基于计算机视觉的苹果颜色分级系统的研究
|
摘要
苹果是深受人们喜爱的一种水果。我国是世界苹果第一大生产国，我国苹果的出口量和创汇额这几年有了显著的提高，但仍远远低于苹果先进生产国的水平。原因有很多，一个主要的原因就是忽视了采后处理。水果的采后商品化处理包括下面几个部分：挑选、清洗、打蜡、分级和包装，其中分级是最重要的一个环节。目前我国主要采用人工分级，但人工分级不仅费时、效率低下，而且分级质量与检验员自身的技术水平有很大的关系，难以保证出口苹果的品质。分级的效率低已经成为制约加工效率的一个瓶颈因素。所以迫切需要开发出自动分级系统。颜色和着色度是水果重要的外观品质之一，也是分级的一个重要标准。本文就从颜色方面入手，来研究苹果的分级系统。
整个处理系统包括：预处理、特征提取、分级这三个方面。
预处理是图像处理中一个重要的环节，只有采用的预处理方法合适，才能使后面的特征提取顺利进行。论文根据图像的具体问题和处理效果最终确定下面几种预处理方法：灰度的线性拉伸、平滑化去噪、最小误差法分割图像和轮廓提取，最终结果显示这些方法适合作为苹果分级系统的预处理过程。
特征提取是处理系统的核心部分，特征提取得好，后面的分级才会顺利。论文基于苹果是一个近似的球体这一事实(并在论文中验证了这一点)，利用一种空间变换的方法将苹果的真实面积求取出来，这种方法更加合理地反映了苹果上面红颜色的面积百分比。前人主要使用的是统计投影面上像素点数的方法，这种方法简单但并不是很准确；对两种方法比较可以看出，当红颜色集中在被拍摄苹果的中间部分，这两种方法求出来的面积比相差不大，但是若红颜色比较靠近边缘，那么它们之间的差异就比较大。根据对苹果的色度直方图进行分析，并参考色度的概念最终选定了色度阈值将苹果上面的鲜红、浓红颜色分割出来。
分级方法是系统的最后一个环节，论文选用了模糊识别法中的隶属原则法根据提取的特征来对苹果进行最后的分级，这种方法近似于人脑分级的模式，简单且易于操作；根据实际的情况选定了隶属函数，求出隶属度并确定苹果的最终等级。经过实验检验这种方法可行，苹果的分级准确率可达89.2％。
Apple is a sort of fruit that is liked by all the people. Our country has the highest total quantity of apple yield in the world, and the profits and the exportation quantity have being notable improved in recent years, but is still far from the advanced countries. There are many reasons towards this result; the most dominant one is that the post-process is despised. The post-process includes: selection, washing, waxing, grading and packaging, and the most important one is grading. In our country the grading is still mainly depends on manual grading, and it has many defects such as: low efficiency, slow speed. The grading result is mostly depends on the level of workers, so the apple quality is unable to be ensured. Manual grading has been the bottleneck factor that restricts the efficiency of the processes; so an automatic grading system is required imminently. The color and the red area are important appearance quantities of apple, and they are also one of the important standards of grading. In this paper
this grading system is studied through color.
The whole process system includes: preprocess, character pick-up, grading. Preprocess is a very important step in image manipulation. Only the proper preprocess method can ensure the success of character pick-up. After considering the actual status and the process effect, the following methods are determined at last: grey-degree linear transformation, smoothness, minimum-error image segmenting and the profile extraction. The final results show that these methods are proper for the preprocess.
Character pick-up is the main part of the process system. Only if it is carried out properly, the grading, could be done successfully. By using a method of three-dimensional counterchanges, the true area of an apple's surface can be calculated, based on the fact that an apple is an approximate sphere (this fact is approved in the paper). This method is more reasonable in getting the proportion of the red-area on an apple, than that by taking count of the number of pixels on the projection. After comparing the two methods we can see that the areas calculated with the two methods are not quite different while the red-area is concentrated in the center of the image, but if the red-area is close to the border of the apple in image, the result will be quite different. According to the analysis towards the hue-distribution curves of the apples, hue-threshold is chosen to divide the cardinal red and the thicken red.
The grading method is the last step in the system, and in this paper a rule of direct membership function is selected to deal with the final grading. This rule is similar to the thinking pattern of the human brain. Membership function is determined according to the
actual aspect, and the final grade is operated after the value of membership function is calculated. Experimental results show that this method has a good effect with a veracity of 89.2%.
整个处理系统包括：预处理、特征提取、分级这三个方面。
预处理是图像处理中一个重要的环节，只有采用的预处理方法合适，才能使后面的特征提取顺利进行。论文根据图像的具体问题和处理效果最终确定下面几种预处理方法：灰度的线性拉伸、平滑化去噪、最小误差法分割图像和轮廓提取，最终结果显示这些方法适合作为苹果分级系统的预处理过程。
特征提取是处理系统的核心部分，特征提取得好，后面的分级才会顺利。论文基于苹果是一个近似的球体这一事实(并在论文中验证了这一点)，利用一种空间变换的方法将苹果的真实面积求取出来，这种方法更加合理地反映了苹果上面红颜色的面积百分比。前人主要使用的是统计投影面上像素点数的方法，这种方法简单但并不是很准确；对两种方法比较可以看出，当红颜色集中在被拍摄苹果的中间部分，这两种方法求出来的面积比相差不大，但是若红颜色比较靠近边缘，那么它们之间的差异就比较大。根据对苹果的色度直方图进行分析，并参考色度的概念最终选定了色度阈值将苹果上面的鲜红、浓红颜色分割出来。
分级方法是系统的最后一个环节，论文选用了模糊识别法中的隶属原则法根据提取的特征来对苹果进行最后的分级，这种方法近似于人脑分级的模式，简单且易于操作；根据实际的情况选定了隶属函数，求出隶属度并确定苹果的最终等级。经过实验检验这种方法可行，苹果的分级准确率可达89.2％。
Apple is a sort of fruit that is liked by all the people. Our country has the highest total quantity of apple yield in the world, and the profits and the exportation quantity have being notable improved in recent years, but is still far from the advanced countries. There are many reasons towards this result; the most dominant one is that the post-process is despised. The post-process includes: selection, washing, waxing, grading and packaging, and the most important one is grading. In our country the grading is still mainly depends on manual grading, and it has many defects such as: low efficiency, slow speed. The grading result is mostly depends on the level of workers, so the apple quality is unable to be ensured. Manual grading has been the bottleneck factor that restricts the efficiency of the processes; so an automatic grading system is required imminently. The color and the red area are important appearance quantities of apple, and they are also one of the important standards of grading. In this paper
this grading system is studied through color.
The whole process system includes: preprocess, character pick-up, grading. Preprocess is a very important step in image manipulation. Only the proper preprocess method can ensure the success of character pick-up. After considering the actual status and the process effect, the following methods are determined at last: grey-degree linear transformation, smoothness, minimum-error image segmenting and the profile extraction. The final results show that these methods are proper for the preprocess.
Character pick-up is the main part of the process system. Only if it is carried out properly, the grading, could be done successfully. By using a method of three-dimensional counterchanges, the true area of an apple's surface can be calculated, based on the fact that an apple is an approximate sphere (this fact is approved in the paper). This method is more reasonable in getting the proportion of the red-area on an apple, than that by taking count of the number of pixels on the projection. After comparing the two methods we can see that the areas calculated with the two methods are not quite different while the red-area is concentrated in the center of the image, but if the red-area is close to the border of the apple in image, the result will be quite different. According to the analysis towards the hue-distribution curves of the apples, hue-threshold is chosen to divide the cardinal red and the thicken red.
The grading method is the last step in the system, and in this paper a rule of direct membership function is selected to deal with the final grading. This rule is similar to the thinking pattern of the human brain. Membership function is determined according to the
actual aspect, and the final grade is operated after the value of membership function is calculated. Experimental results show that this method has a good effect with a veracity of 89.2%.
引文
[1] 廖小军 胡小松．我国苹果生产、加工现状与发展对策．中国农业科技导报 2001，3(6)：13
[2] 李晓瑞，袁宝财．国内外苹果发展现状．宁夏农林科技，1997，5：43
[3] 刘凤之，孙希生等．我国苹果出口问题及主要对策．中国果树，2002，1：48～50
[4] 籍保平，吴文才．计算机视觉苹果分级系统．农业机械学报，2000，31(6)：118～120
[5] 袁亚祥．国产水果为何难出国门．柑桔与亚热带果树信息，2002，8：1～12
[6] 宁纪锋，龙满生等．农业领域中的计算机视觉研究．计算机与农业，2001，1：1～3
[7] 容观澳．计算机图象处理．清华大学出版社．2000
[8] 吴立德．计算机视觉．上海：复旦大学出版社．1993
[9] Taylor R W, Rehkugler G E, Throop J A. Apple bruise detection using a digital line scan camera system. In Agriculture Electronics-1983 and Beyond-Volume Ⅱ. St. Joseph, MI: ASAE, 1984
[10] Rehkugler G E, Throop J A. Apple sorting with machine vision. Transactions of the ASAE, 1985, 29 (5): 1388～1395
[11] 郭文川，王转卫，朱新华．机器视觉技术在果蔬的识别和分级中的应用．粮油加工与食品机械，2002，5：32～33
[12] Yang Q. An approach to apple surface feature detection by machine vision. Compute. Electron. Agric., 1994, 11:249～264
[13] Yang Q, Machant J A. Accurate blemish detection with active contour models. Compute. Electron. Agric., 1995, 14: 77～89
[14] 杨秀坤，陈晓光，马成林等．水果表面缺陷自动检测系统中的人工智能方法研究[J]．农业工程学报，1998，13(增刊)：242～247
[15] 刘禾，汪懋华．用计算机图像技术进行苹果坏损自动检测研究[J]．农业机械学报，1998，29(4)：81～86
[16] 张秦岭，邓继忠．应用计算机视觉技术对梨碰压伤的检测[J]．农业工程学报，1999，15(1)：205～209
[17] 李庆中，汪懋华．基于分形特征的水果缺陷快速识别方法[J]．中国图象图形学报，2000，5(2)：144～148
[18] 应义斌，饶秀勤，赵匀等．机器视觉技术在农产品品质自动识别中的应用研究进展[J]．农业工程学报，2000，16(3)：4～7
[19] Pavlidis T. Algorithms for graphics and image processing[M]. Computer Science Press. Rockville, Md, 1982
[20] Byler R K, Diehl KC, Stephens J W et al. Digital imaging of oyster means. ASAE Paper,
1987, 87～6502
[21] Marchant J A, Onyango C M, Street M J. High speed sorting of potatoes using computer vision. ASAE Paper, 1988, 88～3540
[22] Churchill D B, Bilsland D M, Cooper T M. Comparison of machine vision with human measurement of seed dimensions. Trans of the ASAE, 1992, 35(1) 61～64
[23] Ingrid Paulus, Eddie Schrevens. Shape characterization of new apple cultivars by Fourier expansion of digitized images. J. Agric. Engng. Res., 1999, 72:113～118
[24] 刘禾，汪懋华．水果果形判别人工神经网络专家系统的研究[J]．农业工程学报，1996．12(1)：172～176
[25] 应义斌，景寒松，马俊福等．黄花梨果形的机器视觉识别方法研究[J]．农业工程学报，1999，15(1)：192～196
[26] 吴雪．计算机视觉技术在农产品和食品检测中的应用．粮油加工与食品机械，2002，3：38～39
[27] 潘伟．计算机视觉在农产品自动检测与分级中的研究—番茄的自动检测与分级[D]．哈尔滨：东北农业大学，2000
[28] Miller B K, Delwiche M JA color vision system for peach grading[J]. Trans of the ASAE, 1989, 32(4): 1484～1490
[29] Shearer S A, Payne F A, Color and defect sorting of bell peppers using machine vision. Trans of the ASAE, 1990, 33(6): 2045～2050
[30] McConnell R K, Blau HH. Color classification of non-uniform baked and roasted foods[M]. Chicago, Illinois: Proceedings of the FPAC Ⅳ Conference, 1995, 40～46
[31] Heinemann D Z, Varghess Z A, Morrow C T, et al. Machine visions inspection of golden delicious apples[J]. Applied Engineering in Agriculture, 1995, 11(6): 910～906
[32] Tao Y. Method and apparatus for sorting objects including stable color transformation[J]. U.S. Patent No, 1996 (5): 533～628
[33] Ling PP, Cheng Z, Musacchio DJ. Quantification of somatic coffee embryo growth using machine vision[J] Transactions of the ASAE, 1996, 1911～1917
[34] 杨秀坤，陈晓光，马成林等．用遗传神经网络方法进行苹果颜色自动检测的研究．农业工程学报，1997，13(2)：173～176
[35] 何东健，杨青，薛绍平等．果实表面颜色计算机视觉分级技术研究[J]．农业工程学报，1998，14(3)：202～205
[36] 李庆中，汪懋华基于计算机视觉的苹果自动分级系统硬件开发[J]．农业机械学报，2000，31(2)：56～59
[37] 蔡健荣．利用计算机视觉定量描述茶叶色泽[J]．农业工程学报，2000，31(4)：67～70
[38] 章毓晋．图像工程——图象处理和分析．北京：清华大学出版社，1999
[39] 何斌，马天予，王运坚等．Visual C++数字图像处理．北京：人民邮电出版社，2001
[40] 方如明，蔡健荣，许俐等．计算机图像处理技术及其在农业工程中的应用．清华大学出版社．1999
[41] 陈延标，夏良正．数字图象处理．北京：人民邮电出版社，1990
[42] 中国标准出版社总编室．中国国家标准汇编．北京：中国标准出版社，1993．GB10651-89：471～484
[43] Kenneth R Castleman著，朱志刚，石定机等译．数字图像处理．北京：电子工业出版社，1998
[44] 阮秋琦．数字图像处理学．北京：电子工业出版社，2001
[45] 张智星，孙春在，[日]水谷英二．神经—模糊和软计算．西安：西安交大出版社，2000
[46] 姜长生，吴庆宪．智能控制及应用．南京航天航空大学，2000
[2] 李晓瑞，袁宝财．国内外苹果发展现状．宁夏农林科技，1997，5：43
[3] 刘凤之，孙希生等．我国苹果出口问题及主要对策．中国果树，2002，1：48～50
[4] 籍保平，吴文才．计算机视觉苹果分级系统．农业机械学报，2000，31(6)：118～120
[5] 袁亚祥．国产水果为何难出国门．柑桔与亚热带果树信息，2002，8：1～12
[6] 宁纪锋，龙满生等．农业领域中的计算机视觉研究．计算机与农业，2001，1：1～3
[7] 容观澳．计算机图象处理．清华大学出版社．2000
[8] 吴立德．计算机视觉．上海：复旦大学出版社．1993
[9] Taylor R W, Rehkugler G E, Throop J A. Apple bruise detection using a digital line scan camera system. In Agriculture Electronics-1983 and Beyond-Volume Ⅱ. St. Joseph, MI: ASAE, 1984
[10] Rehkugler G E, Throop J A. Apple sorting with machine vision. Transactions of the ASAE, 1985, 29 (5): 1388～1395
[11] 郭文川，王转卫，朱新华．机器视觉技术在果蔬的识别和分级中的应用．粮油加工与食品机械，2002，5：32～33
[12] Yang Q. An approach to apple surface feature detection by machine vision. Compute. Electron. Agric., 1994, 11:249～264
[13] Yang Q, Machant J A. Accurate blemish detection with active contour models. Compute. Electron. Agric., 1995, 14: 77～89
[14] 杨秀坤，陈晓光，马成林等．水果表面缺陷自动检测系统中的人工智能方法研究[J]．农业工程学报，1998，13(增刊)：242～247
[15] 刘禾，汪懋华．用计算机图像技术进行苹果坏损自动检测研究[J]．农业机械学报，1998，29(4)：81～86
[16] 张秦岭，邓继忠．应用计算机视觉技术对梨碰压伤的检测[J]．农业工程学报，1999，15(1)：205～209
[17] 李庆中，汪懋华．基于分形特征的水果缺陷快速识别方法[J]．中国图象图形学报，2000，5(2)：144～148
[18] 应义斌，饶秀勤，赵匀等．机器视觉技术在农产品品质自动识别中的应用研究进展[J]．农业工程学报，2000，16(3)：4～7
[19] Pavlidis T. Algorithms for graphics and image processing[M]. Computer Science Press. Rockville, Md, 1982
[20] Byler R K, Diehl KC, Stephens J W et al. Digital imaging of oyster means. ASAE Paper,
1987, 87～6502
[21] Marchant J A, Onyango C M, Street M J. High speed sorting of potatoes using computer vision. ASAE Paper, 1988, 88～3540
[22] Churchill D B, Bilsland D M, Cooper T M. Comparison of machine vision with human measurement of seed dimensions. Trans of the ASAE, 1992, 35(1) 61～64
[23] Ingrid Paulus, Eddie Schrevens. Shape characterization of new apple cultivars by Fourier expansion of digitized images. J. Agric. Engng. Res., 1999, 72:113～118
[24] 刘禾，汪懋华．水果果形判别人工神经网络专家系统的研究[J]．农业工程学报，1996．12(1)：172～176
[25] 应义斌，景寒松，马俊福等．黄花梨果形的机器视觉识别方法研究[J]．农业工程学报，1999，15(1)：192～196
[26] 吴雪．计算机视觉技术在农产品和食品检测中的应用．粮油加工与食品机械，2002，3：38～39
[27] 潘伟．计算机视觉在农产品自动检测与分级中的研究—番茄的自动检测与分级[D]．哈尔滨：东北农业大学，2000
[28] Miller B K, Delwiche M JA color vision system for peach grading[J]. Trans of the ASAE, 1989, 32(4): 1484～1490
[29] Shearer S A, Payne F A, Color and defect sorting of bell peppers using machine vision. Trans of the ASAE, 1990, 33(6): 2045～2050
[30] McConnell R K, Blau HH. Color classification of non-uniform baked and roasted foods[M]. Chicago, Illinois: Proceedings of the FPAC Ⅳ Conference, 1995, 40～46
[31] Heinemann D Z, Varghess Z A, Morrow C T, et al. Machine visions inspection of golden delicious apples[J]. Applied Engineering in Agriculture, 1995, 11(6): 910～906
[32] Tao Y. Method and apparatus for sorting objects including stable color transformation[J]. U.S. Patent No, 1996 (5): 533～628
[33] Ling PP, Cheng Z, Musacchio DJ. Quantification of somatic coffee embryo growth using machine vision[J] Transactions of the ASAE, 1996, 1911～1917
[34] 杨秀坤，陈晓光，马成林等．用遗传神经网络方法进行苹果颜色自动检测的研究．农业工程学报，1997，13(2)：173～176
[35] 何东健，杨青，薛绍平等．果实表面颜色计算机视觉分级技术研究[J]．农业工程学报，1998，14(3)：202～205
[36] 李庆中，汪懋华基于计算机视觉的苹果自动分级系统硬件开发[J]．农业机械学报，2000，31(2)：56～59
[37] 蔡健荣．利用计算机视觉定量描述茶叶色泽[J]．农业工程学报，2000，31(4)：67～70
[38] 章毓晋．图像工程——图象处理和分析．北京：清华大学出版社，1999
[39] 何斌，马天予，王运坚等．Visual C++数字图像处理．北京：人民邮电出版社，2001
[40] 方如明，蔡健荣，许俐等．计算机图像处理技术及其在农业工程中的应用．清华大学出版社．1999
[41] 陈延标，夏良正．数字图象处理．北京：人民邮电出版社，1990
[42] 中国标准出版社总编室．中国国家标准汇编．北京：中国标准出版社，1993．GB10651-89：471～484
[43] Kenneth R Castleman著，朱志刚，石定机等译．数字图像处理．北京：电子工业出版社，1998
[44] 阮秋琦．数字图像处理学．北京：电子工业出版社，2001
[45] 张智星，孙春在，[日]水谷英二．神经—模糊和软计算．西安：西安交大出版社，2000
[46] 姜长生，吴庆宪．智能控制及应用．南京航天航空大学，2000