Small datasets for fruit detection with transfer learning

Dai, Dan, Gao, Junfeng, Parsons, Simon and Sklar, Elizabeth (2021) Small datasets for fruit detection with transfer learning. UKRAS21 Conference: Robotics at home Proceedings . pp. 5-6. ISSN 2516-502X

Full content URL: http://doi.org/10.31256/Nf6Uh8Q

Documents
Small datasets for fruit detection with transfer learning
Published Open Access manuscript
[img]
[Download]
UK-RAS21-Proceeding-3.pdf
[img]
Preview
PDF
UK-RAS21-Proceeding-3.pdf - Whole Document

4MB
[img] PDF
UK-RAS21-Proceeding-3.pdf
Restricted to Repository staff only

4MB
Item Type:Article
Item Status:Live Archive

Abstract

A common approach to the problem of fruit detection in images is to design a deep learning network and
train a model to locate objects, using bounding boxes to identify regions containing fruit. However, this requires sufficient data and presents challenges for small datasets. Transfer learning, which acquires knowledge from a source domain and brings that to a new target domain, can produce improved performance in the target domain. The work discussed in this paper shows the application of transfer learning for fruit detection with small datasets and presents analysis between the number of training images in source and target domains. This investigation is based
on three datasets: two containing tomatoes and one containing strawberries. Experimental results indicate that transfer learning can enhance prediction with limited data.

Keywords:—fruit detection, limited datasets, transfer learning, target domain
Subjects:G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > Lincoln Institute for Agri-Food Technology
ID Code:46519
Deposited On:20 Sep 2021 10:04

Repository Staff Only: item control page