Research on Color and Shape Recognition of Maize Diseases Based on HSV and OTSU Method

Chen, Guifen; Meng, Ying; Lü, Jian; Wang, Dongxue

doi:10.1007/978-3-030-06155-5_30

Cited by 2 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the early stages of conventional machine learning, some scholars used image processing techniques to simply process maize seed images for recognition. Chen et al [6] proposed a method based on image In HSV and Otsu method based on genetic algorithm optimization, which achieved more accurate segmentation and recognition of the disease of color and shape features, and enhanced the real-time and accuracy of the image of maize disease detection and recognition. Subsequently, many researchers began to use neural network approaches for maize seed image analysis.…”

Section: Introuductionmentioning

confidence: 99%

Research on a Lightweight Method for Maize Seed Quality Detection Based on Improved YOLOv8

Niu,

Xu,

Liang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Seeds are the most basic and important means of production for agriculture. During the production and processing of seeds, they may undergo potential mechanical damages and mildew alterations, which might jeopardize their germination viability. Hence, checking the quality of seeds before sowing is of paramount importance for the benefit of the sower and the safety of agricultural production. In order to achieve an efficient detection of maize seed quality, our experiment assembled a dataset composed of 2,128 seeds with four different health statuses of maize: healthy, broken, moth-eaten, and mildewed. In this thesis, we proposed a lightweight maize seed quality detection model for small objects based on improved YOLOv8: I-YOLOv8. Firstly, we introduced a multi-scale attention mechanism called EMA to efficiently retain information across channels and reduce computational load. Next, we chosen the SPD-Conv module for lowresolution images and small objects, and applied it to the backbone, which addressed the loss of fine-grained information and the less efficient learning of feature representations present in YOLOv8. Lastly, we reduced the large detection layer, which directed the network to pay more attention to the location, channel, and dimensional information of smaller objects, and we also replaced the loss function with WIoUv3. We validated our model using ablation studies and compared it with YOLOv5, YOLOv6, and YOLOv8. The mAP (Mean Average Precision) of the improved model I_YOLOv8 reaches 98.5%, which is 6.7% higher than YOLOv8. The average recognition time per image was 163.9fps, a boost of 5.2fps compared to YOLOv8. This study lays a theoretical foundation for the efficient, convenient, and rapid detection of maize quality, while also offering a technical basis for advancing automated maize quality detection means.

show abstract

Section: Introuductionmentioning

confidence: 99%

Research on a Lightweight Method for Maize Seed Quality Detection Based on Improved YOLOv8

Niu,

Xu,

Liang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

Broadening the Research Pathways in Smart Agriculture: Predictive Analysis Using Semiautomatic Information Modeling

Sharma

Sharma²,

Sharma³

et al. 2022

Journal of Sensors

View full text Add to dashboard Cite

Agriculture has become more industrialized and intensive due to the rising demand for food in quality and quantity. Agricultural modernization will be made possible by the Internet of Things (IoT), a technology with a great promise for revolutionizing the industry. Agricultural products will be in high demand by 2050 due to a 30% increase in the global population, so there is a need to devise new mechanisms for agriculture, and smart agriculture is one of those mechanisms; however, smart agriculture needs to be explored further to realize its potential fully. So, to explore the potential of this field, the researchers have used a corpus that is extracted from the Scopus database from the year 2008 to the year 2022 and applied the LDA technique. A corpus of 4309 articles was selected from the Scopus database to apply the latent Dirichlet analysis (LDA) model to predict research areas for smart agriculture. Using IoT technology, farmers and producers may better manage their resources, such as fertilizer consumption and the number of trips made by farm vehicles, while minimizing waste and maximizing productivity, including water, electricity, and other inputs. This data-driven experimental study identifies smart agriculture research trends by implementing a topic modeling technique previously used in smart agriculture. The authors have created seventeen research themes in smart agriculture based on the LDA topic modeling. This analysis suggests that the indicated areas are in the growth phase and require further research and exploration.

show abstract

Research on Color and Shape Recognition of Maize Diseases Based on HSV and OTSU Method

Cited by 2 publications

References 3 publications

Research on a Lightweight Method for Maize Seed Quality Detection Based on Improved YOLOv8

Research on a Lightweight Method for Maize Seed Quality Detection Based on Improved YOLOv8

Broadening the Research Pathways in Smart Agriculture: Predictive Analysis Using Semiautomatic Information Modeling

Contact Info

Product

Resources

About