Multi-Class Image Classification Model for Lemon Quality Detection Using TensorFlow Take 3

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: This project aims to construct a predictive model using a TensorFlow convolutional neural network (CNN) and document the end-to-end steps using a template. The Lemon Quality Dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: The dataset contains 2,533 images of lemons on concrete surfaces. The research team collected these images to investigate the possibilities of enforcing a fruit quality control system. The images can be broken down into three different labels: good quality, bad quality, and empty background.

ANALYSIS: The ResNet50V2 model’s performance achieved an accuracy score of 98.96% after five epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 98.81%.

CONCLUSION: In this iteration, the TensorFlow ResNet50V2 CNN model appeared suitable for modeling this dataset.

Dataset ML Model: Multi-Class classification with numerical features

Dataset Used: Lemon Quality Dataset

Dataset Reference:

One source of potential performance benchmarks:

The HTML formatted report can be found here on GitHub.