首页|Bougie location algorithm of lattice biochip based on YOLOv5
Bougie location algorithm of lattice biochip based on YOLOv5
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Spie-Soc Photo-Optical Instrumentation Engineers
Bougie location is the crucial step of information extraction in biochips. Manyresearchers have used algorithms, such as image brightness information or autocovariance,to grid the biochip images. However, these algorithms cannot resolve problems such as the bougielattice being tilted or there being some bougies with insufficient hybridization. To resolvesuch problems, we propose a grid location algorithm based on the output of the fifth version ofYou Only Look Once (YOLOv5) for bougies in lattice biochip images. First, we use theYOLOv5 algorithm to detect and locate the bougies with sufficient hybridization. Second,we build a linear model for bougie location based on the least squares method and use thedepth-first search algorithm to detect and locate the bougies with insufficient hybridization.Finally, we use Otsu’s method to extract the gray values of grid areas. The algorithm was testedon a dataset consisting of 100 lattice biochip images. The experimental results show that theaverage accuracy is 99.76%, and the average detection time is 5.04 s. The algorithm has goodrobustness and high accuracy and can accurately locate the bougies.
biochipbougie locationYOLOv5the least squares methodOtsu’s method
Jihua Peng、Zhongxiu Yang、Hongwei Ying、Yefeng Li
展开 >
Ningbo University of Technology, Department of Cyberspace Security, Ningbo, China
Ningbo University of Technology, Department of Electronic and Information Engineering,Ningbo, China
NETL
NSTL
Spie-Soc Photo-Optical Instrumentation Engineers
