Abstract
Objective: The study aimed to explore a fast and accurate method to detect brown spot and damage decay in grape bunches. Methods: Colour images （RGB） and near-infrared images （NIR） of red globe grapes bunches were captured by a near-infrared industrial camera. The edges of the samples and the edges of the defective parts were first extracted by applying the Sobel algorithm to the NIR images （NIR）, and then the images were binarized by the adaptive thresholding algorithm to achieve the segmentation of the images. Then the sample edges and fruit stalks were removed by the normalized supergreen method and the finding large connected domain algorithm to extract the shape feature parameters such as roundness, rectangularity and external rectangular aspect ratio of the defective part of red globe grapes bunches and fruit edges, respectively. Finally, a classification model based on BP neural network and support vector machine was developed to discriminate the defective parts and fruit edges. The model enables the rejection of kernel edges to obtain image information of brown spots and damage decay. Results: Using the above-mentioned testing method to verify 60 samples, the accuracy of discriminating red globe grape bunches with intact appearance was as high as 90.00%, those with defects reached 93.33%, and the overall discriminating accuracy reached 91.67%. Conclusion: The study established a method to detect brown spot and damage decay images to enable grading and selection of red globe grapes.
Publication Date
4-25-2023
First Page
146
Last Page
151
DOI
10.13652/j.spjx.1003.5788.2022.80409
Recommended Citation
Sheng, GAO
(2023)
"Defect detection method of red globe grapes bunches based on near infrared camera imaging,"
Food and Machinery: Vol. 39:
Iss.
1, Article 24.
DOI: 10.13652/j.spjx.1003.5788.2022.80409
Available at:
https://www.ifoodmm.cn/journal/vol39/iss1/24
References
[1] ZHANG J X, WU Z Y, SONG P, et al. Embryo feature extraction and dynamic recognition method for maize haploid seeds[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29（4）: 199-203.
[2] KHEIRALIPOUR K, ABBAS K. Introducing new shape features for classification of cucumber fruit based on image processing technique and artificial neural networks[J]. Journal of Food Process Engineering, 2017, 40（6）: e12558.
[3] 吴明清, 弋晓康, 罗华平, 等. 基于多轮廓模型的红枣体积和表面积在线测量方法[J]. 农业工程学报, 2019, 35（19）: 283-290.
[4] 陈林琳, 姜大庆, 黄菊, 等. 基于机器视觉的火龙果自动分级系统设计[J]. 农机化研究, 2020, 42（5）: 130-133.
[5] 李泽平, 郭俊先, 郭阳, 等. 基于支持向量机的无核白葡萄串分级系统设计与测试[J]. 食品与机械, 2021, 37（10）: 106-111, 246.
[6] 高辉, 马国峰, 刘伟杰. 基于机器视觉的苹果缺陷快速检测方法研究[J]. 食品与机械, 2020, 36（10）: 125-129, 148.
[7] 杜永忠, 平雪良, 何佳唯. 圣女果表面缺陷检测与分级系统研究[J]. 农业机械学报, 2013, 44（S1）: 194-199.
[8] 王昭. 基于机器视觉的樱桃缺陷检测[D]. 北京: 北京林业大学, 2019: 10-35.
[9] 邵志明, 王怀彬, 董志城, 等. 基于近红外相机成像和阈值分割的苹果早期损伤检测[J]. 农业机械学报, 2021, 52（S1）: 134-139.
[10] 陈英, 廖涛, 林初靠, 等. 基于计算机视觉的葡萄检测分级系统[J]. 农业机械学报, 2010, 41（3）: 169-172.
[11] 袁雷明. 基于多视成像及近红外光谱技术的巨峰葡萄品质无损检测研究[D]. 镇江: 江苏大学, 2016: 20-40.
[12] 周文静, 查志华, 吴杰. 改进圆形Hough变换的田间红提葡萄果穗成熟度判别[J]. 农业工程学报, 2020, 36（9）: 205-213.
[13] 肖壮, 王巧华, 王彬, 等. 基于数字图像及随机最小二乘的红提串果粒尺寸检测分级方法[J]. 食品科学, 2018, 39（15）: 60-66.
[14] 施行, 王巧华, 顾伟, 等. 基于机器视觉的红提串无损检测及分级[J]. 食品科学, 2021, 42（18）: 232-239.
[15] MIN L, WANG Q, JIANG Z. Automatic recognition of grapes' size level based on machine vision[J]. Journal of Food Agriculture and Environment, 2012, 10（3）: 78-80.
[16] KABURLASOS V G. A Review of the state-of-art, limitations, and perspectives of machine vision for grape ripening estimation[J]. Engineering Proceedings, 2021, 9（1）: 1-2.
[17] 潘磊庆, 屠康, 苏子鹏, 等. 基于计算机视觉和神经网络检测鸡蛋裂纹的研究[J]. 农业工程学报, 2007（5）: 154-158.
[18] 陈远哲, 王巧华, 高升, 等. 皮蛋凝胶品质含水率和弹性的高光谱预测及其可视化[J]. 食品科学, 2022, 43（2）: 324-331.
[19] 刘超, 林寿英, 王彩霞, 等. 基于Gabor滤波器和SVM结合的中华蜂图像识别方法[J]. 农业工程学报, 2021, 11（8）: 49-52.
[20] 楚松峰, 赵凤霞, 方双, 等. 基于PCA-SVM的红枣缺陷识别方法[J]. 食品与机械, 2021, 37（1）: 156-160, 198.
[21] 李泽平, 郭俊先, 郭阳, 等. 基于支持向量机的无核白葡萄串分级系统设计与测试[J]. 食品与机械, 2021, 37（10）: 106-111, 246.