Scholarlink

This study aims to create an automated system that checks flower quality using picture-based algorithms. Checking flowers by hand to see if they’re ready for market takes a lot of time, people can make mistakes, and handling the flowers too much can make them lose quality. To fix these problems, we looked into using machine learning and computer vision algorithms to check flower quality. This cuts down on inspection time and keeps the flowers fresh and valuable for the market. In our research, we tested and compared how well different deep learning models work for sorting flowers by quality. We looked at VGG19, DenseNet, Convolutional Neural Networks (CNNs) to find out which one does the best job. To train and test these models, we made our own set of flower pictures. We got these images from Google and by taking photos ourselves. Our findings show how each method performs in terms of getting things right and working. They also point out the good things about using computers to check flower quality. This approach helps keep things consistent and stops quality from getting worse. Our work shows why it’s crucial to use machines in the flower industry. It can make products better and cut down on running costs.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Flower Identification and Quality Assessment Using Deep Learning Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • K. V. Deshpande,
  • Kulkarni Vaibhavi,
  • More Vishakha,
  • Subhedar Aditi,
  • Mohalkar Tejaswini

摘要

This study aims to create an automated system that checks flower quality using picture-based algorithms. Checking flowers by hand to see if they’re ready for market takes a lot of time, people can make mistakes, and handling the flowers too much can make them lose quality. To fix these problems, we looked into using machine learning and computer vision algorithms to check flower quality. This cuts down on inspection time and keeps the flowers fresh and valuable for the market. In our research, we tested and compared how well different deep learning models work for sorting flowers by quality. We looked at VGG19, DenseNet, Convolutional Neural Networks (CNNs) to find out which one does the best job. To train and test these models, we made our own set of flower pictures. We got these images from Google and by taking photos ourselves. Our findings show how each method performs in terms of getting things right and working. They also point out the good things about using computers to check flower quality. This approach helps keep things consistent and stops quality from getting worse. Our work shows why it’s crucial to use machines in the flower industry. It can make products better and cut down on running costs.