Assessing Tomato Maturity: CNN vs VGG16

被引：1

作者：

Maged, Salma ^{[1
]}

Adel, Aya ^{[2
]}

Tawfik, Mohamed ^{[1
]}

Badawy, Wael ^{[1
]}

机构：

[1] Egyptian Russian Univ, Sch Artificial Intelligence, Dept Data Sci, Cairo, Egypt

[2] Egyptian Russian Univ, Sch Artificial Intelligence, Dept Artificial Intelligence, Cairo, Egypt

来源：

2024 INTERNATIONAL CONFERENCE ON MACHINE INTELLIGENCE AND SMART INNOVATION, ICMISI 2024 | 2024年

关键词：

Tomato Maturity; Machine Learning; Computer Vision; Agriculture assisted technology;

D O I：

10.1109/ICMISI61517.2024.10580489

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we present a performance analysis of two techniques for detection tomato maturity. Detecting plant maturity from images inherits several challenges. We designed two different architectures: (1) a general Convolutional Neural Networks "CNN" architecture. And (2) a pretrained architecture with 16 layers "VGG16". The experiment uses a set of 2986 images and proof that the general CNN has a better performance due to its ability to accommodate several challenges.

引用

页码：136 / 139

页数：4