17638897. LEARNING SYSTEM, ESTIMATION SYSTEM, LEARNING METHOD, AND COMPUTER PROGRAM simplified abstract (NEC Corporation)
Contents
LEARNING SYSTEM, ESTIMATION SYSTEM, LEARNING METHOD, AND COMPUTER PROGRAM
Organization Name
Inventor(s)
Takahiro Toizumi of Tokyo (JP)
LEARNING SYSTEM, ESTIMATION SYSTEM, LEARNING METHOD, AND COMPUTER PROGRAM - A simplified explanation of the abstract
This abstract first appeared for US patent application 17638897 titled 'LEARNING SYSTEM, ESTIMATION SYSTEM, LEARNING METHOD, AND COMPUTER PROGRAM
Simplified Explanation
The learning system described in this patent application consists of a generation unit and a learning unit.
- The generation unit is responsible for synthesizing an original image that includes a living body, and adding information on a reflection component of light that is not derived from the original image. This process generates a synthetic image.
- The learning unit is designed to perform learning for an estimation model based on information on a specific portion of the living body, estimated from the synthetic image using the estimation model. It also uses correct answer information that shows the correct answer of the information on the specific portion in the original image.
Potential applications of this technology:
- Medical imaging: The learning system could be used to improve the accuracy of medical imaging by estimating specific portions of the living body from synthetic images and comparing them with the correct answer information.
- Computer vision: This technology could be applied to computer vision systems to enhance their ability to estimate and recognize specific portions of living bodies in images.
Problems solved by this technology:
- Inaccurate estimation: The learning system addresses the problem of inaccurate estimation by generating synthetic images that include information on the reflection component of light not present in the original image. This allows for more accurate estimation of specific portions of the living body.
- Lack of correct answer information: The learning unit uses correct answer information from the original image to train the estimation model, ensuring that the model learns to provide accurate estimations.
Benefits of this technology:
- Improved accuracy: By incorporating information on the reflection component of light and using correct answer information, the learning system can learn to estimate specific portions of the living body more accurately.
- Enhanced learning capabilities: The learning unit can continuously improve the estimation model through learning, allowing for ongoing refinement and better performance over time.
Original Abstract Submitted
A learning system () comprises: a generation unit () configured to synthesize with an original image including a living body, information on a reflection component of light not derived from the original image to generate a synthetic image; and a learning unit () configured to perform learning for an estimation model () based on information on a specific portion of the living body estimated from the synthetic image by the estimation model and correct answer information showing a correct answer of the information on the specific portion in the original image. According to this learning system, it is possible to learn the estimation model appropriately.
