Lightweight banana ripeness detection based on improved Alexnet

Authors

JIANG Yu, Guangxi Agricultural Vocational and Technical University, Nanning, Guangxi 530007, China
WANG Lingmin, Guilin University of Technology at Nannning, Nanning, Guangxi 530001, ChinaFollow

Corresponding Author(s)

王灵敏（1989—），女，桂林理工大学南宁分校工程师，硕士。E-mail:742709113@qq.com

Abstract

Objective: To obtain a lightweight Mini-Alexnet banana ripeness grading model and apply it to Android mobile devices. Methods: Based on the external characteristics of bananas with different ripeness, the Alexnet network model was restructured, part of the convolutional layer was deleted, and the global average pooling was used instead of the full connection layer to reduce the model parameters and required memory. A larger convolutional kernel was replaced to extract the global characteristics of the banana skin to achieve an improved lightweight Mini-Alexnet network model. Then the Mini-Alexnet network model was deployed as Android mobile APP, and its feasibility and practicability were verified. Results: The Mini-Alexnet model was only 11.6 MB, and the identification accuracy rate of banana ripeness level 5 was 97.76%. The accuracy rate of local picture recognition mode, photo recognition mode and real-time recognition mode of the mobile APP banana ripeness automatic identification system was 86.66%, 79.33% and 74.00%, respectively, with an average accuracy rate of 80%. Conclusion: The improved Mini-Alexnet model occupies less memory space.

Publication Date

7-22-2024

First Page

128

Last Page

136

DOI

10.13652/j.spjx.1003.5788.2023.80986

Recommended Citation

Yu, JIANG and Lingmin, WANG (2024) "Lightweight banana ripeness detection based on improved Alexnet," Food and Machinery: Vol. 40: Iss. 5, Article 19.
DOI: 10.13652/j.spjx.1003.5788.2023.80986
Available at: https://www.ifoodmm.cn/journal/vol40/iss5/19

References

[1] 刘海军, 赵文锋, 刘韵锋, 等. 基于ANN和贝叶斯优化算法的香蕉成熟度检测模型研究[J]. 现代农业装备, 2021, 42（5）: 42-46. LIU H J, ZHAO W F, LIU Y F, et al. Model for detecting banana maturity based on artificial neural network and bayesian optimization algorithm[J]. Modern Agricultural Equipment, 2021, 42（5）: 42-46.
[2] 刘阳泰, 董庆利, 秦智轩, 等. 基于Android智能手机图像分析判定香蕉成熟阶段[J]. 食品与发酵工业, 2016, 42（1）: 212-218. LIU Y T, DONG Q L, QIN Z X, et al. Determination of banana ripening stage based on Android smartphone image analysis[J]. Food and Fermentation Industry, 2016, 42（1）: 212-218.
[3] 王顺. 水果成熟度检测的机器视觉和嗅觉可视化技术研究[D]. 杭州: 江苏大学, 2018: 2-5. WANG S. Research on machine vision and olfactory visualization technology for fruit maturity detection[D]. Hangzhou: Jiangsu University, 2018: 2-5.
[4] SANAEIFAR A, MOHTASEBI S S, GHASEMI-VARNAMKHASTI M, et al. Application of MOS based electronicnose for the prediction of banana quality properties[J]. Measurement, 2016, 82: 105-114.
[5] RAJKUMAR P, WANG N, EIMASRY G, et al. Studies on banana fruit quality and maturity stages using hyperspectral imaging[J]. Journal of Food Engineering, 2012, 108（1）: 194-200.
[6] 黎源鸿, 王红军, 邓建猛, 等. 基于PCA-ELM和光谱技术预测香蕉成熟度[J]. 现代食品科技, 2017, 33（10）: 268-274. LI Y H, WANG H J, DENG J M, et al. Prediction of banana maturity based on PCA-ELM and spectral technology[J]. Modern Food Technology, 2017, 33（10）: 268-274.
[7] SOLTANI M, ALIMARDANI R, OMID M. Prediction of banana quality during ripening stage using capacitance sensing system[J]. Australian Journal of Crop Science, 2010, 4（6）: 443-447.
[8] CHEN C R, ＲAMASWAMY H S. Color and texture change kinetics in ripening bananas[J]. LWT-Food Science and Technology, 2002, 35（5）: 415-419.
[9] 樊刚伦. 香蕉无伤采收及采后商品处理技术[J]. 农业与技术, 2012, 32（11）: 104. FAN G L. Techniques for harmless harvesting and postharvest commodity treatment of bananas[J]. Agriculture and Technology, 2012, 32（11）: 104.
[10] 王文超, 葛凤丽, 徐文凯, 等. 水果品质分选机的研发[J]. 食品与机械, 2022, 38（9）: 98-102. WANG W C, GE F L, XU W K, et al. Research and development of fruit quality sorting machine[J]. Food & Machinery, 2022, 38（9）: 98-102.
[11] 陈锋军, 张新伟, 朱学岩, 等. 基于改进EfficientDet的油橄榄果实成熟度检测[J]. 农业工程学报, 2022, 38（13）: 158-166. CHEN F J, ZHANG X W, ZHU X Y, et al. Maturity detection of olive fruit based on improved EfficientDet[J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38（13）: 158-166.
[12] 朱旭, 马淏, 姬江涛, 等. 基于Faster R-CNN的蓝莓冠层果实检测识别分析[J]. 南方农业学报, 2020, 51（6）: 1 493-1 501. ZHU X, MA H, JI J T, et al. Detection and identification analysis of blueberry canopy fruits based on Faster R-CNN[J]. Journal of Southern Agriculture, 2020, 51（6）: 1 493-1 501.
[13] 王辉, 张帆, 刘晓凤, 等. 基于DarkNet-53和YOLOv3的水果图像识别[J]. 东北师大学报（自然科学版）, 2020, 52（4）: 60-65. WANG H, ZHANG F, LIU X F, et al. Fruit image recognition based on DarkNet-53 and YOLOv3[J]. Journal of Northeast Normal University （Natural Science Edition）, 2020, 52（4）: 60-65.
[14] VIJAYAKUMAR T, VINOTHKANNA R. Mellowness detection of dragon fruit using deep learning strategy[J]. Journal of Innovative Image Processing, 2020（1）: 35-43.
[15] 穆龙涛, 高宗斌, 崔永杰, 等. 基于改进AlexNet的广域复杂环境下遮挡猕猴桃目标识别[J]. 农业机械学报, 2019, 50（10）: 24-34. MU L T, GAO Z B, CUI Y J, et al. Recognition of occluded kiwifruit targets in wide-area complex environments based on improved AlexNet[J]. Journal of Agricultural Machinery, 2019, 50（10）: 24-34.
[16] 张瑞青, 李张威, 郝建军, 等. 基于迁移学习的卷积神经网络花生荚果等级图像识别[J]. 农业工程学报, 2020, 36（23）: 171-180. ZHANG R Q, LI Z W, HAO J J, et al. Convolutional neural network based on transfer learning for peanut pod level image recognition[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36（23）: 171-180.
[17] 王灵敏, 蒋瑜. 基于深度学习的香蕉成熟度自动分级[J]. 食品与机械, 2022, 38（11）: 149-154. WANG L M, JIANG Y. Automatic classification of banana ripeness based on deep learning[J]. Food & Machinery, 2022, 38（11）: 149-154.
[18] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60（6）: 84-90.
[19] 孙道宗, 丁郑, 刘锦源, 等. 基于改进SqueezeNet模型的多品种茶树叶片分类方法[J]. 农业机械学报, 2023, 54（2）: 223-230, 248. SUN D Z, DING Z, LIU J Y, et al. A multi variety tea tree leaf classification method based on improved SqueezeNet model[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54（2）: 223-230, 248.
[20] 李阳德, 马晓慧, 王骥. 基于轻量级MobileNet V3-YOLOv4的生长期菠萝成熟度分析[J]. 智慧农业（中英文）, 2023, 5（2）: 35-44. LI D Y, MA X H, WANG J. Analysis of pineapple maturity during growth period based on lightweight MobileNet V3-YOLOv4[J]. Smart Agriculture, 2023, 5（2）: 35-44.
[21] 吕金锐, 付燕, 倪美玉, 等. 基于改进YOLOv4模型的番茄成熟度检测方法[J]. 食品与机械, 2023, 39（9）: 134-139. LU J R, FU Y, NI M Y, et al. Research on tomato maturity detection method based on improved YOLOv4 model[J]. Food & Machinery, 2023, 39（9）: 134-139.
[22] 李志臣, 凌秀军, 李鸿秋, 等. 基于改进ShuffleNet的板栗分级方法[J]. 山东农业大学学报（自然科学版）, 2023, 54（2）: 299-307. LI Z C, LING X J, LI H Q, et al. Chestnut grading method based on improved ShuffleNet[J]. Journal of Shandong Agricultural University （Natural Science Edition）, 2023, 54（2）: 299-307.
[23] ZHOU Z, SONG Z, FU L, et al. Real-time kiwifruit detection in orchard using deep learning on Android^TM smartphones for yield estimation[J]. Comput Electron Agric, 2020, 179: 105856.
[24] GENAEV M A, KOMYSHEV E G, SHISHKINA O D, et al. Classification of fruit flies by gender in images using smartphones and the YOLOv4-tiny neural network[J]. Mathematics, 2022, 10（3）: 295.
[25] ZENG T, LI S, SONG Q, et al. Lightweight tomato real-time detection method based on improved YOLO and mobile deployment[J]. Computers and Electronics in Agriculture, 2023, 205: 107625.
[26] ELWIREHARDJA G N, PRAYOGA J S. Oil palm fresh fruit bunch ripeness classification on mobile devices using deep learning approaches[J]. Computers and Electronics in Agriculture, 2021, 188: 106359.