Reservoir fisherman detection method based on deep convolutional neural network

The invention discloses a reservoir phishing person detection method based on a deep convolutional neural network, wherein the method comprises the steps: taking an image as the input of a full convolutional neural network, carrying out the feature extraction of the image through employing the netwo...

Full description

Saved in:
Bibliographic Details
Main Authors LYU CHANG, SHI QUAN, SUN CHANGJUN, YANG QISHUO, SHAO YEQIN, SONG JINWEI
Format Patent
LanguageChinese
English
Published 24.12.2021
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
Online AccessGet full text

Cover

More Information
Summary:The invention discloses a reservoir phishing person detection method based on a deep convolutional neural network, wherein the method comprises the steps: taking an image as the input of a full convolutional neural network, carrying out the feature extraction of the image through employing the network, and taking different convolution as a filter to extract different features of the image; taking the obtained feature image as the input of a detection module, extracting a candidate frame, and finally obtaining the category probability of the candidate frame and a predicted target position; and filtering the candidate frame by adopting a non-maximum suppression method to finally obtain a detection result. According to the invention, reservoir fisherman detection is carried out by using the deep neural network, and a reservoir fisherman detection algorithm, experimental parameters and results are introduced. Therefore, experiments prove that the reservoir fisherman can be accurately detected under different scen
Bibliography:Application Number: CN202111121039