Abstract
[Objective] To improve the detection accuracy of early apple spoilage zone. [Methods] An apple spoilage detection method was proposed based on generative adversarial network and convolutional neural network. The Pix2PixHD model was used to generate near-infrared imaging data of stored apples in the early postharvest metamorphic area. The Mask R-CNN model was used to segment the generated near Infrared image to detect the deterioration zone in the apple. Based on generative adversarial network and convolutional neural network technology, the early deterioration region segmentation and prediction of postharvest apples were implemented by using the generated near-infrared imaging data on a low-cost embedded system with artificial intelligence function. [Results] The average accuracy of this method was 1.825%～10.435% higher than that of the other nine methods. The Pix2PixHD generated a visible NIR image from an RGB image at 17 frames per second, and the Mask R-CNN was able to segment spoilage areas in an apple image at 4.2 frames per second. [Conclusion] The proposed method is expected to facilitate the development of low-cost food quality controllers.
Publication Date
7-22-2024
First Page
143
Last Page
151,169
DOI
10.13652/j.spjx.1003.5788.2024.60038
Recommended Citation
Qilong, YU; Xiaodong, ZHAO; Yu, JI; Chunrong, WANG; and Yao, SUN
(2024)
"Early spoilage detection of apple based on generative adversarial network and Mask R-CNN,"
Food and Machinery: Vol. 40:
Iss.
6, Article 20.
DOI: 10.13652/j.spjx.1003.5788.2024.60038
Available at:
https://www.ifoodmm.cn/journal/vol40/iss6/20
References
[1] 赵敏, 王成荣, 李苒. 联合图像最优特征提取及改进RBF神经网络的苹果质量估计[J]. 食品与机械, 2024, 40（2）: 125-130, 183.
ZHAO M, WANG C R, LI R. Apple weight estimation based on joint image optimal feature extraction and improved RBF neural network[J]. Food & Machinery, 2024, 40（2）: 125-130, 183.
[2] 符灵梅, 王玉健, 徐莉, 等. 超高效液相色谱—串联质谱法快速分析氰霜唑及其代谢物CCIM在水果中的残留[J]. 食品与生物技术学报, 2022, 41（9）: 93-103.
FU L M, WANG Y J, XU L, et al. Rapid analysis of cyazofamid and CCIM residues in fruits by ultra-high performance liquid chromatography tandem mass-spectrometry[J]. Journal of Food Science and Biotechnology, 2022, 41（9）: 93-103.
[3] 关洪浦, 耿明阳, 周逸博, 等. 基于SERS的苹果树腐烂病原菌早期侵染检测[J]. 农业工程学报, 2024, 40（5）: 224-230.
GUAN H P, GENG M Y, ZHOU Y B, et al. Early infection detection of applevalsa canker pathogens based on SERS[J]. Transactions of the Chinese Society of Agricultural Engineering, 2024, 40（5）: 224-230.
[4] 代云, 卢明, 何婷, 等. 基于改进型YOLO的密集环境下槟榔果实的快速识别方法[J]. 食品与机械, 2023, 39（4）: 83-88.
DAI Y, LU M, HE T, et al. Fast recognition method for betel nut in dense environments based on improved YOLO[J]. Food & Machinery, 2023, 39（4）: 83-88.
[5] 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.
[6] BUYUKARIKAN B, ULKER E. Classification of physiological disorders in apples fruit using a hybrid model based on convolutional neural network and machine learning methods[J]. Neural Computing and Applications, 2022, 34（19）: 16 973-16 988.
[7] 李鑫, 沈晓君, 王媛媛, 等. 近红外光谱法快速测定晒青毛茶三种儿茶素组分含量[J]. 现代食品科技, 2024, 40（3）: 326-332.
LI X, SHEN X J, WANG Y Y, et al. Rapid determination of three catechin components in crude Pu-erh tea by near infrared spectroscopy[J]. Modern Food Science and Technology, 2024, 40（3）: 326-332.
[8] EKRAMIRAD N, KHALED A Y, DOYLE L E, et al. Nondestructive detection of codling moth infestation in apples using pixel-based nir hyperspectral imaging with machine learning and feature selection[J]. Foods, 2021, 11（1）: 8.
[9] 陈龙跃, 段丹丹, 王凡, 等. 高光谱成像技术在水果品质无损检测中的研究进展[J]. 广东农业科学, 2023, 50（7）: 83-94.
CHEN L Y, DUAN D D, WANG F, et al. Research progress of non-destructive testing of fruit quality by hyperspectral imaging technology[J]. Guangdong Agricultural Sciences, 2023, 50（7）: 83-94.
[10] SA I, LIM J Y, AHN H S, et al. DeepNIR: datasets for generating synthetic NIR images and improved fruit detection system using deep learning techniques[J]. Sensors, 2022, 22（13）: 4 721.
[11] STASENKO N, SAVINOV M, BURLUSKIY V, et al. Deep learning for postharvest decay prediction in apples[C]// IECON 2021-47th Annual Conference of the IEEE Industrial Electronics Society. [S.l.]: IEEE, 2021: 1-6.
[12] 朱赫鹏, 丁喆, 张严, 等. 基于生成对抗网络的跨分辨率拓扑优化方法的比较研究[J]. 振动与冲击, 2024, 43（6）: 132-140.
ZHU H P, DING Z, ZHANG Y, et al. Comparative study on cross-resolution topology optimization methods based on generative adversarial networks[J]. Journal of Vibration and Shock, 2024, 43（6）: 132-140.
[13] 陈嘉欣, 孙传猛, 葛耀栋, 等. 基于CycleGAN和Pix2Pix的轨面缺陷图像智能生成技术[J]. 铁道学报, 2024, 46（2）: 122-130.
CHEN J X, SUN C M, GE Y D, et al. Intelligent generation of rail surface defect images based on CycleGAN and Pix2Pix[J]. Journal of the China Railway Society, 2024, 46（2）: 122-130.
[14] 高志军, 冀远明, 史二美. 基于改进pix2pixHD模型的COVID-19 CT图像生成方法研究[J]. 智能计算机与应用, 2023, 13（5）: 82-89, 97.
GAO Z Y, YI Y M, SHI E M. Generation method of the COVID-19 CT image based on improved pix2pixHD model[J].Intelligent Computer and Applications, 2023, 13（5）: 82-89, 97.
[15] 赵振宇, 杨天豪, 蒋汶乘, 等. 基于机器学习的多压多温多参标准单元延迟快速计算方法[J]. 计算机工程与科学, 2023, 45（8）: 1 331-1 338.
ZHAO Z Y, YANG T H, JIANG W C, et al. A machine learning-based fast calculation method of multi-voltage, multi-temperature and multi-parameter standard celldelay[J]. Computer Engineering & Science, 2023, 45（8）: 1 331-1 338.
[16] 夏军勇, 王康宇, 周宏娣. 基于改进Faster R-CNN的食品包装缺陷检测[J]. 食品与机械, 2023, 39（11）: 131-136, 151.
XIA J Y, WANG K Y, ZHOU H D, et al. Food packaging defect detection by improved network model of Faster R-CNN[J]. Food & Machinery, 2023, 39（11）: 131-136, 151.
[17] FAN S X, LIANG X T, HUANG W Q, et al. Real-time defects detection for apple sorting using NIR cameras with pruning-based YOLOV4 network[J]. Computers and Electronics in Agriculture, 2022, 193: 106715.
[18] TANG Y, BAI H Y, SUN L J, et al. Multi-band-image based detection of apple surface defect using machine vision and deep learning[J]. Horticulturae, 2022, 8（7）: 666.
[19] TIAN M M, ZHANG J C, YANG Z R, et al. Detection of early bruises on apples using near-infrared camera imaging technology combined with adaptive threshold segmentation algorithm[J]. Journal of Food Process Engineering, 2024, 47（1）: e14500.
[20] YUAN R R, LIU G S, HE J G, et al. Classification of Lingwu long jujube internal bruise over time based on visible near-infrared hyperspectral imaging combined with partial least squares-discriminant analysis[J]. Computers and Electronics in Agriculture, 2021, 182: 106043.
[21] YANG Z R, YUAN Y H, ZHENG J H, et al. Early apple bruise recognition based on near-infrared imaging and grayscale gradient images[J]. Journal of Food Measurement and Characterization, 2023, 17（3）: 2 841-2 849.
[22] HU Q X, TIAN J, FANG Y. Detection of moldy cores in apples with near-infrared transmission spectroscopy based on wavelet and BP network[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2019, 33（12）: 1950020.