Method for analyzing iris images and retina images by using artificial intelligence technology

Abstract

The invention discloses a method for analyzing diagnosis diabetes and precursor symptoms of iris images and retinal images. The method comprises the following steps of: shooting an eye image of a userby using a mobile terminal of the user; a stage of performing image preprocessing for extracting a region of interest; expanding the resolution of the attention field; in order to reduce the data storage amount, compressing attention field data needing to be transmitted to a server in a database form; performing user authentication by using the iris image; encrypting the image data; enabling theartificial neural network to learn the stored data for the diagnosis of the diabetes and the precursor symptoms thereof; and predicting the disease probability of the diabetes by using the learned artificial neural network. Meanwhile, the stage of pre-processing the imaging image further comprises the following steps of: performing gray processing on the part which is not extracted into the concerned field, and only extracting the concerned field; the stage of predicting the disease probability of the diabetes further comprises a stage of predicting the diabetes type based on the lesion position and shape.

Description

technical field [0001] The present invention relates to a method of analyzing iris and retinal images using artificial intelligence technology in order to diagnose diabetes and its precursor symptoms. It is about to provide a correct diagnosis of diabetes after taking iris and retinal images on a smart phone, and provide a reliable Invention of services such as diabetes probability. Background technique [0002] Diabetes is a metabolic disease characterized by hyperglycemia (elevated blood glucose concentration). Hyperglycemia is due to defective insulin secretion or impaired biological action, or both. Hyperglycemia will cause various symptoms and precursors, and glucose will be eliminated through urination. [0003] Diabetes is divided into type 1 diabetes and type 2 diabetes. Type 1 diabetes, formerly known as insulin-dependent diabetes, generally results from a complete inability to produce insulin, and usually occurs in children and adolescents. Type 2 diabetes deve...

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to solve the shortcomings of the existing artificial neural network disease diagnosis technology such as high cost, space constraints, and lack of convenience, and realize the prediction and diagnosis of diabetes and precursor symptoms only by using a smartphone technology

Images