Object recognition algorithm based on optimized nonlinear activation function-global convolutional neural network

Traditional object recognition algorithms cannot meet the requirements of object recognition accuracy in the actual warehousing and logistics field. In recent years, the rapid development of the deep learning theory has provided a technical approach for solving the above problems, and a number of ob...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	The Visual computer Ročník 38; číslo 2; s. 541 - 553
Hlavní autoři:	An, Feng-Ping, Liu, Jun-e, Bai, Lei
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Berlin/Heidelberg Springer Berlin Heidelberg 01.02.2022 Springer Nature B.V
Témata:	Accuracy Algorithms Artificial Intelligence Artificial neural networks Classification Computer Graphics Computer Science Datasets Deep learning Feature maps Image Processing and Computer Vision Learning theory Machine learning Mathematical models Modelling Neural networks Object recognition Original Article Parameters Target recognition Deep learning Global convolutional neural network Object recognition Nonlinear activation function Object detection
ISSN:	0178-2789, 1432-2315
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!