Over the last few years, the research into agriculture has gained momentum, showing signs of rapid growth. The latest to appear on the scene is bringing convenience in how agriculture can be done by employing various computational technologies. There are lots of factors that affect agricultural production, with seed quality topping the list. Seed classification can provide additional knowledge about quality production, seed quality control and impurity identification. The process of categorising seeds has been traditionally done based on characteristics like colour, shape and texture. Generally, this is performed by specialists by visually inspecting each sample, which is a very tedious and time-consuming task. This procedure can be easily automated, providing a significantly more efficient method for seed sorting than having them be inspected using human labour. In related areas, computer vision technology based on machine learning (ML), symmetry and, more particularly, convolutional neural networks (CNNs) have been generously applied, often resulting in increased work efficiency. Considering the success of the computational intelligence methods in other image classification problems, this research proposes a classification system for seeds by employing CNN and transfer learning. The proposed system contains a model that classifies 14 commonly known seeds with the implication of advanced deep learning techniques. The techniques applied in this research include decayed learning rate, model checkpointing and hybrid weight adjustment. This research applies symmetry when sampling the images of the seeds during data formation. The application of symmetry generates homogeneity with regards to resizing and labelling the images to extract their features. This resulted in 99% classification accuracy during the training set. The proposed model produced results with an accuracy of 99% for the test set, which contained 234 images. These results were much higher than the results reported in related research.

https://hal-agrosup-dijon.archives-ouvertes.fr/hal-03055108/document

A convolution neural network-based seed classification system

Genetically diverse plant germplasm stored in ex-situ genebanks are excellent resources for breeding new high yielding and sustainable crop varieties to ensure future food security Novel alleles have been discovered through routine genebank activities such as seed regeneration and characterization, with subsequent utilization providing significant genetic gains and improvements for the selection of favorable traits, including yield, biotic, and abiotic resistance Although some genebanks have implemented cost-effective genotyping technologies through advances in DNA technology, the adoption of modern phenotyping is lagging The introduction of advanced phenotyping technologies in recent decades has provided genebank scientists with time and cost-effective screening tools to obtain valuable phenotypic data for more traits on large germplasm collections during routine activities The utilization of these phenotyping tools, coupled with high-throughput genotyping, will accelerate the use of genetic resources and fast-track the development of more resilient food crops for the future In this review, we highlight current digital phenotyping methods that can capture traits during annual seed regeneration to enrich genebank phenotypic datasets Next, we describe strategies for the collection and use of phenotypic data of specific traits for downstream research using high-throughput phenotyping technology Finally, we examine the challenges and future perspectives of genebank phenomics

https://www.mdpi.com/2223-7747/9/7/817/pdf

Genebank Phenomics: A Strategic Approach to Enhance Value and Utilization of Crop Germplasm.

Assessment of seed germination is an essential task for seed researchers to measure the quality and performance of seeds. Usually, seed assessments are done manually, which is a cumbersome, time consuming and error-prone process. Classical image analyses methods are not well suited for large-scale germination experiments, because they often rely on manual adjustments of color-based thresholds. We here propose a machine learning approach using modern artificial neural networks with region proposals for accurate seed germination detection and high-throughput seed germination experiments. We generated labeled imaging data of the germination process of more than 2400 seeds for three different crops, Zea mays (maize), Secale cereale (rye) and Pennisetum glaucum (pearl millet), with a total of more than 23,000 images. Different state-of-the-art convolutional neural network (CNN) architectures with region proposals have been trained using transfer learning to automatically identify seeds within petri dishes and to predict whether the seeds germinated or not. Our proposed models achieved a high mean average precision (mAP) on a hold-out test data set of approximately 97.9%, 94.2% and 94.3% for Zea mays, Secale cereale and Pennisetum glaucum respectively. Further, various single-value germination indices, such as Mean Germination Time and Germination Uncertainty, can be computed more accurately with the predictions of our proposed model compared to manual countings. Our proposed machine learning-based method can help to speed up the assessment of seed germination experiments for different seed cultivars. It has lower error rates and a higher performance compared to conventional and manual methods, leading to more accurate germination indices and quality assessments of seeds.

/pdf/accurate-machine-learning-based-germination-detection-of3nmlhd45.pdf

Accurate machine learning-based germination detection, prediction and quality assessment of three grain crops

The agricultural transformation in the last decade using artificial intelligence has led to significant gains in productivity and profitability. The traditional machine learning approaches present inherent limitations in extracting features and information from image data. Deep learning techniques, particularly CNN&#x0027;s, help to overcome these limitations due to their multi-level architecture. Various deep learning applications in agriculture include crop disease identification, fruit classification, and germination rate monitoring. Seed image analysis is considered a significant task for the preservation of biodiversity and sustainability. This research uses MobileNetV2, a deep learning convolutional neural network (DCNNs) for seed classification. This model has been preferred due to its simple architecture and memory-efficient characteristics. A total of 14 different classes of seeds were used for the experimentation. The results indicate accuracies of 98&#x0025; and 95&#x0025; on training and test sets, respectively. 

Smart Seed Classification System based on MobileNetV2 Architecture

The importance of agriculture in modern society need not be overstated. In order to meet the huge requirements of food and to mitigate, the conventional problems of cropping smart and sustainable agriculture have emerged over the conventional agriculture. From computational perspective, computer vision and machine learning techniques have been applied in many aspects of human and social life, and agriculture is not also an exception. This review paper gives an overview of machine learning and computer vision techniques which are inherently associated with this domain. A summary of the works highlighting different seeds, crops, fruits with the country is also enclosed. The paper also tries to give an analysis, which can help researchers to look at some relevant problems in the context of India.

A Review on Agricultural Advancement Based on Computer Vision and Machine Learning

https://www.pubhort.org/ejhs/80/2/4/80_2_4.pdf

Č. Rozman

Papers

Assessment of germination rate of the tomato seeds using image processing and machine learning