An Advanced Deep Learning Approach to Detect Water Lily

Abstract

This project is titled “to detect water lily using deep learning” the traditional method of image recognition is to extract features manually, which cannot solve this problem well due to the complex background of flowers and the similarity between their categories. With the advancement of science and technology. This work will help us to detect different flowers. I used deep learning algorithms like CNN, INCEPTION V3, RESNET50, RESNET152V2, VGG19, and MOBILE NET to detect 3 different types of water lilies. I achieved 100% accuracy at RESNET152V2, 99% accuracy at INCEPTIONV3, 99% at VGG19, and 99% at MOBILE NET. My system also achieved 86% accuracy at RESNET50.