On Plant Detection of Intact Tomato Fruits Using Image Analysis and Machine Learning Methods

Abstract

Fully automated yield estimation of intact fruits prior to harvesting provides various benefits to farmers. Until now, several studies have been conducted to estimate fruit yield using image-processing technologies. However, most of these techniques require thresholds for features such as color, shape and size. In addition, their performance strongly depends on the thresholds used, although optimal thresholds tend to vary with images. Furthermore, most of these techniques have attempted to detect only mature and immature fruits, although the number of young fruits is more important for the prediction of long-term fluctuations in yield. In this study, we aimed to develop a method to accurately detect individual intact tomato fruits including mature, immature and young fruits on a plant using a conventional RGB digital camera in conjunction with machine learning approaches. The developed method did not require an adjustment of threshold values for fruit detection from each image because image segmentation was conducted based on classification models generated in accordance with the color, shape, texture and size of the images. The results of fruit detection in the test images showed that the developed method achieved a recall of 0.80, while the precision was 0.88. The recall values of mature, immature and young fruits were 1.00, 0.80 and 0.78, respectively.

Image classification with orchard metadata

“…In [4], a combination of SIFT and SURF descriptors are extracted densely over the image to detect pineapples using SVMs. Pixel-based segmentation is used in [9] to detect tomatoes using manually specified colour features with decision trees. Nearest neighbour matching is used in [3] over colour and texture features extracted at key-points for berry detection.…”

Sensors and systems for fruit detection and localization: A review

“…Numerous research efforts have been reported in the literature on the development of a machine vision system for image acquisition, fruit detection, and fruit localization for robotic harvesting of fruits (Parish and Goksel, 1977;Harrell et al, 1985;Yang et al, 2007;Baeten et al, 2008;Scarfe et al, 2009;Yamamoto et al, 2014). However, proper synthesization of the literature to provide a clear guidance on the state-of-the-art and potential future direction has been lacking.…”

A review of key techniques of vision-based control for harvesting robot

“…In order to solve the overlapping problem in plantlets recognition, Pastrana and Rath (2013) developed a novel pattern recognition approach using an active shape model (ASM). Yamamoto et al (2014) applied the X-means clustering algorithm on the basis of K-means clustering to determine the optimal number of clusters and to detect individual fruit in a multi-fruit blob. Due to their similarities, fruit detection tasks can be conducted with the similar method for face recognition and detection.…”