18233385. NEURAL NETWORK DEVICE AND SYSTEM AND OPERATING METHOD OF THE NEURAL NETWORK DEVICE simplified abstract (Samsung Electronics Co., Ltd.)
NEURAL NETWORK DEVICE AND SYSTEM AND OPERATING METHOD OF THE NEURAL NETWORK DEVICE
Organization Name
Inventor(s)
SEONGRYEOL Kim of SUWON-SI (KR)
NEURAL NETWORK DEVICE AND SYSTEM AND OPERATING METHOD OF THE NEURAL NETWORK DEVICE - A simplified explanation of the abstract
This abstract first appeared for US patent application 18233385 titled 'NEURAL NETWORK DEVICE AND SYSTEM AND OPERATING METHOD OF THE NEURAL NETWORK DEVICE
Simplified Explanation
The patent application describes a neural network device that processes scanning electron microscope (SEM) images to detect target objects.
- Pre-processor selects target images from SEM images based on frequencies and crops them into multiple smaller images.
- Neural network processor generates crop detection images by inferring target objects from the cropped images using a segmentation model.
- Post-processor merges the crop detection images into the same size as the original SEM images based on position information from the cropped images.
---
- Potential Applications
- Medical imaging for detecting abnormalities in tissues.
- Quality control in manufacturing for identifying defects in products.
- Environmental monitoring for analyzing microscopic particles in samples.
- Problems Solved
- Automates the process of detecting target objects in SEM images.
- Increases efficiency and accuracy of identifying objects in microscopic images.
- Allows for faster analysis of large amounts of data.
- Benefits
- Reduces the need for manual inspection of SEM images.
- Improves the speed and accuracy of detecting target objects.
- Enables more detailed analysis of microscopic images for various industries.
Original Abstract Submitted
A neural network device includes: (1) a pre-processor configured to select target images from scanning electron microscope (SEM) images, based on frequencies respectively corresponding to the SEM images, and crop each of the target images into a plurality of cropped images; (2) a neural network processor configured to generate a crop detection image by inferring a target object from each of the plurality of cropped images by using a segmentation model trained to detect the target object in each of the plurality of cropped images; and (3) a post-processor configured to merge crop detection images with each other in a same size as the SEM images, based on position information of the plurality of cropped images.
