Recognition model training method and device, fundus feature recognition method and device, equipment and medium
A technology for identifying models and training methods, applied in the field of image processing, can solve the problem of no leopard-like fundus feature identification method, etc., and achieve the effects of improving efficiency and reliability, rapid identification, and improving accuracy.
Pending Publication Date: 2020-02-14
PING AN TECH (SHENZHEN) CO LTD
View PDF0 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
As myopia and other related eye diseases are becoming more and more common, and there is no identification method for leopard-like fundus features closely related to high myopia in the prior art, there is an urgent need for a fast and accurate leopard-like fundus feature recognition methods
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this application.
[0037] The recognition model training method provided by this application can be applied in such as figure 1 , where a client (computer device) communicates with a server over a network. Wherein, the client (computer device) includes but is not limited to various personal computers, notebook computers, smart phones, tablet computers, cameras and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of multiple serve...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a recognition model training method and device, a fundus feature recognition method and device, a computer device and a storage medium, and the method comprises the steps: obtaining a fundus color photo image sample associated with a label value, and inputting the fundus color photo image sample into a preset recognition model which comprises an input layer unit, a first convolutional neural network and a second convolutional neural network; extracting a red channel image in the fundus color photo image sample and inputting the red channel image into a first convolutional neural network to obtain a first identification result and a feature map of the red channel image; combining the fundus color photo image sample with the feature map to generate a combined image, and inputting the combined image into a second convolutional neural network to obtain a second recognition result; obtaining a total loss value through a preset loss function; and when the total loss value is smaller than or equal to a preset loss threshold, finishing training. Thus, the leopard-print-shaped fundus features of the fundus color photo image are automatically recognized, the accuracyof the recognition model is improved, and the efficiency and reliability of the recognition model are improved.
Description
technical field [0001] The present application relates to the field of image processing, and in particular to a recognition model training and fundus feature recognition method, device, computer equipment and storage medium. Background technique [0002] Generally, due to the lack of pigment in the retinal pigment epithelium, the space between the choroidal capillaries is blocked and the pigmentation increases, and the transparency of the choroidal vessels decreases, and the capillaries become more and more sparse. The large and medium vascular structures of the choroid and the pigmented areas in the vascular space can be seen through the retina , forming a texture similar to leopard skin, so it is called leopard-like fundus, or texture-like fundus. Leopard-like fundus is common in young adults with high myopia. As myopia and other related eye diseases are becoming more and more common, and there is no identification method for leopard-like fundus features closely related t...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06T7/00G06N3/04
CPCG06T7/0012G06T2207/10024G06T2207/20081G06T2207/20084G06T2207/30041G06T2207/30101G06V2201/03G06N3/045G06F18/241G06F18/253G06T7/90G06V40/193G06V40/18G06V10/82G06N3/0464G06N3/09Y02T10/40
Inventor 王瑞赵君寰王立龙袁源智吕传峰
Owner PING AN TECH (SHENZHEN) CO LTD