18058099. IMAGE PROCESSING APPARATUS simplified abstract (CANON KABUSHIKI KAISHA)
Contents
IMAGE PROCESSING APPARATUS
Organization Name
Inventor(s)
TSUYOSHI Kobayashi of Tokyo (JP)
IMAGE PROCESSING APPARATUS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18058099 titled 'IMAGE PROCESSING APPARATUS
Simplified Explanation
The abstract describes an image processing apparatus that reduces noise in radiation images captured by a radiation imaging apparatus. The apparatus obtains a first radiation image of an inspection target object and generates a second radiation image with reduced noise using a learned model.
- The image processing apparatus obtains a first radiation image captured by a radiation imaging apparatus.
- It generates a second radiation image with reduced noise compared to the first image.
- The noise reduction is achieved by inputting the first radiation image into a learned model.
- The learned model is obtained through learning using data that includes radiation images with simulated system noise.
- The simulated system noise is based on the manufacturing variation of the radiation imaging apparatus.
Potential applications of this technology:
- Medical imaging: The image processing apparatus can be used in medical imaging systems to enhance the quality of radiation images, improving diagnostic accuracy.
- Industrial inspection: The technology can be applied in industrial inspection systems to improve the clarity of radiation images, aiding in defect detection and quality control processes.
Problems solved by this technology:
- Noise reduction: The image processing apparatus addresses the issue of noise in radiation images, which can degrade image quality and affect the accuracy of analysis and interpretation.
- Manufacturing variation: By considering the manufacturing variation of the radiation imaging apparatus, the learned model can effectively reduce noise specific to each device, improving consistency and reliability.
Benefits of this technology:
- Improved image quality: The second radiation image generated by the apparatus has reduced noise, resulting in clearer and more detailed images for analysis and interpretation.
- Consistency across devices: By accounting for manufacturing variation, the learned model can be applied to different radiation imaging apparatuses, ensuring consistent noise reduction performance.
- Enhanced diagnostic accuracy: The noise reduction provided by the apparatus can improve the accuracy of diagnoses in medical imaging, leading to better patient care.
Original Abstract Submitted
An image processing apparatus includes an obtaining unit configured to obtain a first radiation image of an inspection target object that has been captured by a radiation imaging apparatus, and a generation unit configured to generate a second radiation image including noise reduced as compared with the first radiation image, by inputting the first radiation image obtained by the obtaining unit, to a learned model obtained by performing learning using learning data including a radiation image to which noise simulating system noise of a radiation imaging apparatus in accordance with a distribution that is based on a manufacturing variation of a radiation imaging apparatus is added.
