Automated seed identification with computer vision: challenges and opportunities

Zhao, Liang; Haque, Samiha; Wang, Ruojing

doi:10.15258/sst.2022.50.1.s.05

Cited by 10 publications

(3 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, targeting larger seeds with a laser while weed seedlings are controlled with lasers may be an option in the future. Still, it requires developing seed recognition tools based on artificial intelligence (Zhao et al, 2022). Many common weed species continuously shatter their seeds during the growing season (Burton et al, 2016;Bitarafan and Andreasen, 2020b).…”

Section: Figure 10mentioning

confidence: 99%

Laser weed seed control: challenges and opportunities

Andreasen,

Vlassi,

Salehan

et al. 2024

Front. Agron.

View full text Add to dashboard Cite

Farmers are greatly interested in reducing weed seeds in their fields to avoid unnecessary weed infestation. Autonomous vehicles equipped with plant recognition systems and lasers can be used to control weed plants and may therefore be used to replace or supplement herbicides and mechanical weed control. However, less is known about the ability of laser to control weed seeds. In this study, seeds of weeds (Alopecurus myosuroides, Anisantha sterilis, Avena fatua, Centaurea cyanus, Silene noctiflora) and crops (wheat (Triticum aestivum), maize (Zea mays)) were exposed to increasing dosages of laser energy. The species represented dicots and monocots with different seed sizes and morphology. We used a thulium-doped 50 W fiber laser with a wavelength of 2 µm and a diameter of 2 mm developed for weed control. The seeds were exposed to laser directly on the seed surface or after been covered with soil (2.5 and 5 mm). Small doses of energy (0.4 J mm−2 and 0.8 J mm−2) affected the germination ability of small seeds (S. noctiflora and C. cyanus) when the seeds were irradiated directly on the seed surface, and they were completely burned at the high doses (8.0 J mm−2 and 15.9 J mm−2). However, there was not a clear relationship between seed size and sensitivity to laser dose. Additionally, increasing the laser dose on the seed surface resulted in increasing infection of fungi. Seeds covered with soil were not affected by the laser treatments except C. cyanus seeds. Controlling large seeds on the ground while weed seedlings are controlled with laser robots seems realistic in the future. However, dosages higher than 50 J (~15.9 J mm−2) is necessary to control large seeds.

show abstract

Section: Figure 10mentioning

confidence: 99%

Laser weed seed control: challenges and opportunities

Andreasen,

Vlassi,

Salehan

et al. 2024

Front. Agron.

View full text Add to dashboard Cite

show abstract

“…VGG16 architecture has been used to identify 14 different varieties of seeds [26]. A deep review of computer vision techniques for seed testing is provided in [27]. The author introduced a combination of near-infrared hyperspectral with ML models (SVM, logistic regression, random forest) and DL model (LeNet, GoogleNet, ResNet) in rice seed varieties.…”

Section: Related Workmentioning

confidence: 99%

Quantifying Soybean Defects: A Computational Approach to Seed Classification Using Deep Learning Techniques

Sable,

Singh,

Kaur

et al. 2024

Agronomy

View full text Add to dashboard Cite

This paper presents a computational approach for quantifying soybean defects through seed classification using deep learning techniques. To differentiate between good and defective soybean seeds quickly and accurately, we introduce a lightweight soybean seed defect identification network (SSDINet). Initially, the labeled soybean seed dataset is developed and processed through the proposed seed contour detection (SCD) algorithm, which enhances the quality of soybean seed images and performs segmentation, followed by SSDINet. The classification network, SSDINet, consists of a convolutional neural network, depthwise convolution blocks, and squeeze-and-excitation blocks, making the network lightweight, faster, and more accurate than other state-of-the-art approaches. Experimental results demonstrate that SSDINet achieved the highest accuracy, of 98.64%, with 1.15 M parameters in 4.70 ms, surpassing existing state-of-the-art models. This research contributes to advancing deep learning techniques in agricultural applications and offers insights into the practical implementation of seed classification systems for quality control in the soybean industry.

show abstract

“…At present, most researches on the identification of seed cultivars by hyperspectral imaging technology focus on the seeds of corn, wheat, soybean, etc. [ 5 , 23 , 24 ]. The performance of hyperspectral imaging technology in the identification of cotton seed cultivars is still unclear.…”

Section: Introductionmentioning

confidence: 99%

Cotton seed cultivar identification based on the fusion of spectral and textural features

Liu,

Guo,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

The mixing of cotton seeds of different cultivars and qualities can lead to differences in growth conditions and make field management difficult. In particular, except for yield loss, it can also lead to inconsistent cotton quality and poor textile product quality, causing huge economic losses to farmers and the cotton processing industry. However, traditional cultivar identification methods for cotton seeds are time-consuming, labor-intensive, and cumbersome, which cannot meet the needs of modern agriculture and modern cotton processing industry. Therefore, there is an urgent need for a fast, accurate, and non-destructive method for identifying cotton seed cultivars. In this study, hyperspectral images (397.32 nm—1003.58 nm) of five cotton cultivars, namely Jinke 20, Jinke 21, Xinluzao 64, Xinluzao 74, and Zhongmiansuo 5, were captured using a Specim IQ camera, and then the average spectral information of seeds of each cultivar was used for spectral analysis, aiming to estab-lish a cotton seed cultivar identification model. Due to the presence of many obvious noises in the < 400 nm and > 1000 nm regions of the collected spectral data, spectra from 400 nm to 1000 nm were selected as the representative spectra of the seed samples. Then, various denoising techniques, including Savitzky-Golay (SG), Standard Normal Variate (SNV), and First Derivative (FD), were applied individually and in combination to improve the quality of the spectra. Additionally, a successive projections algorithm (SPA) was employed for spectral feature selection. Based on the full-band spectra, a Partial Least Squares-Discriminant Analysis (PLS-DA) model was established. Furthermore, spectral features and textural features were fused to create Random Forest (RF), Convolutional Neural Network (CNN), and Extreme Learning Machine (ELM) identification models. The results showed that: (1) The SNV-FD preprocessing method showed the optimal denoising performance. (2) SPA highlighted the near-infrared region (800–1000 nm), red region (620–700 nm), and blue-green region (420–570 nm) for identifying cotton cultivar. (3) The fusion of spectral features and textural features did not consistently improve the accuracy of all modeling strategies, suggesting the need for further research on appropriate modeling strategies. (4) The ELM model had the highest cotton cultivar identification accuracy, with an accuracy of 100% for the training set and 98.89% for the test set. In conclusion, this study successfully developed a highly accurate cotton seed cultivar identification model (ELM model). This study provides a new method for the rapid and non-destructive identification of cotton seed cultivars, which will help ensure the cultivar consistency of seeds used in cotton planting, and improve the overall quality and yield of cotton.

show abstract

Automated seed identification with computer vision: challenges and opportunities

Cited by 10 publications

References 75 publications

Laser weed seed control: challenges and opportunities

Laser weed seed control: challenges and opportunities

Quantifying Soybean Defects: A Computational Approach to Seed Classification Using Deep Learning Techniques

Cotton seed cultivar identification based on the fusion of spectral and textural features

Contact Info

Product

Resources

About