Thousand-seed weight determination in forest species by image analysis

Abstract

Thousand-seed weight (TSW) is used to calculate the sowing density, number of seeds present in a sample, and predict seed size. Our aim was to establish an alternative methodology for thousand-seed weight determination in forest species using image analysis techniques. The traditional methodology was compared with the alternative one, testing them on seeds from 16 forest species. The traditional method was performed by manually counting eight repetitions of 100 seeds, weighing of samples, and computation of thousand-seed weight. The alternative methodology was performed by counting seed samples captured by images and processing in ImageJ® software, followed by weighing a single sample, and computation. All steps were timed, and each methodology was repeated ten times per species. The TSW obtained by the alternative methodology was similar to that obtained by the traditional one, and the average execution time of the activities was reduced by 62%. The proposed thousand-seed weight determination by image analysis is an efficient and optimized alternative to the traditional method. Thousand-seed weight determination from image analysis reduces execution time for the seed analyst and forest seedling producer.

Image-based phenotyping of seed architectural traits and prediction of seed weight using machine learning models in soybean

“…Singh et al (2020) reported that a simple foreground area was found to be the best predictor and has a greater association with seed weight. A similar type of image-based seed weight prediction using seed architectural traits has been reported in rice (Singh et al, 2020), wheat (Sabanci et al, 2016), and forest species (Felix et al, 2021).…”

“…(2016) used a Logitech c905 webcam camera to acquire still images and accurately predicted wheat seed weight (99.66%) using a simple polynomial regression model. Similarly, Felix et al. (2021) determined the thousand seed weight (TSW) of seeds harvested from 16 different forest tree species using digital image processing through image J software and demonstrated the comparative advantages (60-80% time savings) of image-based phenotyping for counting seed number, weight, and TSW over traditional manual measurement.…”

“…Recently, Sabanci et al ( 2016) used a Logitech c905 webcam camera to acquire still images and accurately predicted wheat seed weight (99.66%) using a simple polynomial regression model. Similarly, Felix et al (2021) determined the thousand seed weight (TSW) of seeds harvested from 16 different forest tree species using digital image processing through image J software and demonstrated the comparative advantages (60-80% time savings) of image-based phenotyping for counting seed number, weight, and TSW over traditional manual measurement. Singh et al (2020) used a mobile camera (Apple iPhone) to acquire the RGB images and used six machine learning algorithms in a stacked ensemble model to predict the size and weight of rice kernels using the pixel count derived from the segmented foreground images.…”

Physiological potential of canola seeds and its relationship with electrical conductivity

“…Quanto ao peso de mil sementes, houve diferença entre os híbridos, com variação de aproximadamente 1,58 gramas entre o híbrido Hyola 401 com maior peso de mil sementes, e o híbrido Hyola 76 de menor peso (Tabela 1). O peso de mil sementes é uma medida utilizada para diferentes finalidades, dentre elas a comparação da qualidade de lotes de sementes em diversas espécies (FELIX et al, 2021).…”