Summary of Classifying Healthy and Defective Fruits with a Multi-input Architecture and Cnn Models, by Luis Chuquimarca et al.
Classifying Healthy and Defective Fruits with a Multi-Input Architecture and CNN Models
by Luis Chuquimarca, Boris Vintimilla, Sergio Velastin
First submitted to arxiv on: 14 Oct 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel study explores the use of a Multi-Input architecture for classifying apples and mangoes into healthy and defective states, utilizing both RGB and silhouette images. The goal is to improve the accuracy of convolutional neural network (CNN) models. The researchers employed image acquisition, preprocessing, training, and evaluation of two CNN models: MobileNetV2 and VGG16. Results show that combining silhouette images with the Multi-Input architecture yields better-performing models compared to using only RGB images for fruit classification. Specifically, the MobileNetV2 model achieved 100% accuracy. This finding highlights the effectiveness of this combined methodology in improving fruit classification, which could have significant implications for applications like external quality inspection. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new study looks at how to better identify healthy and defective apples and mangoes using a special kind of computer program called a Multi-Input architecture. They took pictures of the fruits from different angles (RGB) and also used outlines (silhouette images). The goal was to make sure the computer program could correctly sort the fruits into healthy or defective categories. The researchers tested two types of computer programs: MobileNetV2 and VGG16. When they combined the RGB and silhouette images, the computer programs got much better at identifying the fruits. In fact, one program (MobileNetV2) was perfect! This new way of doing things could be very helpful for checking fruit quality before it’s sold. |
Keywords
» Artificial intelligence » Classification » Cnn » Neural network
