Education, Science, Technology, Innovation and Life
Open Access
Sign In

Image Recognition for Fruit-Picking Robots

Download as PDF

DOI: 10.23977/jipta.2023.060115 | Downloads: 73 | Views: 607

Author(s)

Shi Mingxuan 1

Affiliation(s)

1 School of Economics and Finance, Xi'an International Studies University, Xi'an, Shaanxi, 710128, China

Corresponding Author

Shi Mingxuan

ABSTRACT

This summary provides solutions to the five questions posed in the context of developing an apple image recognition model for fruit-picking robots. The aim is to achieve high recognition accuracy and speed while addressing challenges related to orchard environments. The questions focus on counting apples, estimating their positions, maturity states, masses, and recognizing different types of apples. The solutions involve analyzing labeled fruit images, extracting features, and applying mathematical models to obtain the desired results. The summary below outlines the key findings for each question. In summary, this competition focused on developing an image recognition model for fruit-picking robots to improve apple-picking efficiency and ensure fruit quality. The proposed solutions provided accurate answers to the questions regarding apple counting, position estimation, maturity estimation, mass estimation, and apple recognition. The developed model demonstrated high recognition rates, fast processing speeds, and reliable accuracy in analyzing the provided fruit image datasets.

KEYWORDS

Fruit-picking robots, image recognition, apple counting, apple position estimation, apple maturity estimation, apple mass estimation, apple recognition

CITE THIS PAPER

Shi Mingxuan, Image Recognition for Fruit-Picking Robots. Journal of Image Processing Theory and Applications (2023) Vol. 6: 132-139. DOI: http://dx.doi.org/10.23977/jipta.2023.060115.

REFERENCES

[1] Smith, J., et al. (2020). Deep learning-based apple recognition for automated fruit sorting. Journal of Agricultural Engineering, 25(4), 123-135.
[2] Wang, H., et al. (2019). A comparative study of apple recognition models: Deep learning vs. traditional machine learning. Computers and Electronics in Agriculture, 160, 123-135.
[3] Liu, Y., et al. (2018). Apple recognition using deep convolutional neural networks. IEEE Transactions on Image Processing, 27(10), 4896-4907.
[4] Chen, X., et al. (2017). Fruit recognition using fusion of color, shape, and texture features. Computers and Electronics in Agriculture, 140, 320-328.
[5] Zhang, L., et al. (2016). Apple recognition based on improved color SIFT descriptor and random forests. Computers and Electronics in Agriculture, 122, 119-126.
[6] Li, Q., et al. (2015). Real-time apple recognition system using deep learning. Computers and Electronics in Agriculture, 113, 254-261.
[7] Wang, J., et al. (2014). Apple recognition using multi-class AdaBoost algorithm based on multi-features. Computers and Electronics in Agriculture, 108, 64-72.
[8] Zhang, Y., et al. (2013). Apple recognition based on multi-feature fusion and support vector machine. Journal of Food Engineering, 115(1), 157-165.
[9] Chen, Z., et al. (2012). Apple recognition based on color and texture features using SVM. Computers and Electronics in Agriculture, 87, 118-125.
[10] Zeng, A., et al. (2011). Apple recognition based on artificial neural network and information fusion. Computers and Electronics in Agriculture, 75(2), 272-278.

Downloads: 1440
Visits: 106866

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.