The CAPA Apple Quality Grading Multi-Spectral Image Database

The CAPA Apple Quality Grading Multi-Spectral Image Database consists of multispectral (450nm, 500nm, 750nm, and 800nm) images of health and defected apples of bi-color, manual segmentations of defected regions, and expert evaluations of the apples into 4 quality categories. The defect types consist of bruise, rot, flesh damage, frost damage, russet, etc. The database can be used for academic or research purposes with the aim of computer vision based apple quality inspection. The CAPA Apple Quality Grading Multi-Spectral Image Database is a propriety of ULG (Gembloux Agro-Bio Tech) - Belgium, and cannot be used without the consent of the ULG (Gembloux Agro-Bio Tech), Belgium. For consent, contact Devrim Unay, İzmir University of Economics, Turkey: [e-mail] OR Marie-France Destain, Gembloux Agro-Bio Tech, Belgium: [e-mail] In disseminating results using this database, 1. the author should indicate in the manuscript that it was acquired by ULG (Gembloux Agro-Bio Tech), Belgium. 2. cite the following article Kleynen, O., Leemans, V., & Destain, M.-F. (2005). Development of a multi-spectral vision system for the detection of defects on apples. Journal of Food Engineering, 69(1), 41-49. Relevant publications: Kleynen et al., 2003 O. Kleynen, V. Leemans and M.F. Destain, Selection of the most efficient wavelength bands for ‘Jonagold’ apple sorting. Postharv. Biol. Technol., 30 (2003), pp. 221–232. Leemans and Destain, 2004 V. Leemans and M.F. Destain, A real-time grading method of apples based on features extracted from defects. J. Food Eng., 61 (2004), pp. 83–89. Leemans et al., 2002 V. Leemans, H. Magein and M.F. Destain, On-line fruit grading according to their external quality using machine vision. Biosyst. Eng., 83 (2002), pp. 397–404. Unay and Gosselin, 2006 D. Unay and B. Gosselin, Automatic defect detection of ‘Jonagold’ apples on multi-spectral images: A comparative study. Postharv. Biol. Technol., 42 (2006), pp. 271–279. Unay and Gosselin, 2007 D. Unay and B. Gosselin, Stem and calyx recognition on ‘Jonagold’ apples by pattern recognition. J. Food Eng., 78 (2007), pp. 597–605. Unay et al., 2011 Unay, D., Gosselin, B., Kleynen, O, Leemans, V., Destain, M.-F., Debeir, O, “Automatic Grading of Bi-Colored Apples by Multispectral Machine Vision”, Computers and Electronics in Agriculture, 75(1), 204-212, 2011.

CAPA苹果品质分级多光谱图像数据库（CAPA Apple Quality Grading Multi-Spectral Image Database）收录了双色健康苹果与缺陷苹果的多光谱（450nm、500nm、750nm、800nm）图像、缺陷区域的手动分割标注，以及经专家评估划分的4个品质等级。该数据集涵盖的苹果缺陷类型包括碰伤、腐烂、果肉损伤、冻害、锈斑等，可用于基于计算机视觉的苹果品质检测相关学术与研究工作。

本CAPA苹果品质分级多光谱图像数据库为比利时列日大学吉姆勒农业与生物工程学院（ULG, Gembloux Agro-Bio Tech）所有，未经其书面许可，不得擅自使用该数据集。如需获取使用许可，请联系土耳其经济大学的Devrim Unay（电子邮箱：[e-mail]），或比利时列日大学吉姆勒农业与生物工程学院的Marie-France Destain（电子邮箱：[e-mail]）。

在发表使用本数据集的研究成果时，需满足以下两项要求：
1. 稿件中需注明该数据集由比利时列日大学吉姆勒农业与生物工程学院（ULG, Gembloux Agro-Bio Tech）提供；
2. 需引用以下核心文献：Kleynen, O., Leemans, V., & Destain, M.-F. (2005). 多光谱视觉系统用于苹果缺陷检测的研发. 《食品工程学报》, 69(1), 41-49.

相关参考文献列表如下：
1. Kleynen等，2003：O. Kleynen、V. Leemans与M.F. Destain, 《“乔纳金”苹果分选最优波长波段的选择》, 《采后生物学与技术》, 30(2003), 221–232.
2. Leemans与Destain，2004：V. Leemans与M.F. Destain, 《基于缺陷特征提取的苹果实时分级方法》, 《食品工程学报》, 61(2004), 83–89.
3. Leemans等，2002：V. Leemans、H. Magein与M.F. Destain, 《基于机器视觉的果实外观品质在线分级技术》, 《生物系统工程》, 83(2002), 397–404.
4. Unay与Gosselin，2006：D. Unay与B. Gosselin, 《多光谱图像中“乔纳金”苹果的自动缺陷检测：对比研究》, 《采后生物学与技术》, 42(2006), 271–279.
5. Unay与Gosselin，2007：D. Unay与B. Gosselin, 《基于模式识别的“乔纳金”苹果果柄与花萼识别》, 《食品工程学报》, 78(2007), 597–605.
6. Unay等，2011：Unay, D., Gosselin, B., Kleynen, O., Leemans, V., Destain, M.-F., Debeir, O., 《基于多光谱机器视觉的双色苹果自动分级》, 《农业计算机与电子学》, 75(1), 204-212, 2011.

搜集汇总

背景与挑战

背景概述

该数据集是一个多光谱苹果质量分级图像数据库，包含健康和缺陷苹果的多光谱图像、缺陷区域的手动分割和专家质量评估，适用于计算机视觉在农业质量检测中的应用研究。