CN105698693B - A kind of egg gas chamber diameter measuring method based on near-infrared laser image - Google Patents

A kind of egg gas chamber diameter measuring method based on near-infrared laser image Download PDF

Info

Publication number
CN105698693B
CN105698693B CN201610180628.3A CN201610180628A CN105698693B CN 105698693 B CN105698693 B CN 105698693B CN 201610180628 A CN201610180628 A CN 201610180628A CN 105698693 B CN105698693 B CN 105698693B
Authority
CN
China
Prior art keywords
egg
image
point
air cell
infrared laser
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201610180628.3A
Other languages
Chinese (zh)
Other versions
CN105698693A (en
Inventor
屠康
孙柯
马龙
潘磊庆
彭菁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ningxia Jiusanling Ecological Agriculture And Animal Husbandry Co ltd
Original Assignee
Nanjing Agricultural University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing Agricultural University filed Critical Nanjing Agricultural University
Priority to CN201610180628.3A priority Critical patent/CN105698693B/en
Publication of CN105698693A publication Critical patent/CN105698693A/en
Application granted granted Critical
Publication of CN105698693B publication Critical patent/CN105698693B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01BMEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00Measuring arrangements characterised by the use of optical techniques
    • G01B11/08Measuring arrangements characterised by the use of optical techniques for measuring diameters
    • G01B11/12Measuring arrangements characterised by the use of optical techniques for measuring diameters internal diameters
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
    • G01N21/3563Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
    • G01N21/359Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/95Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined

Landscapes

  • Physics & Mathematics (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Biochemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

本发明公开一种基于近红外激光图像的鸡蛋气室直径测量方法,属于计算机视觉无损检测领域。该方法提供了一种由红外激光器、黑色金属管、蛋托、近红外摄像头和暗箱组成的鸡蛋气室图像采集装置及相应气室图像采集方法,还提供了包含图像中值滤波、64阶灰度直方图提取、自动双峰法阈值分割、去除所有非最大面积的连通区域、计算气室二值图像面积的图像处理方法和计算鸡蛋气室直径的方法。该方法可以快速准确地测量鸡蛋的气室直径,为基于气室特征的鸡蛋新鲜度检测研究奠定了基础。The invention discloses a method for measuring the diameter of an egg air chamber based on a near-infrared laser image, which belongs to the field of computer vision nondestructive testing. The method provides an egg air chamber image acquisition device and a corresponding air chamber image acquisition method composed of an infrared laser, a ferrous metal tube, an egg tray, a near-infrared camera, and a dark box. Degree histogram extraction, automatic bimodal threshold segmentation, removal of all non-maximum area connected regions, image processing method to calculate air cell binary image area and method to calculate egg air cell diameter. This method can quickly and accurately measure the air cell diameter of eggs, which lays the foundation for the research on egg freshness detection based on air cell characteristics.

Description

一种基于近红外激光图像的鸡蛋气室直径测量方法A method for measuring the air cell diameter of eggs based on near-infrared laser images

技术领域:Technical field:

本发明属于计算机视觉无损检测领域,特别涉及一种基于近红外激光图像的鸡蛋气室直径测量方法。The invention belongs to the field of computer vision non-destructive testing, in particular to a method for measuring the diameter of an egg air chamber based on a near-infrared laser image.

背景技术:Background technique:

鸡蛋营养丰富、价格低廉,深受广大消费者的欢迎。随着贮藏时间的增长,鸡蛋新鲜度、营养价值和食用安全性都会逐渐降低。鸡蛋气室是鸡蛋排除母鸡体外后,其内容物由于温度降低收缩而在鸡蛋大头形成的中空区域。随着鸡蛋贮藏时间增长和新鲜度的下降,蛋内原有水分通过蛋壳气孔蒸发,部分内容物被微生物分解为CO2和水分通过气孔溢出,导致内容物进一步收缩,气室逐渐变大。气室大小是鸡蛋新鲜度无损检测中的重要参数,很多鸡蛋新鲜度无损检测的方法都采用气室大小作为主要评价指标。Eggs are rich in nutrition and low in price, and are very popular among consumers. As the storage time increases, the freshness, nutritional value and food safety of eggs will gradually decrease. The egg air cell is the hollow area formed in the large head of the egg after the egg is removed from the hen's body and its contents shrink due to cooling. As the egg storage time increases and the freshness decreases, the original water in the egg evaporates through the pores of the eggshell, and part of the contents are decomposed by microorganisms into CO 2 and the water overflows through the pores, resulting in further shrinkage of the contents and the gradual enlargement of the air cells. The size of the air cell is an important parameter in the non-destructive testing of egg freshness. Many methods of non-destructive testing of egg freshness use the size of the air cell as the main evaluation index.

气室高度是鸡蛋气室大小的评价目前常用指标,然而气室在鸡蛋大头端分布的不均匀性导致在不同的方向所观察到的气室高度差别较大,且气室高度测量易受相机拍摄角度的影响,测量的气室高度不能真实反应鸡蛋的气室大小。从鸡蛋大头端观察气室时,气室近似为圆形,相对而言,用气室的直径评价鸡蛋气室大小所受影响因素较小,更能客观地反应鸡蛋气室的大小,从而更准确地评价鸡蛋新鲜度。在气室被光源照亮的情况下,可以用笔描出鸡蛋气室的形状,再用游标卡尺测量其直径,但是由于鸡蛋个体差异较大,蛋壳透光性各不相同,实现鸡蛋气室直径自动检测较为困难,相应方法也未见报道。The air cell height is a commonly used index to evaluate the size of the egg air cell at present. However, the uneven distribution of the air cell at the large end of the egg leads to a large difference in the height of the air cell observed in different directions, and the measurement of the air cell height is easily affected by the camera. Due to the influence of the shooting angle, the measured air cell height cannot truly reflect the size of the air cell of the egg. When the air cell is observed from the big end of the egg, the air cell is approximately circular. Relatively speaking, using the diameter of the air cell to evaluate the size of the egg’s air cell is less affected, and it can more objectively reflect the size of the egg’s air cell. Accurately evaluate egg freshness. When the air cell is illuminated by the light source, you can use a pen to trace the shape of the egg air cell, and then use a vernier caliper to measure its diameter. However, due to the large differences between individual eggs and the light transmittance of eggshells, the diameter of the egg air cell can be realized. Automatic detection is relatively difficult, and the corresponding method has not been reported.

因此,建立能够自动无损检测鸡蛋气室的方法是目前本领域科研工作者需要解决的技术问题。Therefore, establishing a method capable of automatically non-destructively detecting egg air chambers is a technical problem that researchers in this field need to solve.

发明内容:Invention content:

本发明的目的是提供一种测量鸡蛋气室直径方法,该方法可以测量鸡蛋的气室直径。The purpose of the present invention is to provide a method for measuring the diameter of the air cell of an egg, which can measure the diameter of the air cell of the egg.

为解决上述问题,本发明提供了一种基于近红外激光图像的鸡蛋气室直径测量方法,测量步骤为先用近红外激光图像系统按照气室图像采集方法获取图像,再经过图像处理方法得到气室二值图像面积,最后利用模型计算方法得到鸡蛋气室直径,其特征在于:In order to solve the above problems, the present invention provides a method for measuring the diameter of the air cell of an egg based on a near-infrared laser image. The area of the chamber binary image, and finally use the model calculation method to obtain the diameter of the egg air chamber, which is characterized in that:

1)近红外激光图像系统,包含50mW 980nm圆形光斑近红外激光器(1)、黑色金属管(2)、蛋托(4)、近红外摄像头(5)和暗箱(6),其中,近红外激光器(1)与竖直方向夹角为30°;黑色金属管内径4mm,外径6mm连接在近红外激光器(1)的出光孔上,并平行于近红外激光器(1),使激光器射出的激光可以穿过黑色金属管(2),黑色金属管(2)末端为水平切口,切口周围粘贴一层环状黑绒布以防漏光;蛋托(4)位于黑色金属管水平切口下方5cm处,且可上下运动各5mm,以适应不同大小的鸡蛋(3);近红外摄像头(5)感光范围为800到1000nm,130万像素黑白近红外摄像头,焦距为20cm,位于鸡蛋(3)的正上方20cm处;暗箱(6)为不透光箱体,罩在装置外部,为图像采集提供暗环境,并为各部件提供支撑;1) A near-infrared laser imaging system, including a 50mW 980nm circular spot near-infrared laser (1), a ferrous metal tube (2), an egg tray (4), a near-infrared camera (5) and a dark box (6), in which the near-infrared The angle between the laser (1) and the vertical direction is 30°; the black metal tube with an inner diameter of 4 mm and an outer diameter of 6 mm is connected to the light exit hole of the near-infrared laser (1), and is parallel to the near-infrared laser (1), so that the laser emits The laser can pass through the black metal tube (2), and the end of the black metal tube (2) is a horizontal cut, and a layer of ring-shaped black flannelette is pasted around the cut to prevent light leakage; the egg tray (4) is located 5cm below the horizontal cut of the black metal tube, And it can move up and down by 5mm to adapt to eggs (3) of different sizes; the near-infrared camera (5) has a photosensitive range of 800 to 1000nm, a 1.3 million-pixel black and white near-infrared camera with a focal length of 20cm, and is located directly above the egg (3) 20cm; the dark box (6) is an opaque box, which is covered outside the device to provide a dark environment for image acquisition and support for each component;

2)气室图像采集方法为:将鸡蛋(3)大头向上放置于蛋托(4)上,上下移动蛋托(4),使鸡蛋(3)大头端中心紧贴黑色金属管(2)的末端,然后打开近红外激光器(1),近红外激光器(1)发出一束波长为980nm红外光线穿过黑色金属管(2)照在鸡蛋(3)大头端中心,再用近红外摄像头(5)采集图像,即可得到清晰的鸡蛋气室图像;2) The air chamber image acquisition method is as follows: place the egg (3) with the big head up on the egg tray (4), move the egg tray (4) up and down, so that the center of the big end of the egg (3) is close to the center of the black metal tube (2). end, then turn on the near-infrared laser (1), and the near-infrared laser (1) emits a beam of infrared light with a wavelength of 980nm through the black metal tube (2) and shines on the center of the big end of the egg (3), and then uses the near-infrared camera (5 ) to collect images to obtain a clear egg air cell image;

3)图像处理方法为:先对图像进行5×5中值滤波去噪,然后提取图像256阶原始灰度直方图,并将原直方图中每4阶分为一组,取像素点个数的平均值为该阶的像素值,获得图像的64阶灰度直方图,然后从64阶灰度直方图第一点开始向后遍历,若后点对应的像素点个数大于当前点时,前点为一个峰的起点,再从该点的下一个点开始向后遍历,若后点对应像素点个数大于当前点,则当前点为峰的结束点,后点为下一个峰的起点,按照该方法循环向后遍历,直到直方图末端,得到所有峰的起点和结束点,然后遍历找出各峰的峰顶对应的阶数及其像素值,再将所有峰编号,并按各峰峰顶的像素值对各峰排序,求出第二和第三个峰的峰顶对应的阶数a和b,然后从图像原始256阶灰度直方图中遍历灰度值在(a+1)×4和(b-1)×4之间区域,找出像素点个数最小的灰度值作为分割阈值,并用该阈值对原始气室图像阈值分割,得到含噪点的气室的二值图像,然后对气室二值图像中每个连通域进行标记,并计算出各连通域面积,找出最大的连通域面积,再去除小于该面积的所有连通域,得到气室的二值图像,并求其面积S;3) The image processing method is as follows: first perform 5×5 median filter denoising on the image, then extract the 256-order original grayscale histogram of the image, and divide the original histogram into a group for every 4th order, and take the number of pixels The average value of is the pixel value of this order, and obtains the 64-level grayscale histogram of the image, and then traverses backwards from the first point of the 64-level grayscale histogram. If the number of pixels corresponding to the latter point is greater than the current point, The previous point is the starting point of a peak, and then traverse backward from the next point of this point, if the number of pixels corresponding to the latter point is greater than the current point, the current point is the end point of the peak, and the latter point is the starting point of the next peak , follow this method to loop backwards until the end of the histogram to get the start and end points of all peaks, and then traverse to find the order and pixel value corresponding to the peak top of each peak, and then number all the peaks and press each The pixel values of the peaks are sorted for each peak, and the orders a and b corresponding to the peaks of the second and third peaks are obtained, and then the gray value is traversed from the original 256-level gray histogram of the image in (a+ In the area between 1)×4 and (b-1)×4, find out the gray value with the smallest number of pixels as the segmentation threshold, and use this threshold to segment the original air chamber image threshold, and obtain the second image of the air chamber containing noise. Value image, and then mark each connected domain in the binary image of the gas chamber, and calculate the area of each connected domain, find the largest connected domain area, and then remove all connected domains smaller than this area, and obtain the binary value of the gas chamber image, and find its area S;

4)模型计算方法为:模型计算公式为:其中S为鸡蛋气室二值图像的面积,d为鸡蛋气室直径。4) The model calculation method is: the model calculation formula is: Where S is the area of the binary image of the egg air cell, and d is the diameter of the egg air cell.

附图说明:Description of drawings:

图1:鸡蛋气室图像采集装置Figure 1: Egg Air Cell Image Acquisition Device

图2:鸡蛋原始气室图像Figure 2: Image of the original air cell of an egg

图3:256阶灰度直方图Figure 3: 256-level grayscale histogram

图4:64阶灰度直方图Figure 4: 64-level grayscale histogram

图5:气室二值图像Figure 5: Binary image of the gas chamber

具体实施方式:Detailed ways:

本发明的目的是提供一种测量鸡蛋气室直径方法,该方法可以测量鸡蛋的气室直径,获得更客观的描述气室大小的参数。The purpose of the present invention is to provide a method for measuring the diameter of the air cell of an egg, which can measure the diameter of the air cell of the egg and obtain a more objective parameter describing the size of the air cell.

为了使本技术领域人员更好地理解本发明方案,下面结合具体实施方式对本发明作进一步的详细说明。In order to enable those skilled in the art to better understand the solutions of the present invention, the present invention will be further described in detail below in conjunction with specific embodiments.

在一种具体实施例中,测量鸡蛋的气室直径。首先将鸡蛋(3)大头向上放置于近红外激光图像系统的蛋托(4)上,上下移动蛋托(4),使鸡蛋(3)大头端中心紧贴黑色金属管(2)的末端,然后打开近红外激光器(1),近红外激光器(1)发出一束波长为980nm红外光线穿过黑色金属管(2)照在鸡蛋(3)大头端中心,再用近红外摄像头采集图片得到原始鸡蛋气室图像。然后对鸡蛋气室图像进行5×5中值滤波,并提取图像256阶原始灰度直方图。将原始直方图中每4阶分为一组,并取像素点个数的平均值为该阶的像素值,即可得图像的64阶灰度直方图,然后从该直方图第一点开始向后遍历,若后点对应的像素点个数大于当前点时,前点为一个峰的起点,再从该点的下一个点开始向后遍历,若后点对应像素点个数大于当前点,则当前点为峰的结束点,后点为下一个峰的起点,再继续遍历,直到直方图末端,得到所有峰的起点和结束点,然后遍历找出各峰的峰顶对应的阶数及其像素值,再将所有峰编号,并按各峰峰顶的像素值对各峰排序,求出第二和第三个峰的峰顶对应的阶数a和b,然后从图像原始256阶灰度直方图中遍历灰度值在(a+1)×4和(b-1)×4之间区域,找出像素点个数最小的灰度值作为分割阈值,再用该阈值对原始气室图像阈值分割,得到含噪点的气室的二值图像,然后对图像中每个连通域进行标记,计算出各连通域面积,并找出最大的连通域面积,再去除小于该面积的所有连通域,得到气室的二值图像,并计算出气室二值图像的面积S,带入模型计算式中求出鸡蛋的气室直径d。In a specific embodiment, the air cell diameter of an egg is measured. First, put the egg (3) with its big head up on the egg tray (4) of the near-infrared laser imaging system, move the egg tray (4) up and down, so that the center of the big end of the egg (3) is close to the end of the black metal tube (2), Then turn on the near-infrared laser (1), and the near-infrared laser (1) emits a beam of infrared light with a wavelength of 980nm through the black metal tube (2) and shines on the center of the big end of the egg (3), and then collects pictures with a near-infrared camera to obtain the original Egg air cell image. Then the 5×5 median filter is performed on the egg air cell image, and the 256-order original gray histogram of the image is extracted. Divide the original histogram into groups of 4 levels, and take the average value of the number of pixels as the pixel value of this level to get the 64-level grayscale histogram of the image, and then start from the first point of the histogram Traverse backwards, if the number of pixels corresponding to the latter point is greater than the current point, the previous point is the starting point of a peak, and then traverse backwards from the next point of this point, if the number of pixels corresponding to the latter point is greater than the current point , then the current point is the end point of the peak, and the next point is the start point of the next peak, and then continue to traverse until the end of the histogram, get the start and end points of all peaks, and then traverse to find the order corresponding to the peak top of each peak and its pixel value, and then number all the peaks, and sort the peaks according to the pixel value of the top of each peak, and find the order a and b corresponding to the peak top of the second and third peak, and then from the original image 256 In the grayscale histogram, traverse the grayscale value between (a+1)×4 and (b-1)×4, find out the grayscale value with the smallest number of pixels as the segmentation threshold, and then use this threshold to Threshold segmentation of the original air chamber image to obtain the binary image of the air chamber containing noise, and then mark each connected domain in the image, calculate the area of each connected domain, and find the largest connected domain area, and then remove the smaller than the area All the connected domains of , get the binary image of the air chamber, and calculate the area S of the binary image of the air chamber, and bring it into the model calculation formula Find the air cell diameter d of the egg.

实施例Example

鸡蛋气室直径的提取:首先将待测鸡蛋(3)大头向上放置于近红外激光图像系统的蛋托(4)上,上下移动蛋托(4),使鸡蛋(3)大头端中心紧贴黑色金属管(2)的末端,然后打开近红外激光器(1),近红外激光器(1)发出一束波长为980nm红外光线穿过黑色金属管(2)照在鸡蛋(3)大头端中心,再用近红外摄像头采集图片得到原始鸡蛋气室图像,如图2所示。Extraction of egg air cell diameter: first place the egg to be tested (3) with its big head up on the egg tray (4) of the near-infrared laser imaging system, and move the egg tray (4) up and down so that the center of the egg (3) is close to the center of the big end The end of the black metal tube (2), and then turn on the near-infrared laser (1), and the near-infrared laser (1) emits a beam of infrared light with a wavelength of 980nm through the black metal tube (2) and shines on the center of the big end of the egg (3), Then use a near-infrared camera to collect pictures to obtain the original egg air cell image, as shown in Figure 2.

然后对鸡蛋气室图像进行5×5中值滤波,并提取图像256阶原始灰度直方图,如图3所示。将原始直方图中每4阶分为一组,并取像素点个数的平均值为该阶的像素值,获得图像的64阶灰度直方图,如图4所示。Then, the 5×5 median filter is performed on the egg air cell image, and the 256-order original gray histogram of the image is extracted, as shown in Figure 3. Divide the original histogram into groups of 4 levels, and take the average value of the number of pixels as the pixel value of this level to obtain the 64-level grayscale histogram of the image, as shown in Figure 4.

然后从该直方图第一点开始向后遍历,若后点对应的像素点个数大于当前点时,前点为一个峰的起点,再从该点的下一个点开始向后遍历,若后点对应像素点个数大于当前点,则当前点为峰的结束点,后点为下一个峰的起点,再继续遍历,直到直方图末端,得到所有峰的起点和结束点,然后遍历找出各峰的峰顶对应的阶数及其像素值,再将所有峰编号,并按各峰峰顶的像素值对各峰排序,求出第二和第三个峰的峰顶对应的阶数为7和15,然后从图像原始256阶灰度直方图中遍历灰度值在32和56之间区域,找出当灰度值为39时,对应像素点个数最小,即得出最佳分割阈值为39。Then traverse backwards from the first point of the histogram. If the number of pixels corresponding to the latter point is greater than the current point, the previous point is the starting point of a peak, and then traverse backwards from the next point of this point. If the number of pixels corresponding to the point is greater than the current point, the current point is the end point of the peak, and the next point is the start point of the next peak, and then continue to traverse until the end of the histogram, get the start and end points of all peaks, and then traverse to find out The order corresponding to the top of each peak and its pixel value, and then number all the peaks, and sort the peaks according to the pixel value of the top of each peak, and find the order corresponding to the top of the second and third peaks 7 and 15, and then traverse the area with gray values between 32 and 56 from the original 256-level gray histogram of the image, and find out that when the gray value is 39, the number of corresponding pixels is the smallest, that is, the best The segmentation threshold is 39.

再用最佳阈值51对原始气室图像阈值分割,得到带噪点的鸡蛋气室图像,然后对图像中每个连通域进行标记,计算出各连通域面积,并找出最大的连通域面积,再去除小于该面积的所有连通域,得到气室的二值图像,如图5所示,并计算得出气室二值图像面积为27319像素。Then use the optimal threshold 51 to threshold the original air chamber image to obtain the egg air chamber image with noise, then mark each connected domain in the image, calculate the area of each connected domain, and find the largest connected domain area, Then remove all connected domains smaller than this area to obtain the binary image of the air chamber, as shown in Figure 5, and calculate the area of the binary image of the air chamber to be 27319 pixels.

最后将气室二值图像面积带入模型计算式求出气室直径d为25.7mm,与游标卡尺实测值26.3mm相比误差只有2.3%。Finally, bring the area of the binary image of the gas chamber into the model calculation formula The calculated diameter d of the air chamber is 25.7mm, and the error is only 2.3% compared with the measured value of 26.3mm by the vernier caliper.

Claims (1)

1.一种基于近红外激光图像的鸡蛋气室直径测量方法,其测量步骤为先用近红外激光图像系统按照气室图像采集方法获取图像,再经过图像处理方法得到气室二值图像面积,最后利用模型计算方法得到鸡蛋气室直径,其特征在于:1. A method for measuring the diameter of an egg air cell based on a near-infrared laser image, the measurement steps of which are to first use a near-infrared laser image system to obtain an image according to the air cell image acquisition method, and then obtain the binary image area of the air cell through an image processing method, Finally, the diameter of the egg air chamber is obtained by using the model calculation method, which is characterized in that: 1)近红外激光图像系统,包含50mW 980nm圆形光斑近红外激光器(1)、黑色金属管(2)、蛋托(4)、近红外摄像头(5)和暗箱(6),其中,近红外激光器(1)与竖直方向夹角为30°;黑色金属管内径4mm,外径6mm连接在近红外激光器(1)的出光孔上,并平行于近红外激光器(1),使激光器射出的激光可以穿过黑色金属管(2),黑色金属管(2)末端为水平切口,切口周围粘贴一层环状黑绒布以防漏光;蛋托(4)位于黑色金属管水平切口下方5cm处,且可上下运动各5mm,以适应不同大小的鸡蛋(3);近红外摄像头(5)感光范围为800到1000nm,130万像素黑白近红外摄像头,焦距为20cm,位于鸡蛋(3)的正上方20cm处;暗箱(6)为不透光箱体,罩在装置外部,为图像采集提供暗环境,并为各部件提供支撑;1) A near-infrared laser imaging system, including a 50mW 980nm circular spot near-infrared laser (1), a ferrous metal tube (2), an egg tray (4), a near-infrared camera (5) and a dark box (6), in which the near-infrared The angle between the laser (1) and the vertical direction is 30°; the black metal tube with an inner diameter of 4 mm and an outer diameter of 6 mm is connected to the light exit hole of the near-infrared laser (1), and is parallel to the near-infrared laser (1), so that the laser emits The laser can pass through the black metal tube (2), and the end of the black metal tube (2) is a horizontal cut, and a layer of ring-shaped black flannelette is pasted around the cut to prevent light leakage; the egg tray (4) is located 5cm below the horizontal cut of the black metal tube, And it can move up and down by 5mm to adapt to eggs (3) of different sizes; the near-infrared camera (5) has a photosensitive range of 800 to 1000nm, a 1.3 million-pixel black and white near-infrared camera with a focal length of 20cm, and is located directly above the egg (3) 20cm; the dark box (6) is an opaque box, which is covered outside the device to provide a dark environment for image acquisition and support for each component; 2)气室图像采集方法为:将鸡蛋(3)大头向上放置于蛋托(4)上,上下移动蛋托(4),使鸡蛋(3)大头端中心紧贴黑色金属管(2)的末端,然后打开近红外激光器(1),近红外激光器(1)发出一束波长为980nm红外光线穿过黑色金属管(2)照在鸡蛋(3)大头端中心,再用近红外摄像头(5)采集图像,即可得到清晰的鸡蛋气室图像;2) The air chamber image acquisition method is as follows: place the egg (3) with the big head up on the egg tray (4), move the egg tray (4) up and down, so that the center of the big end of the egg (3) is close to the center of the black metal tube (2). end, then turn on the near-infrared laser (1), and the near-infrared laser (1) emits a beam of infrared light with a wavelength of 980nm through the black metal tube (2) and shines on the center of the big end of the egg (3), and then uses the near-infrared camera (5 ) to collect images to obtain a clear egg air cell image; 3)图像处理方法为:先对图像进行5×5中值滤波去噪,然后提取图像256阶原始灰度直方图,并将原直方图中每4阶分为一组,共分为64组,取每组像素点个数的平均值,再用获得的各组的平均像素点个数值绘制图像的64阶灰度直方图,然后从64阶灰度直方图第一点开始向后遍历,若后点对应的像素点个数大于当前点时,前点为一个峰的起点,再从该点的下一个点开始向后遍历,若后点对应像素点个数大于当前点,则当前点为峰的结束点,后点为下一个峰的起点,按照该方法循环向后遍历,直到直方图末端,得到所有峰的起点和结束点,然后遍历找出各峰的峰顶对应的阶数及其像素值,再将所有峰编号,并按各峰峰顶的像素值对各峰排序,求出第二和第三个峰的峰顶对应的阶数a和b,然后从图像原始256阶灰度直方图中遍历灰度值在(a+1)×4和(b-1)×4之间区域,找出像素点个数最小的灰度值作为分割阈值,并用该阈值对原始气室图像阈值分割,得到含噪点的气室的二值图像,然后对气室二值图像中每个连通域进行标记,并计算出各连通域面积,找出最大的连通域面积,再去除小于该面积的所有连通域,得到气室的二值图像,并求其面积S;3) The image processing method is as follows: first perform 5×5 median filter denoising on the image, then extract the 256-order original grayscale histogram of the image, and divide the original histogram into a group for every 4th order, and divide it into 64 groups in total , take the average value of the number of pixels in each group, and then use the obtained average pixel value of each group to draw the 64-level grayscale histogram of the image, and then traverse backward from the first point of the 64-level grayscale histogram, If the number of pixels corresponding to the later point is greater than the current point, the previous point is the starting point of a peak, and then traverse backwards from the next point of the point, if the number of pixels corresponding to the latter point is greater than the current point, the current point is the end point of the peak, and the next point is the starting point of the next peak. According to this method, loop backwards until the end of the histogram to get the starting and ending points of all peaks, and then traverse to find the order corresponding to the peak top of each peak and its pixel value, and then number all the peaks, and sort the peaks according to the pixel value of the top of each peak, and find the order a and b corresponding to the peak top of the second and third peak, and then from the original image 256 In the gray scale histogram, traverse the gray value between (a+1)×4 and (b-1)×4, find out the gray value with the smallest number of pixels as the segmentation threshold, and use this threshold to analyze the original Threshold segmentation of the gas chamber image to obtain the binary image of the gas chamber containing noise, and then mark each connected domain in the gas chamber binary image, and calculate the area of each connected domain, find the largest connected domain area, and then remove For all connected domains smaller than this area, obtain the binary image of the air chamber, and calculate its area S; 4)模型计算方法为:模型计算公式为:其中S为鸡蛋气室二值图像的面积,d为鸡蛋气室直径。4) The model calculation method is: the model calculation formula is: Where S is the area of the binary image of the egg air cell, and d is the diameter of the egg air cell.
CN201610180628.3A 2016-03-24 2016-03-24 A kind of egg gas chamber diameter measuring method based on near-infrared laser image Active CN105698693B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610180628.3A CN105698693B (en) 2016-03-24 2016-03-24 A kind of egg gas chamber diameter measuring method based on near-infrared laser image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610180628.3A CN105698693B (en) 2016-03-24 2016-03-24 A kind of egg gas chamber diameter measuring method based on near-infrared laser image

Publications (2)

Publication Number Publication Date
CN105698693A CN105698693A (en) 2016-06-22
CN105698693B true CN105698693B (en) 2018-04-17

Family

ID=56232916

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610180628.3A Active CN105698693B (en) 2016-03-24 2016-03-24 A kind of egg gas chamber diameter measuring method based on near-infrared laser image

Country Status (1)

Country Link
CN (1) CN105698693B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111014969B (en) * 2019-12-29 2022-03-25 上海赛摩电气有限公司 Automatic change egg broken wall special plane
CN111037102B (en) * 2019-12-29 2021-10-29 上海赛摩电气有限公司 Automatic egg shelling method and device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101672839A (en) * 2009-09-25 2010-03-17 南京农业大学 Device and method for detecting hatching egg incubation quality based on computer vision
CN102147402A (en) * 2011-03-08 2011-08-10 江苏大学 Machine vision technology based method for rapidly detecting egg freshness
CN102169092A (en) * 2011-01-11 2011-08-31 西安理工大学 Method for testing poultry egg freshness based on photon radiation

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001017020A (en) * 1999-07-09 2001-01-23 Seiichi Kitamura Distinguishing device for class and freshness of egg
JP4674685B2 (en) * 2004-08-02 2011-04-20 有限会社ハイ・サーブ Chicken egg freshness detection method and apparatus by impedance sensing

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101672839A (en) * 2009-09-25 2010-03-17 南京农业大学 Device and method for detecting hatching egg incubation quality based on computer vision
CN102169092A (en) * 2011-01-11 2011-08-31 西安理工大学 Method for testing poultry egg freshness based on photon radiation
CN102147402A (en) * 2011-03-08 2011-08-10 江苏大学 Machine vision technology based method for rapidly detecting egg freshness

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
傅里叶变换近红外反射用于鸡蛋蛋品质的研究;候卓成等;《光谱学与光谱分析》;20090831;第29卷(第8期);第2063-2066页 *

Also Published As

Publication number Publication date
CN105698693A (en) 2016-06-22

Similar Documents

Publication Publication Date Title
CN108629775B (en) A kind of hot high-speed wire surface image processing method
CN102176228B (en) A Machine Vision Method for Recognizing Information on Multiple Analog Instrument Dials
CN101634551B (en) Method and system for detecting surface roughness
CN101546426B (en) Weak luminescent image processing method based on region enhancement and region extraction
CN115018844B (en) Plastic film quality evaluation method based on artificial intelligence
CN104198497B (en) Surface defect detection method based on visual saliency map and support vector machine
CN110443278B (en) A method, device and equipment for detecting abnormal thickness of grid lines of solar cells
CN103900972B (en) Multi-feature fusion-based meat freshness hyperspectral image visual detection
CN109766909B (en) Analysis method for aging behavior of shore environment microplastic based on spectrogram fusion
CN105372324B (en) The defects of based on magneto-optic imaging method detection method
CN103674968A (en) Method and device for evaluating machine vision original-value detection of exterior corrosion appearance characteristics of material
CN106023158A (en) SD-OCT-image-based nacre layer defect identification method for fresh water non-nucleated pearl
CN104700395A (en) Method and system for detecting appearance crack of structure
CN108663367A (en) A kind of egg quality lossless detection method based on egg unit weight
CN101709951A (en) Method for measuring and recording phenotypic characters of scallop by computer
CN106340007A (en) Image processing-based automobile body paint film defect detection and identification method
CN107631782A (en) A kind of level testing methods based on Harris Corner Detections
CN109283182A (en) A method, device and system for detecting defects in battery solder joints
CN105698693B (en) A kind of egg gas chamber diameter measuring method based on near-infrared laser image
CN112132803A (en) A method for egg freshness detection based on convolutional neural network
CN101419151A (en) Industrial purified terephthalic acid particle size distribution estimation method based on microscopic image
CN116087036A (en) Device for identifying images of sediment plume of deep sea mining and image analysis method
CN106574224B (en) Method for detecting the presence or absence of biological particles
CN110426395B (en) A kind of solar EL battery silicon wafer surface detection method and device
CN107220972B (en) A kind of quality of poultry eggs discrimination method based on infrared image

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20230609

Address after: 750000 West of Jinshan Village, Hongguang Town, Helan County, Yinchuan, Ningxia (east foot of Helan)

Patentee after: NINGXIA JIUSANLING ECOLOGICAL AGRICULTURE AND ANIMAL HUSBANDRY CO.,LTD.

Address before: Nanjing City, Jiangsu Province, No. 1 210095 Weigang

Patentee before: NANJING AGRICULTURAL University

TR01 Transfer of patent right