EP2572181A1 - Automatic determination of milk quality - Google Patents

Automatic determination of milk quality

Info

Publication number
EP2572181A1
EP2572181A1 EP11724303A EP11724303A EP2572181A1 EP 2572181 A1 EP2572181 A1 EP 2572181A1 EP 11724303 A EP11724303 A EP 11724303A EP 11724303 A EP11724303 A EP 11724303A EP 2572181 A1 EP2572181 A1 EP 2572181A1
Authority
EP
European Patent Office
Prior art keywords
image
img
pressure level
milk
cavity
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.)
Withdrawn
Application number
EP11724303A
Other languages
German (de)
French (fr)
Inventor
Sten Mellberg
Per Klintenstedt
Leif Johannesson
Jörgen STENSTRÖM
Fulin Xiang
Marilyn Krukowski
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.)
DeLaval Holding AB
Original Assignee
DeLaval Holding AB
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 DeLaval Holding AB filed Critical DeLaval Holding AB
Publication of EP2572181A1 publication Critical patent/EP2572181A1/en
Withdrawn legal-status Critical Current

Links

Classifications

    • G01N15/1433—
    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01J—MANUFACTURE OF DAIRY PRODUCTS
    • A01J5/00—Milking machines or devices
    • A01J5/013—On-site detection of mastitis in milk
    • A01J5/0131—On-site detection of mastitis in milk by analysing the milk composition, e.g. concentration or detection of specific substances
    • A01J5/0132—On-site detection of mastitis in milk by analysing the milk composition, e.g. concentration or detection of specific substances using a cell counter
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/1717—Systems in which incident light is modified in accordance with the properties of the material investigated with a modulation of one or more physical properties of the sample during the optical investigation, e.g. electro-reflectance
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/94—Investigating contamination, e.g. dust
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/02—Food
    • G01N33/04—Dairy products
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume, or surface-area of porous materials
    • G01N2015/0007—Investigating dispersion of gas
    • G01N2015/0011—Investigating dispersion of gas in liquids, e.g. bubbles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/1717—Systems in which incident light is modified in accordance with the properties of the material investigated with a modulation of one or more physical properties of the sample during the optical investigation, e.g. electro-reflectance
    • G01N2021/1723—Fluid modulation

Definitions

  • the present invention relates generally to automatic determination of milk quality. More particularly the invention relates to a cell counter unit according to the preamble of claim 1 and a method according to the preamble of claim 5. The invention also relates to a computer program according to claim 9 and a computer readable medium according to claim 10.
  • milking robots have been introduced, which enable animals to autonomously decide when they are to be milked.
  • Milking robots are advantageous because they render it possible to service a relatively large number of milking animals via comparatively few milking machines, Miiking robots are also desirable from an animal health point-of-view, since thereby it is uncomplicated to extract milk more frequently than by applying the existing alternative solutions, and in general, high-frequency milking vouches for a good udder health.
  • milking robots may be somewhat problematic because these machines are often operated without any human operator being present. This, in turn, renders a safe and reliable operation highly important.
  • One aspect of such an operation is that problems related to unsatisfying milk quality must be resolved automatically. For example unac- ceptably high concentration of somatic cells in the milk needs be detected automatically, such that adequate measures can be taken promptly.
  • the object of the present invention is to alleviate the above problem, and thus offer a solution for detecting undesired elements in milk having improved reliability.
  • the object is achieved by the initially described cell counter unit, wherein the cell counter unit includes pressure control means configured to vary a pressure level in the cavity containing the milk sample.
  • the image registration means is configured to, for each milk sample: capture a first image representing the milk sample in the cavity at a first pressure level, and capture a second image representing the milk sample in the cavity at a second pressure level different from said first pressure level.
  • the processor means is configured to correlate image data in the first image with image data in the second image, and based thereon discriminate any gas bubbles from somatic cells in the milk sample.
  • This cell counter unit is advantageous because thereby gas bubbles can be separated from other constituents in the milk in a very efficient and straightforward manner. Hence, for example any somatic cells therein can be detected relatively easily.
  • the processor means is configured to discriminate any gas bubbles from somatic cells in the milk sample based on a size difference between at least one image element in the first image and at least one respective corresponding image element in the second image. This procedure is well suited for implementation by an automatic detection algorithm, for instance being based on thresholding.
  • the second pressure level is lower than the first pressure level.
  • the processor means is here configured to dis- criminate a gas bubble as an image element being larger in the second image than in the first image.
  • the second pressure level is higher than the first pressure level, and the processor means is configured to discriminate a gas bubble as an image element being smaller in the second image than in the first image, in both cases, reliable detection of gas bubbles is enabled.
  • the object is achieved by the method described initially, wherein the method fur- ther includes the steps: receiving a milk sample in the cavity; capturing a first image representing the milk sample in the cavity when the milk therein attains a first pressure level; assigning a second pressure level to the milk sample in the cavity, the second pressure level being different from the first pressure level; capturing a second image representing the milk sample in the cavity when the milk therein attains the second pressure level; correlating image data in the first image with image data in the second image; and based thereon, discriminating any gas bubbles from somatic cells the milk sample.
  • the object is achieved by a computer program, which is directly loadable into the memory of a computer, and includes software adapted to implement the method proposed above when said program is run on a computer.
  • the object is achieved by a computer readable medium, having a program recorded thereon, where the program is to control a computer to perform the method proposed above when the program is loaded into the computer.
  • Figure 1 shows an overview of an exemplifying milking system including the present invention
  • Figure 2 schematically shows a cell counter unit according to one embodiment of the invention
  • Figure 3 illustrates the design of a proposed cavity according to one embodiment of the invention.
  • Figures 4a-b show schematic images illustrating how the sizes of various image elements vary in response to pressure variations depending on whether the image elements represent gas bubbles, or more rigid constituents of the milk;
  • Figure 5 illustrates, by means of a flow diagram, the general method according to the invention.
  • FIG. 1 shows an overview of a milking system in which the present invention may be included.
  • the milking system contains a milking machine 1 1 0, an identification arrangement 120, a cell counter unit 130, a control unit 140, a milk tank 150 and a milking robot 160.
  • the milk tank 150 is configured to store milk having been extracted from a plurality of animals A
  • the milking robot 160 is configured to automatically attach teat cups to an animal A, which is present within an operation area of the milking machine 1 10.
  • the milking robot 160 is advantageous because thereby it is made possible for the animals A to autonomously decide when they wish to be milked.
  • the identification arrangement 120 is configured to identify an animal A approaching the milking machine 1 10, For example the animal A may be identified at a gate means before reaching the milking machine 1 10, or the animal A may be identified when already being present at milking machine 1 10. In any case, the animal A is only milked by the milking machine 1 10 if a set of milk permission criteria are fulfilled for that animal A. For example, this can be effected by the identification arrangement 120 forwarding identification data ID for the animal A to the control unit 140, the control unit 140 checking the set of milk permission criteria, and if these are fulfilled, the control unit 140 generates a first control signal C1 , which causes a first gate to the milking machine 1 10 to open.
  • the cell counter unit 130 is configured to determine a quality parameter Qcc, which reflects a so- matic cell concentration for the milk extracted from said animal A (i.e. a number of cells per unit volume, or a weight of the somatic cells relative to a total milk weight).
  • a second control signal C2 from the control unit 140 preferably causes a second gate to the milking machine 1 10 to open, such that the animal A can exit from the operation area of the milking machine 1 10.
  • a milk conduit 158 connecting the milking machine 1 10 to the milk tank 150 is provided with a valve means 157, which is controllable from the control unit 140 via a third control signal C3. Thereby, any milk that is found to be unsuitable for introduction into the milk tank 150 can instead be diverted into a separate container 155.
  • FIG 2 schematically shows a cell counter unit 130 according to one embodiment of the invention
  • the cell counter unit 130 includes a sampling means 210 and processor means 230.
  • the sampling means 210 is configured to take said samples from a flow of milk passing through the cell counter unit 130 in the form of an input and output flow Q
  • the processor means 230 is configured to determine the quality parameter Qcc based on a concentration of somatic cells in said samples.
  • the cell counter unit 130 may include an optical detector means 220 and a cavity 225 having a well-defined volume.
  • the optical detector means 220 in turn, preferably includes at least one lens element and an image sensor (e.g. of CCD or CMOS type), which is configured to register digital image data D img representing the somatic cells in the cavity 225.
  • the processor means 230 receives the image data D img , and based thereon determines the quality parameter Qcc. Since the cavity 225 has a well-defined volume the number of somatic cells therein provides an accurate measure of the concentration of somatic cells in the milk extracted from the animal A.
  • sampling means 210 is preferably configured to collect such a set of samples, mix the samples and feed a representa- tlve part of the mix into the cavity 225.
  • the cell counter unit 130 includes a light source 223 configured to project light through the cavity 225 and thereby further facilitate the registering of the somatic cells. After processing an amount of milk in the cavity 225, the cavity 225 is cleaned, and depending on the quality of the milk sample, the milk from the cavity 225 may either be discarded or fed into the milk tank 150.
  • the processor means 230 includes, or is associated with, a computer readable medium M, e.g. in the form of a memory module, such that the processor means 230 has access to the contents of this medium M.
  • a program is recorded in the computer readable medium M, and the program is adapted to make a data processor in the processor means 230 control the process described above, as well as the embodiments thereof further elaborated on below, when the program is run on the processor.
  • the cell counter unit 130 includes pressure control means configured to vary a pressure level in the cavity 225.
  • Figure 3 illustrates how the proposed cavity 225 is designed according to one embodiment of the invention.
  • An inlet valve means 310 is configured to input milk from the sampling means 210 into the cavity 225, so that the milk can be examined automatically.
  • an outlet valve means 320 is configured to enable milk from the cavity 225 to exit.
  • the inlet and outlet valve means 310 and 320 are controllable in response to fourth and sixth control signals C4 and C6 respectively from the control unit 140.
  • Pressure control means in the form of a piston and cylinder 330 are connected to the cavity 225. Hence, in response to a fifth control signal C5 from the control unit 140, the pressure level in the cavity 225 can be varied.
  • Figures 4a and 4b show schematic enlarged-scale images D img 1 and D img 2 representing a milk sample in the cavity 225 at a first pressure level and a second pressure level respectively.
  • the first image D img 1 in Figure 4a includes image elements de1 1 , de21 , de31 , de41 and de51 .
  • a second image D img 2 in Figure 4b the pressure level in the cavity 225 has been decreased relative to the pressure level at which the first image D jmg 1 was captured.
  • the second image D img 2 a majority of the image elements are unaltered compared to the first image D img 1 .
  • each of the image elements de12, de22, de32, de42 and de52 in the second image D jmg 2 are larger than the corresponding image elements de1 1 , de21 , de31 , de41 and de51 in the first image D img 1 .
  • This is a sign of that these image elements represent gas bubbles (in contrast to the remaining image elements, which for example may represent relatively rigid constituents, e.g. clusters of somatic cells).
  • the image registration means 227 is configured to for each milk sample capture a first image D img 1 representing the milk sample in the cavity 225 at a first pressure level.
  • the mi!k sample in the cavity 225 has a first pressure level.
  • the pressure control means 330 is configured to assign a second pressure level to the milk in the cavity 225. (The second pressure level is different from said first pressure level.) While the milk in the cavity 225 attains the second pressure level, the image registration means 227 is further configured to capture a second image D img 2 representing the milk sample in the cavity 225.
  • the processor means 230 is configured to correlate image data in the first image D img 1 with image data in the second image D img 2, and based thereon discriminate any gas bubbles from somatic cells the milk sample. This process, in turn, forms a basis for the quality parameter Qcc that reflects a somatic cell concentration in the milk.
  • the processor means 230 is configured to discriminate any gas bubbles from somatic cells in the milk sample on the basis of a size difference between at least one image ele- ment in the first image D jmg 1 and at least one respective corresponding image element in the second image D img 2, i.e. the relationships del 1 -to-de12, de21 -to-de22, de31 -to-de32, de41-to- de42 and de51 -to-de52 respectively mentioned above. If the second pressure level is lower than the first pressure level, the processor means 230 is configured to discriminate a gas bubble as an image element being larger in the second image D img 2 than in the first image D img 1 .
  • the processor means 230 is instead configured to discriminate a gas bubble as an image element being smaller in the second image D img 2 than in the first image D img 1 .
  • a first step 510 receives a milk sample in a cavity. Then, in a step 520, a first image of the sample is captured. The milk sample in the cavity is thereafter assigned a new pressure level, where after in a step 540 a second image of the sample is cap- tured. Subsequently, a step 550 discriminates any gas bubbles from somatic cells in the sample based on correlation of the image data in the first image with image data in the second image. Based on this correlation, in turn, a step 560 determines a quality parameter for the milk sample. All of the process steps, as well as any sub-sequence of steps, described with reference to Figure 5 above may be controlled by means of a programmed computer apparatus.
  • the embodiments of the invention described above with reference to the drawings comprise computer apparatus and processes performed in computer apparatus, the invention thus also extends to computer programs, particularly computer programs on or in a carrier, adapted for putting the invention into practice.
  • the program may be in the form of source code, object code, a code intermediate source and object code such as in partially compiled form, or in any other form suitable for use in the implementation of the process according to the invention.
  • the program may either be a part of an operating system, or be a separate application.
  • the carrier may be any entity or device capable of carrying the program.
  • the carrier may comprise a storage medium, such as a Flash memory, a ROM (Read Only Memory), for example a DVD (Digital Video/Versatile Disk), a CD (Compact Disc) or a semiconductor ROM , an EP- ROM (Erasable Programmable Read-Only Memory), an EEP- ROM (Electrically Erasable Programmable Read-Only Memory), or a magnetic recording medium, for example a floppy disc or hard disc.
  • the carrier may be a transmissible carrier such as an electrical or optical signal which may be conveyed via electrical or optical cable or by radio or by other means.
  • the carrier When the program is embodied in a signal which may be conveyed directly by a cable or other device or means, the carrier may be constituted by such cable or device or means.
  • the carrier may be an integrated circuit in which the prog- ram is embedded, the integrated circuit being adapted for performing , or for use in the performance of, the relevant processes.
  • the invention is advantageous in connection with cow milking , the invention is equally well adapted for implementation in milking machines for any other kind of mammals, such as goats , sheep or buffaloes.

Abstract

A cell counter unit (130) determines a quality parameter reflecting a somatic cell concentration in a milk sample. The cell counter unit (130) includes: a cavity (225) for temporarily storing the milk sample and image registration means (227) for capturing image data (Dimg) representing milk in the cavity (225). For each milk sample, the image registration means (227) captures first and second images. The first image represents the milk sample in the cavity (225) at a first pressure level and the second image represents the same sample at a second pressure level. Pressure control means (330) vary the pressure level in the cavity (225) between said images. A processor means (230) correlates image data in the first image with image data in the second image to discriminate any gas bubbles from somatic cells the milk sample, and based thereon the processor means (230) determines the quality parameter.

Description

Automatic Determination of Milk Quality
THE BACKGROUND OF THE INVENTION AND PRIOR ART
The present invention relates generally to automatic determination of milk quality. More particularly the invention relates to a cell counter unit according to the preamble of claim 1 and a method according to the preamble of claim 5. The invention also relates to a computer program according to claim 9 and a computer readable medium according to claim 10.
Automatic milking solutions are becoming increasingly efficient and sophisticated. Today, there is also a strong demand for flexible and animal-friendly milk production. For example, so- called milking robots have been introduced, which enable animals to autonomously decide when they are to be milked. Milking robots are advantageous because they render it possible to service a relatively large number of milking animals via comparatively few milking machines, Miiking robots are also desirable from an animal health point-of-view, since thereby it is uncomplicated to extract milk more frequently than by applying the existing alternative solutions, and in general, high-frequency milking vouches for a good udder health. However, milking robots may be somewhat problematic because these machines are often operated without any human operator being present. This, in turn, renders a safe and reliable operation highly important. One aspect of such an operation is that problems related to unsatisfying milk quality must be resolved automatically. For example unac- ceptably high concentration of somatic cells in the milk needs be detected automatically, such that adequate measures can be taken promptly.
PROBLEMS ASSOCIATED WITH THE PIROR ART
Various image processing solutions are known for identifying un- desired elements in a milk sample. However, due to limited image resolution and/or processing capacity it has proven to be difficult to distinguish the undesired elements from harmless elements in the form of gas bubbles. SUMMARY OF THE INVENTION
The object of the present invention is to alleviate the above problem, and thus offer a solution for detecting undesired elements in milk having improved reliability.
According to one aspect of the invention, the object is achieved by the initially described cell counter unit, wherein the cell counter unit includes pressure control means configured to vary a pressure level in the cavity containing the milk sample. Further, the image registration means is configured to, for each milk sample: capture a first image representing the milk sample in the cavity at a first pressure level, and capture a second image representing the milk sample in the cavity at a second pressure level different from said first pressure level. Moreover, the processor means is configured to correlate image data in the first image with image data in the second image, and based thereon discriminate any gas bubbles from somatic cells in the milk sample.
This cell counter unit is advantageous because thereby gas bubbles can be separated from other constituents in the milk in a very efficient and straightforward manner. Hence, for example any somatic cells therein can be detected relatively easily.
According to one preferred embodiment of this aspect of the invention, the processor means is configured to discriminate any gas bubbles from somatic cells in the milk sample based on a size difference between at least one image element in the first image and at least one respective corresponding image element in the second image. This procedure is well suited for implementation by an automatic detection algorithm, for instance being based on thresholding.
According to another preferred embodiment of this aspect of the invention, the second pressure level is lower than the first pressure level. The processor means is here configured to dis- criminate a gas bubble as an image element being larger in the second image than in the first image. According to yet another preferred embodiment of this aspect of the invention, the second pressure level is higher than the first pressure level, and the processor means is configured to discriminate a gas bubble as an image element being smaller in the second image than in the first image, in both cases, reliable detection of gas bubbles is enabled.
According to another aspect of the invention, the object is achieved by the method described initially, wherein the method fur- ther includes the steps: receiving a milk sample in the cavity; capturing a first image representing the milk sample in the cavity when the milk therein attains a first pressure level; assigning a second pressure level to the milk sample in the cavity, the second pressure level being different from the first pressure level; capturing a second image representing the milk sample in the cavity when the milk therein attains the second pressure level; correlating image data in the first image with image data in the second image; and based thereon, discriminating any gas bubbles from somatic cells the milk sample. The advantages of this method, as well as the preferred embodiments thereof, are apparent from the discussion above with reference to the proposed receiver.
According to a further aspect of the invention the object is achieved by a computer program, which is directly loadable into the memory of a computer, and includes software adapted to implement the method proposed above when said program is run on a computer.
According to another aspect of the invention the object is achieved by a computer readable medium, having a program recorded thereon, where the program is to control a computer to perform the method proposed above when the program is loaded into the computer.
Further advantages, beneficial features and applications of the present invention will be apparent from the following description and the dependent claims.
BRIEF DESCRIPTION OF THE DRAWINGS
The invention is now to be explained more closely by means of preferred embodiments, which are disclosed as examples, and with reference to the attached drawings.
Figure 1 shows an overview of an exemplifying milking system including the present invention;
Figure 2 schematically shows a cell counter unit according to one embodiment of the invention;
Figure 3 illustrates the design of a proposed cavity according to one embodiment of the invention; and
Figures 4a-b show schematic images illustrating how the sizes of various image elements vary in response to pressure variations depending on whether the image elements represent gas bubbles, or more rigid constituents of the milk; and
Figure 5 illustrates, by means of a flow diagram, the general method according to the invention.
DESCRIPTION OF PREFERRED EMBODIMENTS OF THE IN- VENTION
We refer initially to Figure 1 , which shows an overview of a milking system in which the present invention may be included. The milking system contains a milking machine 1 1 0, an identification arrangement 120, a cell counter unit 130, a control unit 140, a milk tank 150 and a milking robot 160. The milk tank 150 is configured to store milk having been extracted from a plurality of animals A, and the milking robot 160 is configured to automatically attach teat cups to an animal A, which is present within an operation area of the milking machine 1 10. The milking robot 160 is advantageous because thereby it is made possible for the animals A to autonomously decide when they wish to be milked.
The identification arrangement 120 is configured to identify an animal A approaching the milking machine 1 10, For example the animal A may be identified at a gate means before reaching the milking machine 1 10, or the animal A may be identified when already being present at milking machine 1 10. In any case, the animal A is only milked by the milking machine 1 10 if a set of milk permission criteria are fulfilled for that animal A. For example, this can be effected by the identification arrangement 120 forwarding identification data ID for the animal A to the control unit 140, the control unit 140 checking the set of milk permission criteria, and if these are fulfilled, the control unit 140 generates a first control signal C1 , which causes a first gate to the milking machine 1 10 to open.
Once the animal A is present within an operation area of the milking machine 1 10, the machine is controlled to automatically extract milk from the animal A. The cell counter unit 130 is configured to determine a quality parameter Qcc, which reflects a so- matic cell concentration for the milk extracted from said animal A (i.e. a number of cells per unit volume, or a weight of the somatic cells relative to a total milk weight). After completed milking a second control signal C2 from the control unit 140 preferably causes a second gate to the milking machine 1 10 to open, such that the animal A can exit from the operation area of the milking machine 1 10.
A milk conduit 158 connecting the milking machine 1 10 to the milk tank 150 is provided with a valve means 157, which is controllable from the control unit 140 via a third control signal C3. Thereby, any milk that is found to be unsuitable for introduction into the milk tank 150 can instead be diverted into a separate container 155.
Figure 2 schematically shows a cell counter unit 130 according to one embodiment of the invention, In Figure 2, we see that the cell counter unit 130 includes a sampling means 210 and processor means 230. The sampling means 210 is configured to take said samples from a flow of milk passing through the cell counter unit 130 in the form of an input and output flow Q|N and QOUT respectively taken from the main milk conduit 1 58, which in turn, transports milk from the milking machine 1 10 to the milk tank 150.
The processor means 230 is configured to determine the quality parameter Qcc based on a concentration of somatic cells in said samples. Specifically, the cell counter unit 130 may include an optical detector means 220 and a cavity 225 having a well-defined volume. The optical detector means 220, in turn, preferably includes at least one lens element and an image sensor (e.g. of CCD or CMOS type), which is configured to register digital image data Dimg representing the somatic cells in the cavity 225. The processor means 230 receives the image data Dimg, and based thereon determines the quality parameter Qcc. Since the cavity 225 has a well-defined volume the number of somatic cells therein provides an accurate measure of the concentration of somatic cells in the milk extracted from the animal A. This measure can be further enhanced by collecting samples from various phases of the milking procedure, e.g. early, mid and/or late. The sampling means 210 is preferably configured to collect such a set of samples, mix the samples and feed a representa- tlve part of the mix into the cavity 225.
It is also advantageous if the cell counter unit 130 includes a light source 223 configured to project light through the cavity 225 and thereby further facilitate the registering of the somatic cells. After processing an amount of milk in the cavity 225, the cavity 225 is cleaned, and depending on the quality of the milk sample, the milk from the cavity 225 may either be discarded or fed into the milk tank 150.
Preferably, the processor means 230 includes, or is associated with, a computer readable medium M, e.g. in the form of a memory module, such that the processor means 230 has access to the contents of this medium M. Furthermore, a program is recorded in the computer readable medium M, and the program is adapted to make a data processor in the processor means 230 control the process described above, as well as the embodiments thereof further elaborated on below, when the program is run on the processor.
In any case, the cell counter unit 130 includes pressure control means configured to vary a pressure level in the cavity 225. Figure 3 illustrates how the proposed cavity 225 is designed according to one embodiment of the invention.
An inlet valve means 310 is configured to input milk from the sampling means 210 into the cavity 225, so that the milk can be examined automatically. After examination, an outlet valve means 320 is configured to enable milk from the cavity 225 to exit. The inlet and outlet valve means 310 and 320 are controllable in response to fourth and sixth control signals C4 and C6 respectively from the control unit 140. Pressure control means in the form of a piston and cylinder 330 are connected to the cavity 225. Hence, in response to a fifth control signal C5 from the control unit 140, the pressure level in the cavity 225 can be varied.
Figures 4a and 4b show schematic enlarged-scale images Dimg1 and Dimg2 representing a milk sample in the cavity 225 at a first pressure level and a second pressure level respectively.
In a first image Dimg1 in Figure 4a all image elements have essentially the same shape and size. It is therefore difficult to determine whether a given image element embodies somatic cells, or a gas bubble. For instance, the first image Dimg1 includes image elements de1 1 , de21 , de31 , de41 and de51 .
In a second image Dimg2 in Figure 4b, the pressure level in the cavity 225 has been decreased relative to the pressure level at which the first image Djmg1 was captured. As can be seen, in the second image Dimg2 a majority of the image elements are unaltered compared to the first image Dimg1 . However each of the image elements de12, de22, de32, de42 and de52 in the second image Djmg2 are larger than the corresponding image elements de1 1 , de21 , de31 , de41 and de51 in the first image Dimg1 . This is a sign of that these image elements represent gas bubbles (in contrast to the remaining image elements, which for example may represent relatively rigid constituents, e.g. clusters of somatic cells). Returning now to Figures 2 and 3, according to the invention, the image registration means 227 is configured to for each milk sample capture a first image Dimg1 representing the milk sample in the cavity 225 at a first pressure level. Here, the mi!k sample in the cavity 225 has a first pressure level. Then, the pressure control means 330 is configured to assign a second pressure level to the milk in the cavity 225. (The second pressure level is different from said first pressure level.) While the milk in the cavity 225 attains the second pressure level, the image registration means 227 is further configured to capture a second image Dimg2 representing the milk sample in the cavity 225. Thereafter, the processor means 230 is configured to correlate image data in the first image Dimg1 with image data in the second image Dimg2, and based thereon discriminate any gas bubbles from somatic cells the milk sample. This process, in turn, forms a basis for the quality parameter Qcc that reflects a somatic cell concentration in the milk.
Preferably, the processor means 230 is configured to discriminate any gas bubbles from somatic cells in the milk sample on the basis of a size difference between at least one image ele- ment in the first image Djmg1 and at least one respective corresponding image element in the second image Dimg2, i.e. the relationships del 1 -to-de12, de21 -to-de22, de31 -to-de32, de41-to- de42 and de51 -to-de52 respectively mentioned above. If the second pressure level is lower than the first pressure level, the processor means 230 is configured to discriminate a gas bubble as an image element being larger in the second image Dimg2 than in the first image Dimg1 .
If the second pressure level is higher than the first pressure level, the processor means 230 is instead configured to discriminate a gas bubble as an image element being smaller in the second image Dimg2 than in the first image Dimg1 .
In order to sum up, we will now describe the general method according to the invention with reference to the flow diagram in Figure 5.
A first step 510 receives a milk sample in a cavity. Then, in a step 520, a first image of the sample is captured. The milk sample in the cavity is thereafter assigned a new pressure level, where after in a step 540 a second image of the sample is cap- tured. Subsequently, a step 550 discriminates any gas bubbles from somatic cells in the sample based on correlation of the image data in the first image with image data in the second image. Based on this correlation, in turn, a step 560 determines a quality parameter for the milk sample. All of the process steps, as well as any sub-sequence of steps, described with reference to Figure 5 above may be controlled by means of a programmed computer apparatus. Moreover, although the embodiments of the invention described above with reference to the drawings comprise computer apparatus and processes performed in computer apparatus, the invention thus also extends to computer programs, particularly computer programs on or in a carrier, adapted for putting the invention into practice. The program may be in the form of source code, object code, a code intermediate source and object code such as in partially compiled form, or in any other form suitable for use in the implementation of the process according to the invention. The program may either be a part of an operating system, or be a separate application. The carrier may be any entity or device capable of carrying the program. For example, the carrier may comprise a storage medium, such as a Flash memory, a ROM (Read Only Memory), for example a DVD (Digital Video/Versatile Disk), a CD (Compact Disc) or a semiconductor ROM , an EP- ROM (Erasable Programmable Read-Only Memory), an EEP- ROM (Electrically Erasable Programmable Read-Only Memory), or a magnetic recording medium, for example a floppy disc or hard disc. Further, the carrier may be a transmissible carrier such as an electrical or optical signal which may be conveyed via electrical or optical cable or by radio or by other means. When the program is embodied in a signal which may be conveyed directly by a cable or other device or means, the carrier may be constituted by such cable or device or means. Alternatively, the carrier may be an integrated circuit in which the prog- ram is embedded, the integrated circuit being adapted for performing , or for use in the performance of, the relevant processes.
Although the invention is advantageous in connection with cow milking , the invention is equally well adapted for implementation in milking machines for any other kind of mammals, such as goats , sheep or buffaloes.
The term "comprises/comprising" when used in this specification is taken to specify the presence of stated features, integers, steps or components. However, the term does not preclude the presence or addition of one or more additional features, integers, steps or components or groups thereof.
The invention is not restricted to the described embodiments in the figures, but may be varied freely within the scope of the claims.

Claims

Claims
1 . A ceil counter unit (130) for determining a quality parameter (Qcc) reflecting a somatic cell concentration in milk extracted from a milking animal (A), comprising :
a cavity (225) configured to temporarily store a milk sample from said animal (A), and
image registration means (227) configured to capture image data (Dimg) representing milk contained in the cavity (225), and
a processor means (230) configured to determine the quality parameter (Qcc) based on the image data (Dimg),
characterized in that the cell counter unit (130) comprises pressure control means (330) configured to vary a pressure level in the cavity (225), and
the image registration means (227) is configured to, for each milk sample: capture a first image (Dimg1 ) representing the milk sample in the cavity (225) at a first pressure level, and capture a second image (Dimg2) representing the milk sample in the cavity (225) at a second pressure level different from said first pressure level , and
the processor means (230) is configured to correlate image data in the first image (Dimg1 ) with image data in the second image (Dimg2), and based thereon discriminate any gas bubbles from somatic cells the milk sample.
2. The cell counter unit (130) according to claim 1 , wherein the processor means (230) is configured to discriminate any gas bubbles from somatic cells in the milk sample based on a size difference between at least one image element (de1 1 , de21 , de31 , de41 , de51 ) in the first image (Dimg1 ) and at least one respective corresponding image element (de 12, de22, de32, de42; de52) in the second image (Dimg2).
3. The cell counter unit (130) according to claim 2, wherein the second pressure level is lower than the first pressure level, and the processor means (230) is configured to discriminate a gas bubble as an image element (de1 1 -de12, de21 -de22, de31 - de32, de41 -de42; de51 -de52) being larger in the second image (Djmg2) than in the first image (Dimg1 ).
4. The cell counter unit (130) according to claim 2, wherein the second pressure level is higher than the first pressure level, and the processor means (230) is configured to discriminate a gas bubble as an image element being smaller in the second image (Dimg2) than in the first image (Djmg1 ).
5. A method for determining a quality parameter (Qcc) reflecting a somatic ceil concentration in milk extracted from a milking animal (A), comprising:
storing temporarily a milk sample from said animal (A) in a cavity (225), and
registering image data (Dimg) representing milk contained in the cavity (225), and
determining the quality parameter (Qcc) based on the image data (Dimg),
characterized by the steps
receiving a milk sample in the cavity (225);
capturing a first image (Dimg 1 ) representing the milk sample in the cavity (225) when the milk therein attains a first pressure level;
assigning a second pressure level to the milk sample in the cavity (225), the second pressure level being different from the first pressure level;
capturing a second image (Dimg2) representing the milk sample in the cavity (225) when the milk therein attains the second pressure level;
correlating image data in the first image (Dimg 1 ) with image data in the second image (Dimg2); and based thereon
discriminating any gas bubbles from somatic cells the milk sample.
6. The method according to claim 5, comprising discriminating any gas bubbles from somatic cells the milk sample based on a size difference between at least one image element (de1 , de21 , de31 , de41 , de51 ) in the first image (Dirng1 ) at least one respective corresponding image element (del 2, de22, de32, de42; de52) in the second image (Dimg2),
7. The method according to claim 6, wherein the second pressure level is lower than the first pressure level, and the method comprises discriminating a gas bubble as an image ele- ment (de1 1 -de12, de21 -de22, de31 -de32, de41 -de42; de51 - de52) being larger in the second image (Dimg2) than in the first image (Dimg1 ).
8. The method according to claim 6, wherein the second pressure level is higher than the first pressure level, and the method comprises discriminating a gas bubble as an image element being smaller in the second image {Dimg2) than in the first image (Dimg1 ).
9. A computer program loadable into the memory (M) of a computer, comprising software for controlling the steps of any of the claims 5 to 8 when said program is run on the computer.
10. A computer readable medium (M), having a program recorded thereon, where the program is to make a computer control the steps of any of the claims 5 to 8 when the program is loaded into the computer.
EP11724303A 2010-05-20 2011-05-11 Automatic determination of milk quality Withdrawn EP2572181A1 (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US34658910P 2010-05-20 2010-05-20
SE1050503 2010-05-20
PCT/SE2011/050597 WO2011146001A1 (en) 2010-05-20 2011-05-11 Automatic determination of milk quality

Publications (1)

Publication Number Publication Date
EP2572181A1 true EP2572181A1 (en) 2013-03-27

Family

ID=44390772

Family Applications (1)

Application Number Title Priority Date Filing Date
EP11724303A Withdrawn EP2572181A1 (en) 2010-05-20 2011-05-11 Automatic determination of milk quality

Country Status (2)

Country Link
EP (1) EP2572181A1 (en)
WO (1) WO2011146001A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105303568A (en) * 2015-10-15 2016-02-03 陕西科技大学 Method for counting somatic cells of milk based on image processing

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4164137A (en) * 1978-06-02 1979-08-14 Clark Equipment Company Method of measuring volume of air entrained in hydraulic fluids
SU1099907A1 (en) * 1983-02-08 1984-06-30 Оренбургский Ордена Трудового Красного Знамени Сельскохозяйственный Институт Milk sampler for analysis
JPH07270398A (en) * 1994-03-30 1995-10-20 Snow Brand Milk Prod Co Ltd Method and apparatus for measuring content of air in plastic oils and fats
US7162971B2 (en) * 2002-12-19 2007-01-16 Lattec I/S Milk conveyer device
RU2264171C1 (en) * 2004-03-22 2005-11-20 Институт клеточного внутриклеточного симбиоза УрО РАН Method for predicting subclinical mastitis form of microbial etiology in cows
RU2311759C2 (en) * 2005-09-19 2007-12-10 Государственное научное учреждение Институт экспериментальной ветеринарии Сибири и Дальнего Востока Сибирского отделения Россельхозакадемии (ГНУ ИЭВСиДВ СО РАСХН) Method and device for predicting subclinical mastitis in cows
SE530500C2 (en) * 2006-11-16 2008-06-24 Delaval Holding Ab Device and method for sampling milk

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of WO2011146001A1 *

Also Published As

Publication number Publication date
WO2011146001A1 (en) 2011-11-24

Similar Documents

Publication Publication Date Title
US8191507B2 (en) Automatic monitoring of milking plant valve means
EP1703788B1 (en) Apparatus and method for cleaning and pre-milking a teat of a milking animal
US8794182B2 (en) System and a method for controlling an automatic milking system
US7240635B2 (en) Device and a method for sampling of milk
US6705248B2 (en) Device and method for milking animals, and a contamination meter
EP2089688B1 (en) A device and a method for sampling of milk
US11733160B2 (en) Methods and systems for assessing a health state of a lactating mammal
DK177925B1 (en) Method and apparatus for quality determination of milk produced by machine milking
WO2013081534A1 (en) Milking system and method for cleaning in a milking system
EP2572181A1 (en) Automatic determination of milk quality
US8573155B2 (en) Milking system
WO2008093344A1 (en) System for detecting particles in a dairy fluid such as milk
WO2017065708A1 (en) On-line automatic subclinical mastitis detection device based on optical scattering and an automatic milk sampling system comprising this device
US20240074400A1 (en) Quality sensor, computer-implemented method of predicting inhomogeneities in milk extracted from an animal, computer program and non-volatile data carrier
KR102266731B1 (en) the mastitis diagnosis method of the livestock animals and diagnostic device thereof
NL1035925C (en) Determination of infectious condition in a milk gland during milking.
WO2022008576A1 (en) Detection of clinical mastitis in dairy mammals
CN113825395A (en) System and method for measuring key features of a rotary milking parlor arrangement, computer program and non-volatile data carrier
WO2006045759A1 (en) Method and device for the line monitoring of the health status of a teat of dairy females and/or the health status of the milk produced therefrom
SE516916C2 (en) Method and apparatus for detecting aberrant behavior in a dairy animal

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20121120

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

DAX Request for extension of the european patent (deleted)
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN WITHDRAWN

18W Application withdrawn

Effective date: 20131025