Unlock instant, AI-driven research and patent intelligence for your innovation.

An excrement microscopic image definition evaluation method based on a BP neural network

A BP neural network and sharpness evaluation technology, applied in neural learning methods, biological neural network models, image analysis, etc., can solve the problem that images cannot meet special environments

Active Publication Date: 2019-04-09
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF10 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problem that the traditional image definition evaluation method cannot meet the special environment of feces microscopic images, the purpose of the present invention is to provide a definition evaluation method for fecal microscopic images with strong robustness, high contrast, and good unimodality. method

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
  • An excrement microscopic image definition evaluation method based on a BP neural network
  • An excrement microscopic image definition evaluation method based on a BP neural network
  • An excrement microscopic image definition evaluation method based on a BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] Below in conjunction with accompanying drawing, a kind of stool microscopic image clarity evaluation method of the present invention is described in detail:

[0054] Step 1: Use the built-up microscope autofocus platform to make the motor run from top to bottom at a constant speed, and take a group of pictures during the focusing process of a stool microscopic image at the same time interval, and the number of pictures in each group of pictures is 60>N >40;

[0055] Step 2: Manually judge each group of pictures one by one, find out the ten clearest pictures in each group of pictures, the pixel size of each group of pictures is 1600*1200, and assign a sharpness value of 0.5-1, the clearest among them The image assigned to 1. The remaining pictures are assigned a value of 0-0.5 according to the degree of clarity, and the least clear picture is assigned a value of 0;

[0056] Step 3: Repeat steps 1 and 2 to obtain M groups of feces microscopic image focusing process pict...

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 excrement microscopic image definition evaluation method based on a BP neural network, belongs to the technical field of machine vision, and particularly relates to an excrement microscopic image definition evaluation method based on the BP neural network. According to the method, a four-layer BP neural network is trained through artificially judged excrement microscopicclear images and unclear images, a complete neural network for judging the image clarity degree is obtained, and the method is suitable for automatic focusing of the excrement microscopic images according to the characteristics that the excrement microscopic images are thick in layering and complex in background.

Description

technical field [0001] The invention belongs to the technical field of machine vision, in particular to a BP neural network-based method for evaluating the clarity of microscopic images of feces. The invention can be used in the fields of medical inspection, biological research, precision instrument manufacturing and the like. Background technique [0002] Image clarity evaluation is a quantitative calculation of image clarity, which is of great significance in image analysis and recognition, and is the key to whether the entire machine vision system can automatically focus. Image clarity evaluation has been widely used in medical testing, biological research, industrial testing, precision instrument manufacturing and other fields. [0003] In order to enable the instrument to automatically focus, usually a sharpness evaluation function is selected as a calculation index, and then searched according to a fast search algorithm such as a hill-climbing search algorithm, a dept...

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): G06T7/00G06N3/08
CPCG06N3/08G06N3/084G06T7/0012G06T2207/30168G06T2207/20084G06T2207/20081G06T2207/10061
Inventor 张静邓鼎文杨浩金松王祥舟杜晓辉刘娟秀倪光明刘霖刘永
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA