Development of Deep Learning Methodology for Maize Seed Variety Recognition Based on Improved Swin Transformer

Bi, Chunguang; Hu, Nan; Zou, Yiqiang; Zhang, Shuo; Xu, Suzhen; Yu, Honggang

doi:10.3390/agronomy12081843

Cited by 39 publications

(16 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is in line with what was stated by Sari et al (2021) that imagery from drones (RGB) can be used in rice monitoring. The CNN model is also reported for the detection and classification of plant pests and diseases (Domingues et al, 2022) and corn seeds in the context of testing purity (Bi et al, 2022). However, further development is still needed to increase the number of varieties, especially those that have similar morphological characteristics.…”

Section: Cnn Model Evaluationmentioning

confidence: 99%

Rice variety identification system based on drone images to support seed certification process

Ardiyansah¹,

Zamzami²,

Wulandari³

2023

Indonesian J. Agron.

View full text Add to dashboard Cite

Utilization of technology can be a solution in the process of supervising certified seeds, especially at the stage of field inspection, which is faster and more efficient. This study aimed to develop a drone image-based rice variety system to support the inspection process for seed certification. The research was conducted from March – July 2022. The rice plants of IPB 3S and Inpari 32 varieties located in Karawang, West Java were observed for their agronomic characteristics. The images of the two varieties were taken using a drone and augmented and cropped. The overall image obtained was 80% used as training data, 20% as data validation, and 10% as test data. The variety identification system was built using a model by applying the convolutional neural network (CNN) algorithm. The performance of the model was observed through accuracy, precision, recall, and F1-Score. All agronomic characters justified that the two varieties used were different. This study produced three CNN models that could accurately identify the varieties of IPB 3S and Inpari 32 with an accuracy rate of 99.52% to 100%. Drone imaging is prospective for field inspection process of seed certification. Keywords: CNN, deep learning, image processing, seed production, unmanned aerial vehicle

show abstract

Section: Cnn Model Evaluationmentioning

confidence: 99%

Rice variety identification system based on drone images to support seed certification process

Ardiyansah¹,

Zamzami²,

Wulandari³

2023

Indonesian J. Agron.

View full text Add to dashboard Cite

show abstract

“…The results indicated that the deep learning model achieved a classification accuracy of over 95% on both the training and testing datasets. Bi ( Bi et al., 2022 ) improved the Swin Transformer model and applied transfer learning to achieve high-precision classification and recognition of corn seed images, with an average accuracy of 96.53%. Xing ( Xing et al., 2023 ) proposed a network model called GC_DRNet, incorporating the concept of dense networks and achieving an accuracy of 96.98% on a wheat seed dataset.…”

Section: Introductionmentioning

confidence: 99%

A maize seed variety identification method based on improving deep residual convolutional network

Li,

Xu,

Song

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

Seed quality and safety are related to national food security, and seed variety purity is an essential indicator in seed quality detection. This study established a maize seed dataset comprising 5877 images of six different types and proposed a maize seed recognition model based on an improved ResNet50 framework. Firstly, we introduced the ResStage structure in the early stage of the original model, which facilitated the network’s learning process and enabled more efficient information propagation across the network layers. Meanwhile, in the later residual blocks of the model, we introduced both the efficient channel attention (ECA) mechanism and depthwise separable (DS) convolution, which reduced the model’s parameter cost and enabled the capturing of more precise and detailed features. Finally, a Swish-PReLU mixed activation function was introduced globally to improve the overall predictive power of the model. The results showed that our model achieved an impressive accuracy of 91.23% in corn seed classification, surpassing other related models. Compared with the original model, our model improved the accuracy by 7.07%, reduced the loss value by 0.19, and decreased the number of parameters by 40%. The research suggested that this method can efficiently classify corn seeds, holding significant value in seed variety identification.

show abstract

“…The outcomes of their experiments revealed remarkable results, with all models consistently achieving a classification accuracy surpassing 90%. Bi et al. (2022) introduced an innovative approach known as the swim transformer to enhance the recognition of corn seeds.…”

Section: Introductionmentioning

confidence: 99%

“…The outcomes of their experiments revealed remarkable results, with all models consistently achieving a classification accuracy surpassing 90%. Bi et al (2022) introduced an innovative approach known as the swim transformer to enhance the recognition of corn seeds. Their model integrated feature attention mechanisms and multi-scale feature extraction techniques, substantially enhancing its performance.…”

Section: Introductionmentioning

confidence: 99%

Detection of sweet corn seed viability based on hyperspectral imaging combined with firefly algorithm optimized deep learning

Wang,

Song

2024

Front. Plant Sci.

View full text Add to dashboard Cite

The identification of sweet corn seed vitality is an essential criterion for selecting high-quality varieties. In this research, a combination of hyperspectral imaging technique and diverse deep learning algorithms has been utilized to identify different vitality grades of sweet corn seeds. First, the hyperspectral data of 496 seeds, including four viability-grade seeds, are extracted and preprocessed. Then, support vector machine (SVM) and extreme learning machine (ELM) are used to construct the classification models. Finally, the one-dimensional convolutional neural networks (1DCNN), one-dimensional long short-term memory (1DLSTM), the CNN combined with the LSTM (CNN-LSTM), and the proposed firefly algorithm (FA) optimized CNN-LSTM (FA-CNN-LSTM) are utilized to distinguish spectral images of sweet corn seeds viability grade. The findings from the experimental analysis indicate that the deep learning models exhibit a significant advantage over traditional machine learning approaches in the discrimination of seed vitality levels, boasting a classification accuracy exceeding 94.26% in test datasets and achieving an accuracy improvement of at least 3% compared to the best-performing machine learning model. Moreover, the performance of the FA-CNN-LSTM model proposed in this study demonstrated a slight superiority over the other three models. Besides, the FA-CNN-LSTM achieved a classification accuracy of 97.23%, representing a significant improvement of 2.97% compared to the lowest-performing CNN and a 1.49% enhancement over the CNN-LSTM. In summary, this study reveals the potential of integrating deep learning with hyperspectral imaging as a promising alternative for discriminating sweet corn seed vitality grade, showcasing its value in agricultural research and cultivar breeding.

show abstract

Development of Deep Learning Methodology for Maize Seed Variety Recognition Based on Improved Swin Transformer

Cited by 39 publications

References 52 publications

Rice variety identification system based on drone images to support seed certification process

Rice variety identification system based on drone images to support seed certification process

A maize seed variety identification method based on improving deep residual convolutional network

Detection of sweet corn seed viability based on hyperspectral imaging combined with firefly algorithm optimized deep learning

Contact Info

Product

Resources

About