Method for analyzing micro-droplets in micro-droplet image detection method

The invention provides a method for analyzing micro-droplets in a micro-droplet image detection method. The method comprises the following steps of training a convolutional neural network classifier capable of carrying out the binary classification of an input image, processing a to-be-detected micr...

Full description

Saved in:
Bibliographic Details
Main Authors SHENG TIANCHENG, GUO YONG, SU SHISHENG, CHENG XIN
Format Patent
LanguageChinese
English
Published 11.12.2020
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
Online AccessGet full text

Cover

More Information
Summary:The invention provides a method for analyzing micro-droplets in a micro-droplet image detection method. The method comprises the following steps of training a convolutional neural network classifier capable of carrying out the binary classification of an input image, processing a to-be-detected micro-droplet image through Hough transform, and obtaining the specific position of each suspected droplet in the micro-droplet image, extracting images of all the suspected micro-droplet objects; and sending each micro-droplet suspected object image into the classifier trained in the step S1, and judging which droplets in the micro-droplet image to be detected are qualified droplets and which droplets are unqualified droplets by the classifier. Compared with a traditional digital image processing method, the method adopting Hough transform and deep learning is advantaged in that the micro-droplets can be identified more accurately, the identified micro-droplets can be subjected to quality inspection, and false positiv
Bibliography:Application Number: CN202010502103