Image recognition method and device based on multiple focal lengths and storage medium

An image recognition, multi-focal length technology, applied in the field of medical detection, can solve problems such as reducing the experience of the device, occupying too much system resources, and slowing down the calculation speed of the fusion algorithm.

Active Publication Date: 2020-11-13
SHENZHEN REETOO BIOTECHNOLOGY CO LTD
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are still some deficiencies in this algorithm fusion method. For example, this method requires that when multiple focus images are obtained, the object must not be displaced, otherwise the algorithm fusion cannot avoid the phenomenon of "smear"; in addition, this method needs to traverse many All the pixels of an image will seriously slow down the calculation speed of the fusion algorithm when processing high-definition images, occupying too many system resources, thereby reducing the user's device experience.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image recognition method and device based on multiple focal lengths and storage medium
  • Image recognition method and device based on multiple focal lengths and storage medium
  • Image recognition method and device based on multiple focal lengths and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] Please refer to figure 1 , a medical testing device is disclosed in this implementation, which includes a microscope 11, a camera 12, and a detector 13, which will be described separately below.

[0029] The microscope 11 has an objective stage 111, an objective lens 112 and an eyepiece 113, wherein the objective stage 111 is used to carry the glass slide with the sample dropped, the objective lens 112 is used to focus on the glass slide with the sample dropped with different focal lengths, and the eyepiece 113 is used for The image reflected into the objective lens 112 is visually observed on the glass slide. In addition, the objective lens 112 has an automatic zooming capability, and zooming is realized by switching different lenses or fine-tuning the focal length.

[0030] The camera 12 is arranged at the eyepiece 113 , and is used to take pictures of the glass slide through the eyepiece 113 of the microscope 11 . The type of camera and camera parameters can be sel...

Embodiment 2

[0038] On the basis of the medical detection device disclosed in Embodiment 1, this embodiment discloses an image recognition method based on multi-focal distances, which is mainly used in figure 1 On the detector 13 shown in the figure, so as to realize the corresponding function.

[0039] Please refer to figure 2 , in this embodiment, the image recognition method for protection includes steps S210-S230, which are described below respectively.

[0040] Step S210, acquiring a plurality of sample images with different focal lengths, wherein each sample image includes one or more detection targets, where the detection targets can be the imaging state of cells and / or microorganisms, then each detection target corresponds to a single cell or single microorganism.

[0041] In this embodiment, in order to make the sample in a better distribution state on the glass slide and capture a better sample image, the detector 13 can control the camera 12 to take pictures after the sample ...

Embodiment 3

[0077] Please refer to Figure 7 , this embodiment discloses a medical detection device, the medical detection device 3 may include a memory 31 and a processor 32 .

[0078] Among them, the memory 31 is used to store programs. Since the memory 31 can be regarded as a computer-readable storage medium, the stored program can be the program code corresponding to steps S210-S230 in the second embodiment.

[0079] Wherein, the processor 32 is connected with the memory 31, and is used to execute related programs to realize the image recognition method disclosed in the second embodiment, and process to obtain a multi-focus image target set.

[0080] Those skilled in the art can understand that all or part of the functions of the various methods in the foregoing implementation manners can be realized by means of hardware, or by means of computer programs. When all or part of the functions in the above embodiments are implemented by means of a computer program, the program can be sto...

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

No PUM Login to view more

Abstract

The invention discloses an image recognition method and device based on multiple focal lengths and a storage medium. The image recognition method comprises the steps of acquiring multiple sample images with different focal lengths; respectively carrying out target identification on each sample image to obtain identification information of each detection target in each sample image; and performingduplicate removal processing according to the identification information of each detection target in each sample image, and storing the detection targets after duplicate removal into a preset multi-focus image target set. According to the technical scheme, all detection targets can be effectively recognized without multi-focus reconstruction of the sample images, so that the accuracy of image recognition can be improved, the image processing speed can be increased, the time required for recognition can be shortened, and the practical performance of a medical detection device can be improved.

Description

technical field [0001] The invention relates to the technical field of medical detection, in particular to a multi-focal-based and device and a storage medium. Background technique [0002] In existing medical detection devices, it is often necessary to capture images of samples after staining or color development, and the quality of the captured images plays a vital role in subsequent sample analysis. When the thickness of the object to be photographed is greater than the depth of field, there will be a situation in which part of the captured image is in the focal plane and part is in a defocused state, that is, close objects are clearly captured while distant objects are blurred, and at this time it cannot be well captured. If the information of the out-of-focus object is obtained, the accuracy of image recognition will be seriously affected when a single focus image is used for recognition. [0003] At present, the technical means to solve the out-of-focus problem is to ...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00
CPCG06T7/0012G06T2207/10024G06T2207/10056G06T2207/20081G06T2207/30024
Inventor 许德鹏刘晓康陈齐文王雪锋朱青青
Owner SHENZHEN REETOO BIOTECHNOLOGY CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap