Abstract
Objective: Improve the identification accuracy of banana ripeness. Methods: A novel method was established to identify banana ripeness based on CNN and XgBoost. Firstly, convolutional neural network was used to extract banana image features, and full-connected layer network and linear discriminant analysis were used to simplify banana image features. Then, the hyperparameters of the limit gradient lifting algorithm were optimized by Bayesian optimization algorithm. Finally, the simplified banana image features were input into the limit gradient lifting algorithm, and the banana ripeness was judged by the limit gradient lifting algorithm. Results: The identification accuracy of the method for banana ripeness was 91.25%. Compared with the existing methods, the proposed method was more accurate to distinguish the ripeness of bananas with small data volume. Conclusion: The proposed method can realize the accurate identification of banana ripeness, which is helpful for warehouse managers and exporters to monitor banana ripeness in real time.
Publication Date
5-21-2024
First Page
127
Last Page
135,178
DOI
10.13652/j.spjx.1003.5788.2024.60015
Recommended Citation
Xue, HAN; Lei, ZHANG; Yafei, ZHAO; and Cong, WANG
(2024)
"Banana ripeness determination based on CNN and XgBoost,"
Food and Machinery: Vol. 40:
Iss.
4, Article 20.
DOI: 10.13652/j.spjx.1003.5788.2024.60015
Available at:
https://www.ifoodmm.cn/journal/vol40/iss4/20
References
[1] 覃翠钠, 李志春, 何雪梅, 等. 基于成熟度研究不同品种香蕉多酚含量及抗氧化活性的差异[J]. 食品工业科技, 2022, 43（22）: 52-60.
QIN C N, LI Z C, HE X M, et al. Polyphenol content and antioxidant capacity from banana with different varieties and maturity[J]. Science and Technology of Food Industry, 2022, 43（22）: 52-60.
[2] DO NASCIMENTO TINOCO L P, DE SA OLIVEIRA L, AUGUSTA I M, et al. Green banana biomass （Musa sp.） as an ingredient in the development of pasta[J]. Research, Society and Development, 2022, 11（3）: e2711326204.
[3] 彭思琪, 王娟. 香蕉皮总黄酮的提取及其抗氧化和抑制酪氨酸酶的活性[J]. 食品研究与开发, 2022, 43（20）: 132-140.
PENG S Q, WANG J. Antioxidant activity and inhibition ontyrosinase of total flavonoids extracted from banana peels[J]. Food Research and Development, 2022, 43（20）: 132-140.
[4] AFZAL M F, KHALID W, AKRAM S, et al. Bioactive profile and functional food applications of banana in food sectors and health: A review[J]. International Journal of Food Properties, 2022, 25（1）: 2 286-2 300.
[5] 张帅, 李跃森, 费鹏, 等. 香蕉果肉对乳酸菌在冻干和贮存中活性的影响[J]. 粮食与油脂, 2022, 35（7）: 87-92.
ZHANG S, LI Y S, FEI P, et al. Effects of banana pulp on the viability of lactic acid bacteria during freeze-drying and storage[J].Cereals & Oils, 2022, 35（7）: 87-92.
[6] 吴水金, 张帅, 林宝妹, 等. ‘香粉1号’香蕉成熟过程中挥发性成分组成及其变化分析[J]. 食品安全质量检测学报, 2023, 14（18）: 245-252.
WU S J, ZHANG S, LIN B M, et al. Composition and change analysis of volatile components in 'Xiangfen No.1' banana at different ripening stages[J]. Journal of Food Safety & Quality, 2023, 14（18）: 245-252.
[7] 莫松涛, 董涛, 赵汐璇, 等. 基于遗传算法与SVM的香蕉果实成熟度判别模型[J]. 果树学报, 2022, 39（12）: 2 418-2 427.
MO S T, DONG T, ZHAO X X, et al. Discriminant model of banana fruit maturity based on genetic algorithm and SVM[J]. Journal of Fruit Science, 2022, 39（12）: 2 418-2 427.
[8] 李芬芳, 李奕星, 袁德保, 等. 不同乙烯利浓度及贮藏温度对“南天黄”香蕉果实后熟品质的影响[J]. 中国南方果树, 2022, 51（2）: 72-77, 83.
LI F F, LI Y X, YUAN D B, et al. Effects of different concentrations of ethrel and storage temperatures on post-ripening quality of 'Nantianhuang' banana[J]. South China Fruits, 2022, 51（2）: 72-77, 83.
[9] 刘袆帆, 杜卉妍, 钟玉鸣, 等. 基于香蕉、粉蕉成熟过程中硬度变化建立成熟度随机森林模型[J]. 广东农业科学, 2020, 47（6）: 106-115.
LIU H F, DU H Y, ZHONG Y M, et al. Construction of maturity random forest models based on the changes of fruit firmness[J].Guangdong Agricultural Sciences, 2020, 47（6）: 106-115.
[10] 王菲菲, 刘彭, 孙凤伟, 等. 基于支持向量机和压力传感器的水果分类系统[J]. 食品与机械, 2023, 39（9）: 83-88.
WANG F F, LIU P, SUN F W, et al. Fruit classification system based on the pressure sensor coupled with support vector machine[J]. Food & Machinery, 2023, 39（9）: 83-88.
[11] MASEKO K H, REGNIER T, ANYASI T A, et al. Discrimination of Musa banana genomic and sub-genomic groups based on multi-elemental fingerprints and chemometrics[J]. Journal of Food Composition and Analysis, 2022, 106: 104334.
[12] 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.
[13] 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.
[14] 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.
[15] KAHFI A H, HASAN M, HASANAH R L. Classification of banana ripeness based on color and texture characteristics[J]. Journal of Computer Networks, Architecture and High Performance Computing, 2023, 5（1）: 10-17.
[16] SARANYA N, SRINIVASAN K, PRAVIN K S K. FBCNN-TSA: An optimal deep learning model for banana ripening stages classification[J]. Journal of Intelligent & Fuzzy Systems, 2023, 44（3）: 5 257-5 273.
[17] HE W W, HE H Y, WANG F L, et al. Rapid and uninvasive characterization of bananas by hyperspectral imaging with extreme gradient boosting （XGBoost） [J]. Analytical Letters, 2022, 55（4）: 620-633.
[18] 范志文, 光翠娥, 干建平. 基于反向传播人工神经网络的酱牛肉中金黄色葡萄球菌的生长模型[J]. 食品与生物技术学报, 2020, 39（7）: 83-90.
FAN Z W, GUANG C E, GAN J P. Growth model of Staphylococcusaureus in soy beef based on backpropagation artificial neural network[J]. Journal of Food Science and Biotechnology, 2020, 39（7）: 83-90.
[19] UPADHYAY A, SINGH S, KAOJIYA S. Segregation of ripe and raw bananas using convolutional neural network[J]. Procedia Computer Science, 2023, 218: 461-468.
[20] 高立秀, 陈得丽, 万兴淼, 等. 基于机器学习的切丝后含水率预测及控制方法[J]. 食品与机械, 2021, 37（4）: 189-194, 211.
GAO L X, CHEN D L, WAN X M, et al. Prediction and control method of moisture content after cutting based on machine learning[J]. Food & Machinery,2021, 37（4）: 189-194, 211.