Mature pomegranate recognition methods in natural environments using machine vision

Lei, Xiangxiao; Ouyang, Haibin; Xu, Lijuan

doi:10.1590/0103-8478cr20190298

Cited by 8 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As such, the area growth can be achieved to measure the color similarity between each pixel in the seed area and the 8 neighboring pixels. Lei et al [104] used the kernel fuzzy C-means clustering to segment the pomegranate images. Song et al [105] achieved the segmentation of eggplant images using artificial neural networks.…”

Section: Visual Algorithmmentioning

confidence: 99%

Review of smart robots for fruit and vegetable picking in agriculture

Yang

2022

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

The fruit and vegetable picking has posed a great challenge on the production and markets during the harvest season. Manual picking cannot fully meet the rapid requirements of each market, mainly due to the high labor-intensive and time-consuming tasks, even the aging and shortage of agricultural labor force in recent years. Alternatively, smart robotics can be an efficient solution to increase the planting areas for the markets in combination with changes in cultivation, preservation, and processing technology. However, some improvements still need to be performed on these picking robots. To document the progress in and current status of this field, this study performed a bibliometric analysis. This analysis evaluated the current performance characteristics of various fruit and vegetable picking robots for better prospects in the future. Five perspectives were proposed covering the robotic arms, end effectors, vision systems, picking environments, and picking performance for the large-scale mechanized production of fruits and vegetables in modern agriculture. The current problems of fruit and vegetable picking robots were summarized. Finally, the outlook of the fruit and vegetable picking robots prospected from four aspects: structured environment for fruit planting, the algorithm of recognition and positioning, picking efficiency, and cost-saving picking robots. This study comprehensively assesses the current research status, thus helping researchers steer their projects or locate potential collaborators.

show abstract

Section: Visual Algorithmmentioning

confidence: 99%

Review of smart robots for fruit and vegetable picking in agriculture

Yang

2022

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

show abstract

“…Its maximum value was 66.23 (genotype 26) and its minimum was 39.07 (genotype 27), in relation to the rates of minimum occurrence in the histogram (Table 4). Lei et al (2019) used the RGB, LAB, YCbCr, YIQ and HSV color models under different lighting conditions to recognize ripe pomegranate fruits. The Cr component of the YCbCr model showed the best image, and the ideal segmentation was the threshold with recognition at 0.048s during the day, with 90.3% accuracy in the recognition of ripe pomegranates.…”

Section: Digital Phenotyping Meansmentioning

confidence: 99%

Digital Phenotyping in Inbred Guava Lines: Seed Characterization

Silva¹,

Vieira²,

Viana³

et al. 2021

FPBJ

View full text Add to dashboard Cite

Guava, Psidium guajava L., is a species of economic importance for several countries. The production of new varieties of guava from seeds with good germination and vigor potential has been investigated. In this scenario, the present study characterized and estimated the genetic diversity of seeds of 42 genotypes of guava from an S2 family based on germination response, vigor tests, and digital phenotyping analysis. The experiment was laid out in a randomized-block design with four replicates. Descriptive statistics were carried out for each of the analyzed variables and multivariate analyses were used to estimate genetic diversity based on Gower's Distance. Digital analysis was performed using the GroundEye S120 system, which extracted color, geometry, texture, and histogram data. In total, three color, two geometry, five texture, four physiological analysis, and 17 histogram variables were used. The physiological variables and those obtained by digital phenotyping were efficient to discriminate the genotypes, indicating that there is genetic variability to be exploited within the guava breeding program. The traits that most contributed to genetic diversity were those related to the histogram. The genotypes belonging to groups I and III had the highest means for germination percentage, thousand-seed weight, and shoot length. Based on the results, two options are viable for conducting the guava breeding program. The most vigorous individuals can be self-pollinated for the development of lines and the superior and most divergent ones from groups I and III can be crossed to exploit heterosis. Thus, crosses between the most vigorous individuals from groups I and III are recommended, as they exhibited higher means for the traits of germination percentage, thousand-seed weight, and shoot length.

show abstract

“…With the development and application of deep learning, many target detection algorithms have emerged. The mainstream target detection algorithms: Region proposal-based R-CNN algorithms, and one-stage algorithms like you look only once (YOLO) and single shot detector (SSD) [6].…”

Section: Glass Defect Detection Based On Faster-rcnnmentioning

confidence: 99%

End Image Defect Detection of Float Glass Based on Faster Region-Based Convolutional Neural Network

Jin¹,

Xu²,

Tong³

et al. 2020

View full text Add to dashboard Cite

The float glass contains various defects for reasons of raw materials and production process. These defects can be observed on the end images of the glass. Since the defects are correlated with specific links of the production process, it is possible to discover the process problems by identifying the location and type of defects in end images. Based on faster region-based convolutional neural network (Faster RCNN), this paper proposes a deep learning method that improves the feature extraction network, and adds a Laplacian convolutional layer to preprocess the end images. Considering the defect features in end images, the anchor box size was adjusted to speed up the training. Besides, the lack of generalizability induced by small dataset was solved through data enhancement. With improved VGG16 as the feature extraction layer, a glass defect detection model was established, whose generalizability was improved through transfer learning. The experimental results show that the proposed model achieved a mean detection accuracy of 94% on actual test set, meeting the requirements for actual use in factories.

show abstract

Mature pomegranate recognition methods in natural environments using machine vision

Cited by 8 publications

References 8 publications

Review of smart robots for fruit and vegetable picking in agriculture

Review of smart robots for fruit and vegetable picking in agriculture

Digital Phenotyping in Inbred Guava Lines: Seed Characterization

End Image Defect Detection of Float Glass Based on Faster Region-Based Convolutional Neural Network

Contact Info

Product

Resources

About