSTEM, LEARNING METHOD, COMPUTER PROGRAM, LEARNING MODEL GENERATION APPARATUS, AND ESTIMATION APPARATUS simplified abstract
LEARNING SYSTEM, AUTHENTICATION SYSTEM, LEARNING METHOD, COMPUTER PROGRAM, LEARNING MODEL GENERATION APPARATUS, AND ESTIMATION APPARATUS
Organization Name
Inventor(s)
Takahiro Toizumi of Tokyo (JP)
LEARNING SYSTEM, AUTHENTICATION SYSTEM, LEARNING METHOD, COMPUTER PROGRAM, LEARNING MODEL GENERATION APPARATUS, AND ESTIMATION APPARATUS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17638900 titled 'LEARNING SYSTEM, AUTHENTICATION SYSTEM, LEARNING METHOD, COMPUTER PROGRAM, LEARNING MODEL GENERATION APPARATUS, AND ESTIMATION APPARATUS
Simplified Explanation
The abstract describes a learning system that can perform machine learning on moving images shot at a low frame rate. Here are the key points:
- The learning system includes a selection unit that chooses certain images from a collection of frames shot at a high frame rate.
- The selected images include at least one image taken outside the focus range.
- An extraction unit extracts a feature amount from the selected images.
- A learning unit uses the extracted feature amount and correct answer information to train the extraction unit.
- The learning process enables the system to perform machine learning on moving images assumed to be shot at a low frame rate.
Original Abstract Submitted
A learning system () comprises: a selection unit () that selects from images corresponding to a plurality of frames shot at a first frame rate, part of the images, the part including an image taken outside a focus range; an extraction unit () that extracts a feature amount from the part of the images; and a learning unit () that performs learning for the extraction unit based on the feature amount extracted and correct answer information indicating a correct answer with respect to the feature amount. According to such a learning system, it is possible to execute machine learning assumed that moving images are shot at a low frame rate.
