Open AccessResearch on Target Detection Technology Based on Convolutional Neural Network
Author(s) -
Yang Liu,
Huaguang Zhang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1631/1/012022
Subject(s) - computer science , convolutional neural network , robustness (evolution) , artificial neural network , artificial intelligence , convolution (computer science) , pattern recognition (psychology) , time delay neural network , cognitive neuroscience of visual object recognition , process (computing) , machine learning , object (grammar) , biochemistry , chemistry , gene , operating system
The research and application of neural network has been a research topic in recent years, and the efficient recognition of objects is undoubtedly an important part of the technology application. Convolution of the neural network is in the process of object recognition classification, has carried on the improvement of cognitive machine, thus avoiding the error back propagation in time loss problem, based on the biological neural network structure, convolution weights of neural network are more inclined to study sharing network structure, which shows good performance in the process of a number of image recognition, for translation, proportion to gather scaling and deformation and so on the many kinds of complex operation has certain robustness.