Anterior segment sectional image feature extraction method based on machine vision

Abstract

The invention discloses an anterior segment sectional image feature extraction method based on machine vision, and the method comprises the following steps: collecting an anterior segment sectional image under low-illumination illumination; enhancing the contrast of the anterior segment sectional image by adopting a Retinex algorithm; performing Gaussian filtering to remove noise generated after the step S2; finding a potential corneal region through binarization and blob shape analysis; roughly positioning the edges of the front and rear surfaces of the cornea in the potential cornea region by using a gradient maximum method; determining sub-pixel precision boundaries of the front surface and the rear surface of the cornea through a Gaussian fitting positioning method; according to the solved sub-pixel precision boundaries of the front and rear surfaces of the cornea, finding initial points of the iris and the crystalline lens, and obtaining accurate boundary values of the front and rear surfaces of the cornea, the front surface of the crystalline lens and the front surface of the iris through tracking. The invention has the following advantages and effects that high-precision processing can be performed on the image in a low-illumination imaging mode, and the matching degree and the comfort degree of a patient can be greatly improved.

Description

technical field [0001] The invention relates to the technical field of ophthalmology detection, in particular to a feature extraction method of an anterior segment tomographic image based on machine vision. Background technique [0002] When using a slit lamp or related equipment to collect anterior segment tomographic images, in order to ensure image quality, a high-intensity light source is usually used to irradiate the human eye. Some people who are sensitive to light cannot even cooperate to complete the entire detection, requiring the cooperation of an eye opener, and the eyes cannot be used during the test. Concentrate on the point of gaze, resulting in a decrease in measurement accuracy. Therefore, if the patient's discomfort can be reduced by reducing the intensity of the illumination source, and the image can be processed with high precision even in the low-light imaging mode, the cooperation and comfort of the patient will be greatly improved. Contents of the inv...

AI Technical Summary

Problems solved by technology

[0002] When using a slit lamp or related equipment to collect anterior segment tomographic images, in order to ensure image quality, a high-intensity light source is usually used to irradiate the human eye. Some people who are sensitive to light cannot even cooperate to complete the entire detection, requiring the cooperation of an eye opener, and the eyes cannot be used during the test. Focus on the point of gaze, resulting in a decrease in measurement accuracy

Images