Abstract
Objective: To improve the identification accuracy of fruit categories. Methods: An identification method for fruit categories was established based on an improved Faster regional convolutional neural network （Faster R-CNN） model. Firstly, the regularization method was used to attenuate the weight of some high-dimensional parameters to effectively solve the over-fitting problem that may occur in the training process. Then, two loss functions, a likelihood function and a regularization function, were added to the Faster R-CNN framework to optimize the convolution layer and the pooling layer. Additionally, the least square method was utilized to solve the objective function of fruit recognition. Finally, the accuracy, recall rate, precision and F1 score were used to evaluate the fruit identification effect of the trained fruit identification method. Results: The accuracy, precision and recall rates of the proposed method for fruit identification reached 99.69%, 0.996 8 and 0.994 8, respectively. Compared with the other 10 fruit identification methods, the accuracy, precision and recall rate of the proposed method were at least 0.91%, 1.32% and 0.51% higher. Conclusion: The method can realize the accurate recognition of different categories of fruits.
Publication Date
10-20-2023
First Page
129
Last Page
135
DOI
10.13652/j.spjx.1003.5788.2023.60037
Recommended Citation
Yanping, JIAN; Yanli, SANG; and Yueru, LI
(2023)
"Fruit identification using improved Faster R-CNN model,"
Food and Machinery: Vol. 39:
Iss.
8, Article 20.
DOI: 10.13652/j.spjx.1003.5788.2023.60037
Available at:
https://www.ifoodmm.cn/journal/vol39/iss8/20
References
[1] 胡国喜, 王超, 刘宇珩. 基于改进光滑滑模阻抗控制的水果分拣机械人夹持机构控制方法[J]. 食品与机械, 2021, 37（2）: 130-134.
HU G X, WANG C, LIU Y H. A control technique for clamping mechanism of fruit sorting robot based on improved smooth sliding mode impedance control[J]. Food & Machinery, 2021, 37（2）: 130-134.
[2] 王成军, 韦志文, 严晨. 基于机器视觉技术的分拣机器人研究综述[J]. 科学技术与工程, 2022, 22（3）: 893-902.
WANG C J, WEI Z W, YAN C. Review on sorting robot based on machine vision technology[J]. Science Technology and Engineering,2022, 22（3）: 893-902.
[3] 唐媛红, 刘月云. 基于PLC的水果分拣机器人动作控制优化[J]. 农机化研究, 2021, 43（12）: 233-237.
TANG Y H, LIU Y Y. Optimization of fruit sorting robot action control based on PLC[J]. Journal of Agricultural Mechanization Research, 2021, 43（12）: 233-237.
[4] 魏冉, 裴悦琨, 姜艳超, 等. 基于改进Faster R-CNN模型的樱桃缺陷检测[J]. 食品与机械, 2021, 37（10）: 98-105, 201.
WEI R, PEI Y K, JIANG Y C, et al. Detection of cherry defects based on improved Faster R-CNN model[J]. Food & Machinery, 2021, 37（10）: 98-105, 201.
[5] 金宗毅, 陶学恒, 金艳, 等. 海产品智能分拣装备与系统设计[J]. 食品与机械, 2022, 38（3）: 75-79.
JIN Z Y, TAO X H, JIN Y, et al. Intelligent sorting equipment and system design of seafood[J]. Food & Machinery, 2022, 38（3）: 75-79.
[6] 刘春妹, 高洪民, 王学田, 等. 基于深度学习的水果图像识别系统[J]. 微波学报, 2020, 36（S1）: 427-430.
LIU C M, GAO H M, WANG X T, et al.Fruit image recognition system based on deep learning[J]. Journal of Microwaves, 2020, 36（S1）: 427-430.
[7] INDIRA D N V S L S, GODDU J, INDRAJA B, et al. A review on fruit recognition and feature evaluation using CNN[J]. Materials Today: Proceedings, 2023 80: 3 438-3 443.
[8] 郑太雄, 江明哲, 冯明驰. 基于视觉的采摘机器人目标识别与定位方法研究综述[J]. 仪器仪表学报, 2021, 42（9）: 28-51.
ZHENG T X, JIANG M Z, FENG M C. Vision based target recognition and location for picking robot: A review[J]. Chinese Journal of Scientific Instrument, 2021, 42（9）: 28-51.
[9] NARANJO-TORRES J, MORA M, HERNNDEZ-GARCA R, et al. A review of convolutional neural network applied to fruit image processing[J]. Applied Sciences, 2020, 10（10）: 3 443.
[10] ZHONG S H, XU W P, ZHANG T H, et al. Identification and depth localization of clustered pod pepper based on improved Faster R-CNN[J]. IEEE Access, 2022, 10: 93 615-93 625.
[11] WAN S H, GOUDOS S. Faster R-CNN for multi-class fruit detection using a robotic vision system[J]. Computer Networks, 2020, 168: 107036.
[12] ZHANG Y D, DONG Z, CHEN X, et al. Image based fruit category classification by 13-layer deep convolutional neural network and data augmentation[J]. Multimedia Tools and Applications, 2019, 78: 3 613-3 632.
[13] DU L, SUN Y Q, CHEN S, et al. A novel object detection model based on faster R-CNN for spodoptera frugiperda according to feeding trace of corn leaves[J]. Agriculture, 2022, 12（2）: 248.
[14] MHALLA A, CHATEAU T, MAAMATOU H, et al. SMC faster R-CNN: Toward a scene-specialized multi-object detector[J]. Computer Vision and Image Understanding, 2017, 164: 3-15.
[15] LI L, HASSAN M A, YANG S R, et al. Development of image-based wheat spike counter through a Faster R-CNN algorithm and application for genetic studies[J]. The Crop Journal, 2022, 10（5）: 1 303-1 311.
[16] KARAR M E, ALSUNAYDI F, ALBUSAYMI S, et al. A new mobile application of agricultural pests recognition using deep learning in cloud computing system[J]. Alexandria Engineering Journal, 2021, 60（5）: 4 423-4 432.
[17] 黄晓红, 李铁锋, 刘祥鑫, 等. 基于改进Faster R-CNN算法的岩石裂隙发展方向跟踪预测研究[J]. 河南理工大学学报（自然科学版）, 2022, 41（4）: 134-141.
HUANG X H, LI T F, LIU X X, et al. Research on tracking and prediction of rock fissure development based on improved Faster R-CNN algorithm[J]. Journal of Henan Polytechnic University （Natural Science）, 2022, 41（4）: 134-141.
[18] KAGGLE. Fruits 360 dataset: A dataset of images containing fruits and vegetables\. [2023-04-20]. https://www.kaggle.com/moltean/fruit.
[19] MORID M A, BORJALI A, DEL FIOL G. A scoping review of transfer learning research on medical image analysis using ImageNet[J]. Computers in Biology and Medicine, 2021, 128: 104115.
[20] ZHAO Q, WANG X, LYU S C, et al. A feature consistency driven attention erasing network for fine-grained image retrieval[J]. Pattern Recognition, 2022, 128: 108618.
[21] 倪云峰, 叶健, 樊娇娇. 基于图像识别的水果分拣系统[J]. 江苏农业科学, 2021, 49（10）: 170-176.
NI Y F, YE J, FAN J J. Fruit sorting system based on image recognition[J]. Jiangsu Agricultural Science, 2021, 49（10）: 170-176.
[22] STEINBRENER J, POSCH K, LEITNER R. Hyperspectral fruit and vegetable classification using convolutional neural networks[J]. Computers and Electronics in Agriculture, 2019, 162: 364-372.
[23] WANG S H, CHEN Y. Fruit category classification via an eight-layer convolutional neural network with parametric rectified linear unit and dropout technique[J]. Multimedia Tools and Applications, 2020, 79: 15 117-15 133.
[24] JIA W K, TIAN Y Y, LUO R, et al. Detection and segmentation of overlapped fruits based on optimized mask R-CNN application in apple harvesting robot[J]. Computers and Electronics in Agriculture, 2020, 172: 105380.
[25] VASUMATHI M T, KAMARASAN M. An effective pomegranate fruit classification based on CNN-LSTM deep learning models[J]. Indian Journal of Science and Technology, 2021, 14（16）: 1 310-1 319.
[26] KHAN A, NAWAZ U, UIHAQ A, et al. Real-time plant health assessment via implementing cloud-based scalable transfer learning on AWS DeepLens[J]. PLoS One, 2020, 15（12）: e0243243.
[27] XUE G, LIU S F, MA Y C. A hybrid deep learning-based fruit classification using attention model and convolution autoencoder[J]. Complex & Intelligent Systems, 2023, 9: 2 209-2 219.