A Calculation Method of Cone Cell Density Based on Image Recognition
A calculation method and image recognition technology, applied in the field of cone cell density calculation, can solve the problems of no automatic cone cell counting density, limited application, labor consumption, etc., achieve a high degree of automation, avoid result deviation, and improve detection efficiency. Effect
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Publication Date
- 2016-08-17
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention belongs to the fields of fundus microscopic imaging and medical detection. Specifically, the invention relates to a method for calculating cone cell density based on image recognition. Background technique
[0002] There are three levels of neurons in the retina, including cones, rods, bipolar cells, and ganglion cells. Cone cells and rod cells belong to the first-level neurons. They sense external light and image information and transmit them to the visual center through bipolar cells and ganglion cells. Among them, the cone cells are mainly responsible for brightening vision, distinguishing fine shapes and color vision, and are mainly distributed in the macular area of the retina (the center of the macula only has cone cells), which is the anatomical and physiological basis for the formation of visual acuity, that is, vision. And in some fundus diseases such as retinitis pigmentosa and cone-rod dystrophy, there will be changes in con...
Examples
Embodiment Construction
[0028] Embodiments of the present invention will be further described below in conjunction with accompanying drawings:
[0029] Such as Figure 1-Figure 4 As shown, the present invention discloses a method for calculating the density of cone cells based on image processing. The method utilizes a fundus adaptive confocal laser scanning ophthalmoscope to image fundus cone cells, and based on computer vision, the images are identified, analyzed and counted, and then counted. Cones, to analyze cone density. Said method comprises the following steps:
[0030] (1) Obtain pictures of retinal cones.
[0031] Turn on the power, enter the subject's personal information, and the subject sits in front of the fundus adaptive confocal laser scanning ophthalmoscope, with the lower jaw placed on the jaw rest.
[0032] Instruct the subject to stare at the red fixation light in the instrument, adjust the focus to make the cone cell picture of the fundus scanned and captured the clearest, and...