基于计算机视觉和声学技术融合检测鸡蛋品质的研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
鸡蛋具有很高的营养价值,深受消费者喜爱。蛋内外品质的好坏直接影响蛋的质量和安全。在销售流通及加工方面,如能做到按质论价,则既保护了消费者权益,又有利于生产经营者采取科学的管理,保证蛋的品质。将基于计算机技术的高新检测技术用于禽蛋品质的自动检测和分级,既可以解放劳动力,排除人的主观因素干扰,又能快速而准确地进行禽蛋品质的综合而全面地评价。因此,研究和完善高水平的禽蛋品质检测系统对于提高我国禽蛋在国际市场行业的竞争力有着现实意义。本文是国家自然科学基金项目“基于计算机视觉和动力学特性无损检测禽蛋品质研究”中的一部分,主要研究了利用计算机视觉和声学技术无损检测鸡蛋的裂纹(主要是微裂纹鸡蛋)、污斑和新鲜度的品质情况,提高检测精度。本文主要的研究内容和结果如下:
     1.声学技术检测鸡蛋裂纹的研究
     分析了外部条件(敲击位置、信号采集位置、敲击力、贮藏时间)和鸡蛋自身物理性质(蛋重、蛋壳厚度、蛋形指数、蛋壳强度、裂纹)对鸡蛋特征响应频率的影响,并建立了利用声学敲击检测鸡蛋裂纹的装置和方法。研究发现采集信号位置、贮藏时间、敲击力大小和蛋形指数对鸡蛋的特征频率影响很小,而敲击位置和裂纹对鸡蛋的特征频率影响很大;蛋壳厚度、蛋壳强度和蛋重对特征频率影响也较大,鸡蛋的特征频率随着蛋壳强度和壳厚的增加会变大,但随着蛋重的增加反而变小,而且蛋重与鸡蛋特征频率的相关系数达到0.699。同时发现,对鸡蛋特征频率的影响并不是单个因素,而是多个因素共同起作用。利用建立的声学检测装置,通过敲击赤道不同部位四次,分析四个特征响应频率的变异系数(CV),可将CV作为分级依据,设定参数(CV)的阈值为1时,完好鸡蛋检测准确率达83%,壳裂鸡蛋的检测准确率为91%,整批鸡蛋的检测准确率达到87%。
     2.基于计算机视觉和神经网络检测鸡蛋裂纹的研究
     为了进一步提高鸡蛋裂纹检测的准确性和效率,建立了利用计算机视觉技术检测鸡蛋表面裂纹的装置,综合运用计算机视觉技术和BP神经网络技术,实现鸡蛋表面裂纹的无损检测和分级。首先,通过计算机视觉系统获取鸡蛋表面的图像,对图像分析处理,提取了裂纹区域和噪声区域的5个几何特征参数。其次,将5个参数作为输入量,建立了基于MATLAB的结构为5-10-2的三层BP神经网络模型,对裂纹进行识别和鸡蛋的自动分级。试验结果表明模型对裂纹鸡蛋的识别准确率达到了92.9%,对整批鸡蛋的分级准确率达到了96.8%。
     3.计算机视觉和声学技术融合检测鸡蛋裂纹的研究
     利用计算机视觉系统获取鸡蛋表面图像,并进行分析处理,提取了5个特征参数(A、R、L、S、LS),作为BP神经网络的输入量,创建了基于MATLAB的结构为5-10-2的3层BP神经网络模型识别鸡蛋表面的裂纹,发现利用计算机视觉和BP神经网络判别不同程度破损鸡蛋的准确率只有68%,对完好鸡蛋的判别准确率为98%。对结果分析发现,虽然构建的BP神经网络对图像处理后分割出的裂纹区域识别准确率很高,但计算机视觉方法对裂纹较小的鸡蛋,主要为微裂纹和不可见裂纹鸡蛋,图像处理难以分割出裂纹区域,该类鸡蛋判别准确率较低。
     采集和分析鸡蛋被敲击后的声音信号,提取了特征频率F1、F2、F3、F4、偏斜度平均值CS和崤度平均值CE共6个特征参数,并作为神经网络的输入量,创建了基于MATLAB的结构为6-15-2的3层BP神经网络模型判别鸡蛋裂纹,对蛋壳受各种程度破坏后的鸡蛋判别准确率可达90%以上,对蛋壳完整的鸡蛋判别准确率超过95%,对一批鸡蛋总体的判断准确率可达94%。但也发现,当鸡蛋蛋壳受破坏比较严重,裂纹比较大时,敲击鸡蛋蛋壳的不同部位,采集的各次信号差异不大,利用声学技术结合BP神经网络的方法易产生误判。
     采用融合技术,结合计算机视觉、声学技术和BP神经网络判断各种破损程度鸡蛋,能够发挥计算机视觉技术和声学检测技术的优点,对裂纹蛋检出可达到98%,能够充分的保证鸡蛋的质量和安全。
     4.基于计算机视觉检测鸡蛋污斑的研究
     传统人工检测鸡蛋表面污斑方法由于效率较低,且易造成视觉疲劳等缺点,已不能满足现代化工业生产需要。本文建立了利用计算机视觉检测鸡蛋表面污斑的装置,通过计算机视觉采集鸡蛋表面的图像,然后对图像进行处理分析,提取特征参数,建立污斑识别算法,检测鸡蛋表面的污斑。通过验证,该识别算法分级污斑鸡蛋和干净鸡蛋的准确率达到92.7%,受试鸡蛋总体分级准确率达到90%以上,实现了对鸡蛋表面污斑的无损检测。
     5.基于计算机视觉和神经网络检测鸡蛋新鲜度的研究
     建立了利用计算机视觉检测获取鸡蛋内容物透射图像信息的装置,通过图像处理,获取了蛋壳表面颜色信息和表示鸡蛋新鲜的参数哈夫单位值(HU),得到了利用计算机视觉预测鸡蛋新鲜度的有关的H、I、S、a、b、a~*、b~*、a-a~*、b-b~*七个参数,然后通过分析哈夫单位HU与七个参数之间的相关性,并建立多元线性回归方程,确立了与鸡蛋新鲜度密切相关的三个参数H、I、b。
     以三个参数H、I、b作为输入变量,创建了基于MATLAB的结构为3-15-4的3层BP神经网络模型对鸡蛋的新鲜度进行分级,模型具有较好的泛化功能和鲁棒性,对各个等级鸡蛋的新鲜度分级准确率达90%,对整体鸡蛋新鲜度分级的准确率在92%以上。
     6.融合检测鸡蛋品质系统的软硬件组成
     本章介绍了实现利用计算机视觉、声学技术和神经网络融合技术无损检测鸡蛋品质(污斑、裂纹、新鲜度)的硬件的组成,以及软件的界面及其内部的各个功能模块。
Chicken-egg is very popular with consumers for its high nutrition. Egg quality influences egg's edible quality and safety. In sales and processing, if it can be graded and priced depends on the quality, it may not only protect consumers' right but also help the managers and operators to adopt scientific management. Using computerized technologies in the processing and grading eggs system could release labor force and exclude subjective disturbance factors by human being, and give quick and precise results for egg quality assessment. Therefore, research and optimization on the egg quality detection system is an attractive and promising subject for improving marketing competition. This research is a part of the project entitled "The study on computer vision and dynamics for nondestructively detecting egg quality" (30371050) under National Natural Science Foundation of China. The central research is to detect the egg quality including crack (mainly about tiny cracked egg), dirty, freshness and improving detecting precision. The contents and results are as follows:
     1. Chicken Egg Crack Detection Based on Acoustic Resonance Analysis
     An experimental system was set up to measure acoustic resonance frequency of an egg excited with a light mechanical impact on different locations. The effects of physical properties (egg mass, egg shape index, shell thickness, shell stiffness and crack) and other factors (excitation point, detection point, impact intensity, and storage time) on the dynamic resonance frequency were analyzed. The results showed that detecting point, egg shape index, storage time and impact intensity have little effect on the dominant frequency. The dynamic response frequency has mighty difference with different impact points and if the intact egg was cracked. Egg mass, shell stiffness, shell thickness greatly affected the resonant frequency of an egg. The resonant frequency increased with increase of shell stiffness or shell thickness and decrease of the egg mass. The correlation coefficient between the dominant frequency and the egg mass was 0.699. The dynamic response frequency usually not affected by one factor, by the mechanism of the synthetic effects of the several factors.In order to find out eggshell crack detection nondestructively for on-line application, frequency responses of an egg excited with a light mechanical impact on different locations on the eggshell were studied. Through analyzing the response frequency by computer, it was found that the characteristic response frequency of intact eggs changed in a small range but the characteristic response frequency of cracked eggs were heterogeneous and varied in a larger frequency range. By analyzing coefficient of variation (CV) of the four characteristic response frequencies at the chicken egg equator zone, a sorting algorithm to detect crack eggs was developed. Based on this method and set CV to 1, the detecting rate was 91 % for cracked chicken eggs and 87 % for the total chicken eggs.
     2. Egg crack detection using computer vision and BP neural network
     To improve the accuracy of detection and classification of egg with cracks sequentially, an experimental system was set up based on computer vision for egg crack detection. Computer vision and BP neural network technology were applied to automatically identify and classify the eggs with cracks. Firstly, the picture images of egg with or without cracks were captured through computer vision system, then the images were processed, and 5 geometrical characteristic parameters of crack areas and noise areas were acquired. Secondly, with the 5 parameters as input, the best BP neural network (5 input nodes, 10 hidden nodes, 2 output nodes) by using MATLAB was employed to detect egg crack and classify eggs. The experimented results showed that the rate of detecting precision of cracked egg reached 92.9 % and the classification accuracy of total eggs can reach 96.8 % by the 5-10-2 BP neural network model.
     3. Egg crack detection based on computer vision and acoustic technology
     Firstly, the picture images of egg shell were captured through computer visionsystem, then the images were processed, and 5 geometrical characteristic parameters of crack areas and noise areas were acquired. With the 5 parameters as input, the best BP neural network (5 input nodes, 10 hidden nodes, 2 output nodes) was employed to detect egg crack and classify eggs by using MATLAB. The experimented results showed that the rate of testing precision of cracked egg (mainly for tiny crack) reached only 68 % and the classification accuracy of total eggs can reach 98 % by the 5-10-2 BP neural network model. To analyze the data and results, the method which computer vision and BP neural network find egg with tiny crack and invisible crack from normal egg was difficult, and then show low accuracy.
     Secondly, the acoustic signals were captured and analyzed, then 6 parameters (F1 characteristic response frequency; F2 characteristic response frequency; F3 characteristic response frequency; F4 characteristic response frequency; CS mean value of coefficient of skewness; CE mean value of coefficient of excess) were pick up. With the 6 parameters as input, the best BP neural network (6 input nodes, 15 hidden nodes, 2 output nodes) by using MATLAB was employed to detect egg crack and classify eggs. The results showed that accuracy of using acoustic technology and BP neural network to identify egg shell crack (mainly for tiny crack) can exceed 90 % and reach 94 % for the total tested egg. Moreover the method to detect egg with large crack is relatively difficult.
     Thirdly, the egg with different degree crack or non-crack was detected by using acoustic technology and BP neural network, and then detected by using computer vision technology, and finanlly integrate the two results, the egg quality was showed. The method with fusion computer vision, acoustic technology and BP neural network was good for cracked egg quality detection, and the accuracy for the cracked egg can reach 98%.
     4. Research on dirt detection on brown eggs based on computer vision
     The traditional artificial method of examining dirty spot of egg shell has unavoidable disadvantages, for example, the workers' subjectivity, vision tiredness easily leading to low accuracy, so it can not satisfy the demand of the modern industry production. In this paper, an instrument of detecting egg dirty spot by using computer vision was built up, and the image of egg shell surface was captured, then the images were processed and analyzed. The algorithm and the way of classification were set up based on characteristic parameters obtained from the images. The results showed that the rate of detecting dirty egg could reach 92.7 %. The accuracy of classifying total eggs could exceed 90 %, and could possibly realize the automatic detection of egg dirt.
     5. Egg freshness detection based on computer vision and BP neural network
     An experimental system was build up based on computer vision. With the system,egg's contents transmission images were acquired. After pre-processing H, S, I, a, b values of egg color were extracted. The egg shell color information (a~*, b~*) was measured. The weight of egg was measured using electronic balance and the height of egg's albumen was measured using height vernier caliper. Egg freshness was calculated according to its weight and albumen height. The linear regression model for egg's Hough unit and egg information (H, I, S, a, b, a~*, b~*, a-a~*, b-b~*) was established by SAS. Afterwards the 3 parameters (H, I, b) which is greatly correlated with egg freshness (HU, Egg's Hough unit) was reserved.
     With 3 parameters (H, I, b) of input, the best BP neural network model (3 input nodes, 15 hidden nodes, 4 output nodes) was established by using MATLAB. On the BP neural network model of detecting the egg fresh degree, the automatic detection system was designed in this article, which can immediately show the results according to the egg's color data after the network initialization. The results showed that the grading accuracy by using computer vision and BP neural network for egg freshness is exceed 90 %.
     6. Hardware and software of detection system for egg quality
     The hardware of nondestructively detecting egg quality (shell crack, dirty, freshness) system was set up based on multi-technologies including computer vision, acoustic technology and BP neural network. The primary function of software for this device was also showed.
引文
[1] 相俊红,庞俊杰.国内外禽蛋清选分级技术及设备的比较[J].农产品加工,2004,(1):8-10
    [2] 宁欣.禽蛋的分级、检测与包装[J].中国家禽,2004,26(12):56-60
    [3] Tadhg Brosnan, Da-Wen Sun .Improving quality inspection of food products by computer vision-a review [J]. Journal of Food Engineering, 2004, 61(1):3-16
    [3] Tao Y, Heinemann P H. Machine vision for color inspection of potatoes and apples[J].Trans of the ASAE, 1995, 38(5):1555-1561
    [4] Ni B. Design of an Automatic Corn Kernel Inspection System for Machine Vision [J]. Trans of the ASAE, 1997, 40 (2):491-497
    [5] Wen Z, Tao Y. Building a rule-based machine-vision system for defect inspection on apple sorting and packing lines[J]. Expert Systerms with Application, 1999 (16):307-313
    [7] Elster R T, Goodrum J W. Detection in eggs by machine vision [J]. Transactions of the ASAE, 1991, 30(1): 307-312.
    [8] Goodrum J W, Elster R T .Machine vision for crack detection on rotation eggs [J]. Transactions of the ASAE, 1992, 35 (4):1323-1328.
    [9] Jenshinn L, Hsieh M, Yang C. An Automatic System for Eggshell Quality Monitoring [J]. 2001, ASAE Annal Meeting, 2001, Paper No. 016032
    [10] Cho H K, Kwon Y. Crack Detection in Eggs by Machine Vision [J]. In 6th Int.Conf.On Computers in Agriculture. St. Joseph.Mich.ASAE,1996: 777-784.
    [11] 陈佳娟,陈小光,纪寿文.采用计算机视觉进行孵化鸡蛋成活可能性的自动检测[J].计算机应用与软件,2001,18(6):5-10
    [12] 王巧华,余佑生,宗望远,等.鸡蛋大小等级模型研究[J].华中农业大学学报,2001,20(6):579-583
    [13] 文友先,王巧华,宗望远,等.鸭蛋破损检测的试验研究[J].华中农业大学学报,2002,21 (3):66-70
    [14] 刘剑英,王巧华,熊利荣,等.鸭蛋新鲜度模型的试验研究[J].华中农业大学学报,2002,21(6):71-75
    [15] 王坚,蒋有条.农产品的声学特性及其在农产品品质无损检测中应用[J].农业工程学报,1997,13(3).208-212
    [16] Clark R L. An investigation of the acoustical properties of watermelon as related to maturity[J]. Transactions of the ASAE , 1975:75-6004
    [17] Ymamoto H M. Non-destructive acoustic impulse response method for measuring internal quality of apples and watermelons [J]. J. Jap Soc Hort.Sci,1981,50(2): 247-261
    [18] Chen H, Baerdemaeker J D. Effect of apple shape on acoustic measurement of firmness [J]. Journal of Agricultural Engineering Research, 1993, 56(1): 253-266.
    [19] De Belie N, Tu K, Jancsok P. Preliminary study on the influence of turgot pressure on body Reflectance of red laser light as a ripeness indicator for apples[J]. Post harvest Biology and Technology, 1999, 6: 279-284.
    [20] Duprat F. The acoustic impulse response method for measuring the overall firmness of fruit [J]. Journal of Agricultural Engineering Research. 1991, 66(4): 251-259.
    [21] Sugiyama J, Katsurai T, Hong J, et al. Portable melon firmness tester using acoustic impulse transmission[J].Proceedings from the sensors for nondestructive testing intemational conference, Orlando, Florida, February 18-21, 3-12
    [22] Salveit M E, Upadhyaya S K, Happ J F. Maturity determination of tomatoes using acoustic methods[J]. Transactions of the ASAE, 1985:85-3536
    [23] 王书茂.西瓜成熟度无损检验的冲击振动法[J].农业工程学报,1999,15(3):41-45
    [24] 何东健等.西瓜打击音波特性的研究[J].西北农业大学学报,1994,22(3):105-107
    [25] 韩萍.仓储物害虫声音模式识别的研究[D].郑州:郑州大学,2001
    [25] Finney E E. Dynamic elastic properties of some fruits during growth and development [J]. Journal of Agricultural Engineering Research, 1967,14(4):249-255.
    [26] Robinson B E. An evaluation of acoustical decay time as a measure of watermelon maturity [D]. M S thesis, University of Georgia, Athens, 1976.
    [27] Yamamoto H M. Non-destructive acoustic impulse response method for measuring internal quality of apples and watermelons. JJap Soc Hort. Sci, 1981, 50(2):247-261.
    [29] 潘秀娟,屠康.用冲击共振法无损检测梨采后质地的变化[J].南京农业大学学报,2004,27 (2):94-98
    [30] 屠康,马龙,潘秀娟.敲击振动无损检测3种梨果实品质参数的研究[J].安徽农业大学学报,2005,32(1):50-53
    [31] Coucke P. Assessment of some physical quality parameters of eggs based on vibration analysis[D]. PhD Thesis. Katholieke Universiteit Leuven. Beigium,1998.
    [32] 闰长新.基于神经网络的蛋品破损检测[D].福州:福州大学,2001
    [33] Sinha. D N, Johnston R G, Grace W K, et al. Asoustic Resonance in Chicken Eggs [J], Biotechnology Prog, 1992, 8(3):240-243
    [34] Cho.H.K, Y. Kwon. Crack Detection in Eggs by Machine Vision [J], In 6th Int. Conf. On Computers in Agriculture, St. Joseph. Mich.ASAE, 1996:777-784
    [35] B.De Ketelaere, P. Coucke, J. De Baerdemaeker. Eggshell crack based on Acoustic Resonance Frequency Analysis [J]. Journal of Agricultural Engineering Research,2000,76:157-163
    [36] 公茂法,汤元信,李其才.禽蛋质量自动检测方法与实现[J].自动化与仪器仪表,1995:35-38
    [37] Wang J, Jiang R S, Y Yu. Relationship between dynamic resonance frequency and egg physical properties[J].Food Research International,2004,37(1):45-50
    [38] 王树才,任奕林,陈红,等.利用敲击声音信号进行禽蛋破损检测和模糊识别[J].农业工程学报,2004,20(4):130-133
    [39] 潘磊庆,屠康,赵立,等.敲击振动检测鸡蛋裂纹的初步研究[J].农业工程学报,2005,21 (4):11~15
    [39] 李其才.禽蛋质量自动检测与分选系统[J].新浪潮,1992(5):17-20
    [40] 刘信芳,吴守一.鸡蛋力学特性实验分析[J].江苏工学院学报,1992,13(1):28-30
    [42] 姬长英,鲁植雄.鸡蛋流变模型研究[J].南京农业大学学报,1994,18(4):114-117
    [43] 刘熙,修建国.应用电导率仪检测鸡蛋新鲜度[J].食品科学,1991(10):45-47
    [44] 沈林生,陈宁.用生物电鉴别受精蛋的检测装置的研究[J].农业工程学报,1996,12(3):163-166
    [45] 吴守一,韩宁.鸡蛋新鲜度的光学无损检测和分级[J].农业工程学报,1989,5(4):64-67.
    [46] 方如明,向忠平,李国文.鸡蛋内部品质的光特性无损检测[J].农业工程学报,1993,9(3):102-107.
    [47] 苏臣,吴安翔.鸡蛋六种品质的数字图像特征[J].中国家禽,1995(5):18-20
    [48] 陈斌.鸡蛋品质光电检测的研究[J].江苏理工大学报,1996,17(6):1-5.
    [49] 刘燕德,乔振先.鸡蛋光特性及其与新鲜度的相关性研究[J].江西农业大学学报,2002(1):45-47.
    [50] 丛爽.神经网络、模糊控制系统及其在运动控制中的应用[J].北京:中国科学技术大学出版社,2001
    [51] 周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2004
    [52] 飞思科技产品研发中心.神经网络理论与MATLAB7实现[M].北京:电子工业出版社,2005
    [52] 宋韬,曾德超.基于人工神经网络的玉米籽粒形态识别方法的研究[J].农业工程学报,1996,121(1):177-181
    [53] 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[J].农业工程学报,1997,13(2):173-176
    [54] 殷勇,吴守一.人工嗅觉系统评定卷烟的内在品质[J].农业机械学报,1999,30(6):88-92
    [56] 何东健,杨青,薛少平,等.用人工神经网络进行果实颜色分级技术研究[J].西北农业大学学报,1998,26(6):109-112
    [57] 高大启,吴守一.并联神经网络在烤烟内在品质评定中的应用[J].农业机械学报,1999,30(1):58-62
    [57] 王红永,曹其新,刘文秀,等.基于神经网络的黄瓜等级判别[J].农业机械学报,1999,30(6):83-88
    [58] 殷勇,吴守一.人工嗅觉系统评定卷烟的内在品质[J].农业机械学报,1999,30(6):88-92
    [59] 章文军,许禄.自组织特特映射神经网络——用于茶叶分类[J].计算机与应用化,2000,17(1):85-87
    [61] 赵静,何东健.果实形状的计算机识别方法研究[J].农业工程学报,2001,17(2):165-167
    [62] 龙满生,何东健,宁纪.基于遗传神经网络的苹果综合分级系统[J].西北农林科技大学学报,2001,29(6):108-111
    [63] 蒋德云,张弓.谷物识别中对神经网络的优化[J].农业工程学报,2002,18(5):231-234
    [64] 李少昆,索兴梅,白中英,等.基于BP神经网络的小麦群体图像特征识别[J].中国农业科学,2002,35(6):616-620
    [65] 林文浩.稻米品质综合评价的人工神经网络方法[J].福建农林大学学报,2002,31(2):150-154
    [66] 周维忠,冯心海,孙国基.种蛋外形的计算机视觉识别研究[J].农业工程学报,2000,16(6):126-130
    [67] 郁志宏,王春光,张晓芳,等.改进的粒子群神经网络检测种蛋成活性[J].计算机工程与设计,2007,28(2):427-429
    [68] 黄耀志.基于神经网络分析的鲜蛋破损检测[J].振动、测试与诊断,2003,23(3):205-232
    [69] 王巧华,任奕林,文友先.基于BP神经网络的鸡蛋新鲜度无损检测方法[J].农业机械学报,2006,37(1):104-106
    [70] 王巧华,文友先.基于BP神经网络的鸡蛋大小分级方法研究[J]_湖北农业科学,2005(1):97-99
    [71] 邹小波.计算机视觉、电子鼻、近红外光谱三技术融合的苹果品质检测研究[D].江苏:江苏大学,2005.
    [72] Steinmetz A. Methodology for sensor fusion design: application to fruit quality assessment [J]. Journal of Agricultural Engineering Research, 1999(74):21-31
    [73] Iego Andres luzupiaga. Application of computer vision and electronic nose technologies for quality assessment of colour and odor of shrimp and simon [D]. 1998, 8 doctor dissertation, University of Florida.
    [74] Necla Demir. Objective quality assessment of modified atmosphere stored zucchini slices using electronic nose [J]. Machine Vision and Instron 2008,8
    [75] 马美湖.我国蛋与蛋制品加工重大关键技术筛选研究报告(一)[J].中国家禽,2004,26(23):1-5
    [1] Coucke P, Dewil E, Decuypere E. Measuring the mechanical stiffness of an eggshell using resonant Frequency analysis [J]. British Poultry Science,40, 1998,227-232.
    [2] Ketelaere B De, Coucke P, Baerdemaeker J De. Eggshell crack detection based on acoustic Resonance frequency analysis [J]. Journal of Agricultural Engineering Research. 2000, 76,157-163.
    [3] Cho H K, Choi W K, Paek J H. Detection of surface cracks in shell eggs by acoustic impulse Method [J]. Transactions of the ASAE, 1998, 43(6):1921-1926.
    [4] Cho H K, Kwon Y. Crack detection in eggs by machine vision[J]. In 6th Int.Conf.on computer in agriculture, 1996, 777-784.
    [5] Elaster R T. Goodrum J W. Detection of cracks in eggs using machine vision [J]. Transactions of ASAE, 1991, 307-312.
    [6] Armstrong P, Zapp H R, Brown G K. Impulsive excitation of acoustic vibrations in apples for Firmness determination [J]. Transactions ofASAE, 1990, 33(4):1353-1359.
    [7] Chen P, Sun Z.Huang L. Factors affecting acoustic response of apples [J]. Transactions of ASAE, 1992, 35(6): 1915-1920.
    [8] Duprat F, Grotte M, Pietri E, et al.The acoustic impulse response method for measuring the overall firmness of fruit[J]. Journal of Agricultural Engineering Research, 1997, 66(1): 251-259.
    [9] Hayashi S, Sugiyama J, Otobe K. Nondestructive quality evaluation of fruits and vegetables by acoustic transmission waves [J]. Proc. ARBIP95(JSAM), 1995,227-234.
    [10] Stone M L, Armstrong P R, Zhang X.. Watermelon maturity determination in the field using acoustic impulse impedance techniques [J]. Transactions of ASAE, 1996, 39(6):2325-2330.
    [11] Sugiyama J, Otobe K, Hayashi S. Firmness measurement of muskmelons by acoustic impulse transmission [J]. Transactions ofASAE, 1994, 37(4): 1234-1241.
    [12] Overfield N D. Egg grading as a form of quality control[J]. Poultry Misset, 1987,10-13
    [13] 陈克安,曾向阳,李海英.声学测量[M].北京:科学出版社,2005
    [14] SAS.SAS system release 8.2[M].SAS, Institute Inc. USA, 2002
    [1] Bain M M. Eggshell structure and mechanical strength [A]. In Proc. 8th Australian Poultry and Feed Convention[C], Gold Coast, Queensland, Australia, October. 1990
    [2] Cho H K, Choi W K, Pack J H. Detection of Surface in Shell Eggs by Acoustic Impulse Method [J].TransactionsofASAE. 2000, 43 (6): 1921~1926
    [3] 文友先,王巧华,宗望远,等.鸭蛋破损检测的试验研究[J].华中农业大学学报,2002,(3):285~287
    [4] 陈红,王巧华,文友先.无损检测技术在禽蛋破损自动检测中的应用[J].食品与机械,2003 (05):9~10
    [5] Goodrum J W, Elster R T. Machine vision for crack detection in rotating eggs [J].Transactions of the ASAE, 1992, 35(4):1323~1328
    [6] Jenshin L, Lin Y, Hsieh M.An automatic system for eggshell quality monitoring[J].Transactions of the ASAE, 2001,44(3):1323-1328
    [7] 蒋宗礼.人工神经网络导论[M].北京:高等教育出版社,2001:1-13
    [8] 宋韬,曾德超.基于人工神经网络的玉米籽粒形态识别方法的研究[J].农业工程学报,1997 (2),177-181
    [9] 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[J].农业工程学报,1997,13(2):173-176
    [10] Kivanc Kilic, Ismail Hakki Boyaci, Hamit Koksel. A classification system for beans using computer vision system and artificial neural networks[J]. Journal of Food Engineering, Corrected Proof, Available online 24 January 2006
    [11] 陈兵旗,孙明.Visual C++实用图像处理专业教程[M].北京:清华大学出版社,2004
    [12] 周长发.精通Visual c++图像编程[M].北京:电子工业出版社,2000
    [13] SAS (2002). SAS system release 8.2. [M]. SAS, Institute Inc. USA
    [14] 王耀南,李树涛,毛建旭.计算机图像处理与识别技术[M].北京:高等教育出版社,2001
    [15] 方如明.计算机图像处理技术及其在农业工程中的应用[M].清华大学出版社,1999
    [16] 阮秋琦.数字图像处理学[M].北京:电子工业出版社,2001
    [17] 许东,吴铮.基于MATLAB 6.X系统分析和设计——神经网络[M].西安电子科技大学出版社,2002
    [1] 徐丽娜.神经网络控制[M].北京:电子工业出版社,2003.
    [2] 许东,吴铮.基于MATLAB 6.X系统分析和设计——神经网络[M].西安电子科技大学出版社,2002.
    [1] Elster R T, Goodrum J W. Detection in eggs by machine vision [J]. Transactions of the ASAE, 1991, 30(1): 307-312.
    [2] 孙永海,鲜于建川,石晶.基于计算机视觉的冷却牛肉嫩度分析方法[J].农业机械学报,2003,34(5):102-105.
    [3] 相俊红,庞俊杰.国内外禽蛋清选分级技术及设备的比较[J].农产品加工,2004,(1):8-10
    [4] 沈明霞,张瑞合,姬长英.基于人眼视觉的农产品图象分割方法[J].南京农业大学学报:自然科学版,2004,27(4):114-117.
    [5] Tadhg, Sun Da-wen. Improving quality inspection of food products by computer vision [J]. Journal of Food Engineering,2004,61,3-16.
    [6] 凌云,王一鸣,孙明,等.基于视觉的大米外观品质检测装置[J].农业机械学报,2005,36(9):89-92.
    [7] 林开颜,吴军辉,许立鸿.基于计算机视觉技术的水果形状分级方法[J].农业机械学报,2005,36 (6):71-74.
    [8] 陈全胜,赵杰文,张海东,等.利用计算机视觉识别茶叶的色泽类型[J].江苏大学学报:自然科学版,2005,26,(6):431-463.
    [9] 王树文,张长利,放俊龙.应用计算机视觉对番茄损伤分类的研究[J].东北农业大学学报,2006,37,(2):215-218.
    [1] 李晓东.蛋品科学和技术[M].北京:化学工业出版社,2005。
    [2] 刘燕德,乔振先.鸡蛋光特性及其新鲜度的相关性研究[J].江西农业大学学报,2002,24(1):45-47
    [3] 方如明,向忠乎,李国文.鸡蛋内部品质的光特性无损检测[J].农业工程学报.1993,9(3):102~107
    [4] 徐丽娜.神经网络控制[M].北京:电子工业出版社,2003.
    [5] 包晓安,张瑞林,钟乐海.基于人工神经网络与图像处理的苹果识别方法研究[J].农业工程 学报,2004,20(3):210~112.
    [6] 王树文,张长利,房俊龙.基于计算机视觉的番茄损伤自动检测与分类研究[J].农业工程学报,2005,21(5):98~101.
    [7] 王巧华,任奕林,文友先.基于BP神经网络的鸡蛋新鲜度无损检测方法[J].农业机械学报,2006,37(1):104~106.
    [8] Kivanc Kilic, Ismail Hakki Boyaci, Hamit Koksel. A classification system for beans using computer vision system and artificial neural networks[J]. Journal of Food Engineering, Corrected Proof, Available online 24 January 2006.
    [9] SAS (2002). SAS system release 8.2. [M], SAS, Institute Inc. USA
    [10] 徐丽娜.神经网络控制[M].北京:电子工业出版社,2003.
    [11] 许东,吴铮.基于MATLAB 6.X系统分析和设计——神经网络[M].西安电子科技大学出版社,2002.
    [1] 徐立中.数字图像的智能信息处理[M].北京:国防工业出版社,2001
    [2] 赵小锋,赵辉.Visual C++/MATLAB图像与识别实用案例精选.北京:人民邮电出版社,2004
    [3] 陈兵旗,孙明.Visual C++实用图像处理专业教程[M].北京:清华大学出版社,2004
    [4] 夏德深,傅德胜.现代图像处理技术与应用[M].南京:东南大学出版社,1997

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700