Image-based phenotyping: use of colour signature in evaluation of melon fruit colour

Abstract

Fruit colour, both external and internal, is important because it relates directly to the commercial value of the product. In breeding and in pre-and postharvest studies of fruit colour, an effective method for evaluating colour is needed to replace subjective evaluations by eye. We used a series of data processing and statistical analyses used in content-based image retrieval to evaluate melon flesh colour, and assessed the efficacy of this approach. This method relies on summarizing colour information from images into colour signatures, calculating the earth mover's distance (EMD) between colour signatures, and multi-dimensional scaling (MDS) based on an EMD matrix. Performing MDS on a set of fruit flesh images revealed important colour features, such as the yellowish-green strength in green-fleshed melons and the relative size of the green and red parts in red-fleshed melons, without the need for an explicit definition of these features. The proportion of variance due to differences among cultivars was higher by MDS than by traditional evaluation, indicating that this new method performed best at detecting colour differences among cultivars. The method provides effective, objective indicators of fruit colour, and shows considerable promise for use in research and breeding programs.

Strawberry cultivar identification and quality evaluation on the basis of multiple fruit appearance features

“…Broken rice grains were detected (Lin et al, 2010) by evaluating the shapes of rice grains by the velocity representation method. New indices for melon fruit color evaluation were developed by methods based on content-based image retrieval (Yoshioka and Fukino, 2009). Compared with the traditional indices used for fruit color evaluation, these new indices could detect more color differences among cultivars.…”

Estimation in the Field of Individual Perennial Ryegrass Plant Position and Dry Matter Production Using a Custom‐Made High‐Throughput Image Analysis Tool

“…Each RGB image pixel of the color‐corrected images was then converted into a customized CIELAB color‐space discriminator (Jain, 1989) using the functionality of the image processing toolbox in the MATLAB package. The CIELAB discriminator is commonly used in describing plant colors (Hatier and Gould, 2007, Yoshioka and Fukino, 2010) and enables the description of small differences in colors (Gonnet, 2001). The CIELAB discriminator converts each RGB image pixel into three descriptors, L‐A‐B, where L represents luminosity and A and B are two opposing color descriptors, that widely distribute the different colors in the image through two‐dimensional A‐B space.…”

Using Plant Phenomics to Exploit the Gains of Genomics

“…For example, 'Tomato analyzer' has been successfully used to scan tomato color [112]. Yoshioka and Fukino (2009) [113] used a full flatbed scanner with a black background to color phenotype melon using the color signature method.…”