Fresh and Stale Images of Fruits and Vegetables

Context
This dataset contains images of 6 fruits and vegetables: apple, banana, bitter gourd, capsicum, orange, and tomato. The images of each fruit or vegetable are grouped into two categories: fresh and stale. The purpose behind the creation of this dataset is the development of a machine learning model to classify fruits and vegetables as fresh or stale. This feature is a part of our final year project titled ‘Food Aayush’. (Github Link)

Data Collection and Preprocessing
For collecting the images to create the dataset, images of the fruits and vegetables were captured daily using a mobile phone camera.  The machine learning model requires a 224 x 224-pixel image. 
Frame Extraction

Data Augmentation: We used ImageDataGenerator library from Keras for augmentation. We on average created 20 augmentations per image which indeed improve our models accuracy.
Data Augmentation

Acknowledgements
We would like to give credit to this dataset as we have obtained the images in some of the classes from here.
Dataset

Inspiration
Our BE final year project, titled ‘Food Aayush’, is an application that can be used for the classification of fruits and vegetables as fresh or stale, the classification of cooking oils into different rancidity levels, and the analysis of various parameters related to the nutritional value of food and people’s dietary intake. We have trained a machine learning model for the classification of fruits and vegetables. This dataset was created for training the machine learning model.