AI-driven orchard management: Advancing sustainable apple production through convolutional neural network recognition

The aim of this study is to develop a convolutional neural network architecture designed for apple recognition in images. The relevance of this task is tied to the need for fruit recognition to automate the process of apple crop harvesting. To reduce computations, it is proposed to convert the image...

Full description

Saved in:
Bibliographic Details
Main Authors: Karabanov Georgy, Ricardo Oke Olouafemi, Krakhmalev Alexey
Format: Article
Language:English
Published: EDP Sciences 2025-01-01
Series:E3S Web of Conferences
Online Access:https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/14/e3sconf_icaw2024_03018.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849717188623073280
author Karabanov Georgy
Ricardo Oke Olouafemi
Krakhmalev Alexey
author_facet Karabanov Georgy
Ricardo Oke Olouafemi
Krakhmalev Alexey
author_sort Karabanov Georgy
collection DOAJ
description The aim of this study is to develop a convolutional neural network architecture designed for apple recognition in images. The relevance of this task is tied to the need for fruit recognition to automate the process of apple crop harvesting. To reduce computations, it is proposed to convert the image captured by the camera from RGB format to HSV format. Using the example of a red apple, the creation of a bitmask is demonstrated, which allows for the identification of regions of the desired color within the image. A structure and parameters of the convolutional neural network were proposed, along with a method for computing the distance between the detected object and the camera based on the pre-calculation of the focal length. To analyze the results of the neural network under consideration, software was developed in Python using the TensorFlow and Keras libraries. The training and testing of the neural network were conducted on a PC Aspire A315-23 with an AMD Athlon Silver 3050U 1.2 GHz processor, 4 GB DDR4 RAM, and an AMD Radeon Graphics 2.30 GHz graphics card, running Windows 11 Pro operating system. The neural network was trained for 15 epochs, taking 217 seconds in total. Object recognition by the trained neural network took around 1 second. The proposed convolutional neural network model demonstrated a recognition accuracy of 86% on the test image set.
format Article
id doaj-art-a64680107f7146e2b5cc672334eee84d
institution DOAJ
issn 2267-1242
language English
publishDate 2025-01-01
publisher EDP Sciences
record_format Article
series E3S Web of Conferences
spelling doaj-art-a64680107f7146e2b5cc672334eee84d2025-08-20T03:12:46ZengEDP SciencesE3S Web of Conferences2267-12422025-01-016140301810.1051/e3sconf/202561403018e3sconf_icaw2024_03018AI-driven orchard management: Advancing sustainable apple production through convolutional neural network recognitionKarabanov Georgy0Ricardo Oke Olouafemi1Krakhmalev Alexey2Department of Computer Science and Computer Engineering of Food Production, Russian Biotechnological University «ROSBIOTECH»Department of Automated Control Systems for Biotechnological Processes, Russian Biotechnological University «ROSBIOTECH»Russian State Agrarian University–Timiryazev Moscow Agricultural Academy, Institute of Mechanics and PowerThe aim of this study is to develop a convolutional neural network architecture designed for apple recognition in images. The relevance of this task is tied to the need for fruit recognition to automate the process of apple crop harvesting. To reduce computations, it is proposed to convert the image captured by the camera from RGB format to HSV format. Using the example of a red apple, the creation of a bitmask is demonstrated, which allows for the identification of regions of the desired color within the image. A structure and parameters of the convolutional neural network were proposed, along with a method for computing the distance between the detected object and the camera based on the pre-calculation of the focal length. To analyze the results of the neural network under consideration, software was developed in Python using the TensorFlow and Keras libraries. The training and testing of the neural network were conducted on a PC Aspire A315-23 with an AMD Athlon Silver 3050U 1.2 GHz processor, 4 GB DDR4 RAM, and an AMD Radeon Graphics 2.30 GHz graphics card, running Windows 11 Pro operating system. The neural network was trained for 15 epochs, taking 217 seconds in total. Object recognition by the trained neural network took around 1 second. The proposed convolutional neural network model demonstrated a recognition accuracy of 86% on the test image set.https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/14/e3sconf_icaw2024_03018.pdf
spellingShingle Karabanov Georgy
Ricardo Oke Olouafemi
Krakhmalev Alexey
AI-driven orchard management: Advancing sustainable apple production through convolutional neural network recognition
E3S Web of Conferences
title AI-driven orchard management: Advancing sustainable apple production through convolutional neural network recognition
title_full AI-driven orchard management: Advancing sustainable apple production through convolutional neural network recognition
title_fullStr AI-driven orchard management: Advancing sustainable apple production through convolutional neural network recognition
title_full_unstemmed AI-driven orchard management: Advancing sustainable apple production through convolutional neural network recognition
title_short AI-driven orchard management: Advancing sustainable apple production through convolutional neural network recognition
title_sort ai driven orchard management advancing sustainable apple production through convolutional neural network recognition
url https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/14/e3sconf_icaw2024_03018.pdf
work_keys_str_mv AT karabanovgeorgy aidrivenorchardmanagementadvancingsustainableappleproductionthroughconvolutionalneuralnetworkrecognition
AT ricardookeolouafemi aidrivenorchardmanagementadvancingsustainableappleproductionthroughconvolutionalneuralnetworkrecognition
AT krakhmalevalexey aidrivenorchardmanagementadvancingsustainableappleproductionthroughconvolutionalneuralnetworkrecognition