18105519. ELECTRONIC DEVICE AND METHOD FOR IMAGE SEGMENTATION BASED ON DEEP LEARNING simplified abstract (Samsung Electronics Co., Ltd.)
ELECTRONIC DEVICE AND METHOD FOR IMAGE SEGMENTATION BASED ON DEEP LEARNING
Organization Name
Inventor(s)
ELECTRONIC DEVICE AND METHOD FOR IMAGE SEGMENTATION BASED ON DEEP LEARNING - A simplified explanation of the abstract
This abstract first appeared for US patent application 18105519 titled 'ELECTRONIC DEVICE AND METHOD FOR IMAGE SEGMENTATION BASED ON DEEP LEARNING
Simplified Explanation
The patent application describes a method for image segmentation using deep learning in an electronic device. Here are the key points:
- The method involves acquiring an input image and converting it into two images with different resolutions.
- The first image is processed using a first deep learning engine, while the second image is processed using a different second deep learning engine.
- The processor provides region segmentation information of the input image based on the results obtained from both image processing steps.
Potential Applications
This technology can have various applications in fields such as:
- Medical imaging: It can assist in segmenting different regions of interest in medical images, aiding in diagnosis and treatment planning.
- Autonomous vehicles: By segmenting objects in real-time, it can help vehicles identify and track objects on the road.
- Surveillance systems: It can be used to detect and segment objects or individuals in surveillance footage, enhancing security measures.
Problems Solved
The method addresses the following problems:
- Image segmentation: It automates the process of dividing an image into meaningful regions, which can be time-consuming and challenging for complex images.
- Deep learning efficiency: By utilizing different deep learning engines for different image resolutions, it optimizes the processing efficiency and accuracy.
Benefits
The technology offers several benefits:
- Improved accuracy: By combining the results of two different deep learning engines, it enhances the accuracy of image segmentation.
- Time and resource efficiency: The use of different resolutions and deep learning engines allows for faster processing and efficient use of computational resources.
- Versatility: The method can be applied to various electronic devices, making it adaptable to different industries and applications.
Original Abstract Submitted
A method for image segmentation based on deep learning in an electronic device includes: acquiring, by a processor of the electronic device, an input image, converting, by the processor, the input image into a first image having a first resolution and a second image having a second resolution, performing, by the processor, first image processing for the first image using a first deep learning engine, performing, by the processor, second image processing for the second image using a second deep learning engine different from the first deep learning engine, and providing, by the processor, region segmentation information of the input image based on first region segmentation information associated with the first image processing and second region segmentation information associated with the second image processing.
