Crop and weed classification based on AutoML

TL;DR

This paper introduces an AutoML approach with a novel objective function for crop and weed classification, achieving higher accuracy and reduced crop misclassification compared to traditional deep learning models.

Contribution

The paper presents an autonomous machine learning method with a new objective function tailored for agricultural classification tasks, improving accuracy and reducing crop misclassification.

Findings

Higher classification accuracy than ResNet and VGG19

Lower crop misclassification rate

Outperforms existing state-of-the-art models

Abstract

CNN models already play an important role in classification of crop and weed with high accuracy, more than 95% as reported in literature. However, to manually choose and fine-tune the deep learning models becomes laborious and indispensable in most traditional practices and research. Moreover, the classic objective functions are not thoroughly compatible with agricultural farming tasks as the corresponding models suffer from misclassifying crop to weed, often more likely than in other deep learning application domains. In this paper, we applied autonomous machine learning with a new objective function for crop and weed classification, achieving higher accuracy and lower crop killing rate (rate of identifying a crop as a weed). The experimental results show that our method outperforms state-of-the-art applications, for example, ResNet and VGG19.