Image processing method and system in analyte testing, medium, and device
AssigneeSensura Pte. Ltd
InventorHongzhi ZHENG
Life of this patent
Estimating the term…
Abstract
The present invention provides an image processing method and system in analyte testing, a medium, and a device. The method includes: image obtaining step: obtaining an infrared grayscale image by imaging a first area; dividing: based on a pixel gradient, distinguishing a dark spot from a bright spot, and dividing the infrared grayscale image into a dark spot area and a bright spot area; point selecting step: calculating and selecting first target candidate points; and selecting step: performing outlier point detection and selection on the first target candidate points, and obtaining a position of a first target.
Claims7
An image processing method in analyte testing, comprising:
- image obtaining step:
- obtaining an infrared grayscale image by imaging a first area;
- dividing step:
- based on a pixel gradient, distinguishing a dark spot from a bright spot, and dividing the infrared grayscale image into a dark spot area and a bright spot area;
- point selecting step:
- calculating a grayscale gradient of a pixel combination comprising each pixel in the dark spot area and a surrounding pixel, and selecting a top preset quantity of pixel combinations with large grayscale gradients as first target candidate points;
- and
- selecting step:
- performing outlier point detection on the first target candidate points, obtaining a selected first target candidate point by using a standard deviation with a preset multiple, and using a position of the selected first target candidate point as a position of a first target.
An image processing system in analyte testing, comprising:
- an image obtaining module, configured to obtain an infrared grayscale image by imaging a first area;
- a dividing module, configured to, based on a pixel gradient, distinguish a dark spot from a bright spot, and divide the infrared grayscale image into a dark spot area and a bright spot area;
- a point selection module, configured to calculate a grayscale gradient of a pixel combination comprising each pixel in the dark spot area and a surrounding pixel, and select a top preset quantity of pixel combinations with large grayscale gradients as first target candidate points;
- and
- a selection module, configured to perform outlier point detection on the first target candidate points, obtain a selected first target candidate point by using a standard deviation with a preset multiple, and use a position of the selected first target candidate point as a position of a first target.
Dependencies are inferred from the claim text.