Design of an Intelligent Vision Algorithm for Recognition and Classification of Apples in an Orchard Scene

TL;DR

This paper presents a robust vision algorithm utilizing image processing and neural networks to recognize and classify apples and orchard scene elements, aiming to improve robotic apple harvesting accuracy.

Contribution

It introduces a novel image processing and neural network-based approach for recognizing and classifying apples and orchard objects in complex scenes.

Findings

Achieved accurate recognition of apples and scene elements.

Successfully classified apples into Red Delicious and Golden Delicious.

Demonstrated effectiveness of invariant-moment features with neural networks.

Abstract

Apple is one of the remarkable fresh fruit that contains a high degree of nutritious and medicinal value. Hand harvesting of apples by seasonal farmworkers increases physical damages on the surface of these fruits, which causes a great loss in marketing quality. The main objective of this study is focused on designing a robust vision algorithm for robotic apple harvesters. The proposed algorithm is able to recognize and classify 4-classes of objects found in an orchard scene including apples, leaves, trunk and branches, and sky into two apples and non-apples classes. 100 digital images of Red Delicious apples and 100 digital images of Golden Delicious apples were selected among 1000 captured images of apples from 18 apple gardens in West Azerbaijan, Iran. An image processing algorithm is proposed for segmentation and extraction of the image classes based on the color characteristics of mentioned classes. Invariant-Momentums were chosen as the extracted features from the segmented classes, e.g. apples. Multilayer Feedforward Neural Networks, MFNNs, were used as an artificial intelligence tool for the recognition and classification of image classes.