WO2015045012A1 - コロニー検査プログラム、コロニー検査装置およびコロニー検査方法 - Google Patents
コロニー検査プログラム、コロニー検査装置およびコロニー検査方法 Download PDFInfo
- Publication number
- WO2015045012A1 WO2015045012A1 PCT/JP2013/075778 JP2013075778W WO2015045012A1 WO 2015045012 A1 WO2015045012 A1 WO 2015045012A1 JP 2013075778 W JP2013075778 W JP 2013075778W WO 2015045012 A1 WO2015045012 A1 WO 2015045012A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- colony
- alarm
- inspection
- similarity
- Prior art date
Links
Images
Classifications
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12M—APPARATUS FOR ENZYMOLOGY OR MICROBIOLOGY; APPARATUS FOR CULTURING MICROORGANISMS FOR PRODUCING BIOMASS, FOR GROWING CELLS OR FOR OBTAINING FERMENTATION OR METABOLIC PRODUCTS, i.e. BIOREACTORS OR FERMENTERS
- C12M41/00—Means for regulation, monitoring, measurement or control, e.g. flow regulation
- C12M41/30—Means for regulation, monitoring, measurement or control, e.g. flow regulation of concentration
- C12M41/36—Means for regulation, monitoring, measurement or control, e.g. flow regulation of concentration of biomass, e.g. colony counters or by turbidity measurements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
Definitions
- the present invention relates to a colony inspection program, a colony inspection apparatus, and a colony inspection method.
- inspection quality inspections may be conducted to check whether hygiene inspections are performed accurately.
- inspection quality surveys for example, in order to check whether there are any problems with the procedures, testing equipment, and reagents used every day in the laboratory, a sample for investigation is selected and measured for a certain period or every certain number of tests. There is a case.
- inspection quality may be confirmed in daily hygiene inspection operations. There is a device that automatically counts the number of colonies from an image of a petri dish.
- the inspection quality itself can be investigated in addition to the hygiene inspection.
- the number of colonies should be equal between a plurality of petri dishes created under the same conditions for the same specimen. Therefore, if the difference in the number of colonies between a plurality of petri dishes prepared under the same conditions for the same sample handled in the hygiene test is within a certain range, it can be determined that there is no problem in the quality of the hygiene test.
- the inspection quality cannot be properly evaluated.
- an object of the present invention is to provide a colony inspection program, a colony inspection apparatus, and a colony inspection method that can appropriately evaluate inspection quality.
- the colony inspection program acquires images taken for each of a plurality of petri dishes containing bacterial colonies in a computer, and executes a process of calculating similarity between the plurality of images. Furthermore, the colony inspection program causes the computer to execute a process for controlling whether or not to output an alarm based on the calculated similarity.
- FIG. 1 is a diagram illustrating a configuration of the entire system according to the first embodiment.
- FIG. 2 is a functional block diagram illustrating the configuration of the colony inspection apparatus according to the first embodiment.
- FIG. 3 is a diagram illustrating an example of the data structure of the inspection DB.
- FIG. 4 is a diagram showing a first example of a color histogram.
- FIG. 5 is a diagram showing a second example of the color histogram.
- FIG. 6 is a diagram showing a first example of a colony area distribution histogram.
- FIG. 7 is a diagram illustrating a second example of a colony area distribution histogram.
- FIG. 8 is a diagram showing a first example of alarm display on the determination screen.
- FIG. 1 is a diagram illustrating a configuration of the entire system according to the first embodiment.
- FIG. 2 is a functional block diagram illustrating the configuration of the colony inspection apparatus according to the first embodiment.
- FIG. 3 is a diagram illustrating an example of the
- FIG. 9 is a diagram showing a second example of alarm display on the determination screen.
- FIG. 10 is a diagram illustrating an example of a processing matrix of the colony inspection apparatus.
- FIG. 11 is a diagram illustrating a first example of a processing operation until the colony inspection apparatus outputs an alarm.
- FIG. 12 is a diagram illustrating a second example of the processing operation until the colony inspection apparatus outputs an alarm.
- FIG. 13 is a diagram illustrating a third example of the processing operation until the colony inspection apparatus outputs an alarm.
- FIG. 14 is a diagram illustrating an example of a hardware configuration of a computer according to the colony inspection apparatus.
- FIG. 1 is a diagram illustrating a configuration of the entire system according to the first embodiment.
- the system 10 includes imaging devices 200a to 200c, terminal devices 300a to 300c, a network 50, and a colony inspection device 100.
- the imaging device 200a is connected to the terminal device 300a.
- the imaging device 200b is connected to the terminal device 300b.
- the imaging device 200c is connected to the terminal device 300c.
- a petri dish image captured by each imaging device is referred to as a petri dish image.
- Each imaging device 200 captures an image of the installed petri dish and transmits the image data to each terminal device 300.
- the terminal device 300 transmits image data to the colony inspection device 100 via the network 50.
- the colony inspection apparatus 100 determines whether the petri dish is deficient in the inspection process based on the image data transmitted from each terminal apparatus 300.
- the colony inspection apparatus 100 outputs an alarm when it is determined that the petri dish is likely to be defective.
- each imaging apparatus 200 captures a petri dish image, and the colony inspection apparatus 100 counts the number of colonies from the petri dish image.
- each terminal apparatus 300 calculates the number of colonies based on the petri dish image. You may count. Details regarding the process in which the colony inspection apparatus 100 outputs an alarm will be described later.
- the inspection department is a department that conducts a hygiene inspection in a food manufacturing factory. Inspectors who belong to the inspection department carry out hygiene inspections. On the other hand, the person in charge who belongs to the inspection department makes a final judgment on the hygiene inspection performed by the inspector and evaluates the quality of the hygiene inspection performed by the inspector.
- the inspector of the inspection department collects a sample from the food and prepares a petri dish by a predetermined method in order to perform a hygiene inspection on the food to be shipped.
- an inspector creates a petri dish as follows. First, the inspector attaches an inspection number, which is an identification number for distinguishing the sample collected from the food to be inspected from other samples. Next, the same number as the examination number assigned to the sample is entered on the lids of the two petri dishes. Next, the inspector grinds the specimen and adds dilution water to create a sample stock solution. A part of the sample stock solution is extracted with a dropper, added to two petri dishes, and further diluted with diluted water to prepare a single dish of two petri dishes. Next, the inspector pours a medium such as agar into the petri dish and pours it in the petri dish.
- an inspection number which is an identification number for distinguishing the sample collected from the food to be inspected from other samples.
- the same number as the examination number assigned to the sample is entered on the lids of the two petri dishes.
- the inspector grinds the specimen and adds dilution water to create a sample stock solution. A part of the sample stock solution is extracted with
- the inspector turns the lid aside down after the agar has solidified, keeps the temperature in the two petri dishes at a predetermined temperature with an incubator, and leaves each petri dish for about 1 to 2 days. Thereby, the same specimen is cultured in two petri dishes under the same conditions. Some samples collected from food are stored frozen for retesting. Next, the inspector installs the generated petri dish in each imaging device 200.
- two petri dishes having the same dilution stage are prepared from the beginning. However, two petri dishes having two or three consecutive dilution stages are prepared, and one appropriate dilution stage is selected. You may count the number of colonies.
- the colony counting operation is generally performed visually.
- the inspector in order for the inspector to perform counting work with high accuracy, the inspector needs some practical experience. For this reason, the inspection department cannot request counting work to an inspector who does not have sufficient work experience.
- the inspection department since the inspection department needs to perform regular work with a limited number of inspectors, it is difficult for an inspector with experience in inspection to communicate the know-how of counting work to other inspectors.
- the inspection department has a problem that it is difficult to keep the inspection level constant in the counting work because there is an error in counting due to the difference in practical experience of each inspector. Under such circumstances, when the inspection department causes the inspector to visually count the work, it is difficult to keep the work quality constant.
- FIG. 2 is a functional block diagram illustrating the configuration of the colony inspection apparatus according to the first embodiment.
- the colony inspection apparatus 100 includes an I / F (Interface) 101, a display unit 102, a control unit 110, and a storage unit 120.
- the I / F 101 is a communication interface that is connected to the network 50 and transmits data to each terminal device 300 via the network 50.
- the display part 102 displays the processing result made by the colony inspection apparatus 100 on a monitor.
- the display unit 102 displays an alarm output from the colony inspection apparatus 100.
- the storage unit 120 stores an inspection DB (Database) 121, image data 122, image feature data 123, and threshold data 124.
- the storage unit 120 corresponds to, for example, a semiconductor memory device such as a random access memory (RAM), a read only memory (ROM), or a flash memory, and a storage device such as a hard disk or an optical disk.
- the inspection DB 121 is a database for storing data relating to inspection, similarity between petri dish images, and determination results in association with each inspection.
- FIG. 3 is a diagram illustrating an example of the data structure of the inspection DB.
- the examination DB 121 includes examination No, specimen 1, specimen 2, examination date, specimen name, cfu, dilution rate, count number 1, count number 2, and similarity. And the determination result are associated with each other.
- “Examination No” is a number uniquely assigned to each specimen on the examination date.
- One “examination No” is assigned to a group of specimens generated from the same petri dish.
- Sample 1 represents an image of one sample 1 of a plurality of two samples generated from the same petri dish.
- Sample 2 indicates an image of the other sample 2 of a plurality of two samples generated from the same petri dish.
- Inspection date indicates the date on which the inspection was performed.
- Sample name indicates the name of the food from which the sample was collected.
- Cfu indicates the number of bacteria per gram of the specimen.
- Deution ratio indicates the ratio at which the original solution was diluted.
- Counter number 1 indicates the number of colonies included in the sample 1.
- Counter number 2 indicates the number of colonies included in the sample 2.
- Similarity indicates the similarity between images related to the specimen 1 and the specimen 2. “Similarity” is indicated by 0 to 1, and is 1 when the images to be compared are the same.
- the “determination result” indicates a result determined by the person in charge.
- the “judgment result” is “within the regulation” when the responsible person determines that the cfu counted by the inspector is within the prescribed value determined for each food group. Further, the “judgment result” is “out of regulation” when the responsible person judges that it exceeds the prescribed value determined for each food group.
- the “determination result” is “LA (Laboratory Accident)” when the person in charge determines that there is a problem in the inspection quality.
- the image data 122 is petri dish data received from each terminal device 300.
- the colony testing apparatus 100 stores image data relating to two petri dishes created by dividing a specimen to be examined in association with the examination DB 121 as image data 122.
- the file format of the image data 122 is, for example, a GIF file, JPEG file, BMP file, or the like.
- the image feature amount data 123 is data related to the image feature amount of each corresponding petri dish image.
- the colony inspection apparatus 100 acquires the image feature amount data 123 by various methods. For example, the colony inspection apparatus 100 creates a color histogram corresponding to each petri dish image. Then, the colony inspection device 100 stores the created color histogram in the storage unit 120 as the image feature amount data 123. Moreover, the colony inspection apparatus 100 calculates the average value of the area of a colony based on a petri dish image. Then, the colony inspection device 100 stores the average value of the colony area in the storage unit 120 as the image feature amount data 123.
- the colony inspection apparatus 100 calculates the SIFT (Scale-Invariant Feature Transform) feature amount of each petri dish image. Then, the colony inspection apparatus 100 stores the SIFT feature amount in the storage unit 120 as the image feature amount data 123. Note that the colony inspection apparatus 100 may calculate the image feature amount by SURF (Speed Up Robust Features) or HOG (Histogram of Oriented Gradients). The above is an example of the image feature amount calculated by the colony inspection apparatus 100, and the colony inspection apparatus 100 may calculate the image feature amount by another method. Details regarding the calculation of the image feature amount will be described later.
- SIFT Scale-Invariant Feature Transform
- the threshold data 124 is data indicating each threshold used when the colony inspection apparatus 100 determines whether or not to output an alarm. As will be described later, the colony inspection apparatus 100 calculates the similarity between corresponding petri dish images, and determines whether to output an alarm based on whether the similarity is equal to or greater than a threshold value. For example, the colony inspection apparatus 100 sets the threshold to “0.6” based on the threshold data 124 when comparing petri dishes of vegetables. Note that the colony inspection apparatus 100 may appropriately update the threshold based on feedback from the person in charge. Details of the threshold update will be described later.
- the control unit 110 includes an acquisition unit 111, a counting unit 112, a calculation unit 113, and a determination unit 114.
- the function of the control unit 110 can be realized, for example, by a CPU (Central Processing Unit) executing a predetermined program.
- the function of the control part 110 is realizable by integrated circuits, such as ASIC (Application Specific Integrated Circuit) and FPGA (Field Programmable Gate Array), for example.
- the determination unit 114 is an example of an output unit.
- the acquisition unit 111 acquires count data from each terminal device 300 via the I / F 101 and stores it in the storage unit 120. For example, the acquisition unit 111 receives, from each terminal device 300, two petri dish images created by dividing a specimen to be examined. Next, the acquisition unit 111 stores two corresponding petri dish images in the inspection DB 121 in association with one inspection number. In addition, the acquisition unit 111 receives data on the examination date, sample name, cfu, and dilution factor for each examination from each terminal device 300, and stores these in association with the same examination number.
- the counting unit 112 counts the number of colonies included in the petri dish based on each petri image stored as the image data 122. Further, the counting unit 112 calculates an image feature amount of each petri dish image. For example, the counting unit 112 counts the number of colonies included in the petri dish based on the petri image received from each terminal device 300. Next, the counting unit 112 inserts the number of colonies of the image 1 into the “count number 1” of the examination DB 121 when the image of one petri dish created from the same sample is the image 1 and the other is the image 2. Insert the number of colonies of 2 into “Count 2”. In addition, when the colonies in the petri dish overlap, the counting unit 112 may separate and count the colonies by image processing.
- the counting unit 112 calculates a color histogram, an average value of a colony area, a SIFT feature amount, or the like as the image feature amount of the image 1 and the image 2. For example, when obtaining the color histogram as the image feature amount of the image 1 and the image 2, the counting unit 112 performs the following process. First, the counting unit 112 reduces the color components of the red component R, the green component G, and the blue component B of each pixel included in the image 1 and the image 2 to four colors, and the red component R, the green component G, and the blue component B. There are 64 combinations. Next, the counting unit 112 assigns numbers from 0 to 63 to the 64 colors corresponding to the bin numbers. Next, the counting unit 112 counts how many pixels corresponding to the bin number are included in the image 1 and the image 2, and creates a color histogram.
- FIG. 4 is a diagram showing a first example of a color histogram.
- the color histogram represents the number of pixels corresponding to the bin numbers from 0 to 63 in the image 1. For example, the color histogram indicates that there are approximately 5000 pixels with bin number 0 in image 1. In addition, the color histogram indicates that there are approximately 25,000 pixels with bin number 10 in image 1. The color histogram indicates that there are about 1000 pixels with bin number 20 in image 1. The color histogram indicates the number of pixels corresponding to each bin number in the other bin numbers in the image 1.
- FIG. 5 is a diagram showing a second example of the color histogram.
- the color histogram represents the number of pixels for the bin numbers from 0 to 63 in the image 2 as in FIG.
- the color histogram indicates that there are approximately 4000 bin number 0 pixels in image 2.
- the color histogram indicates that there are about 23000 pixels with bin number 10 in the image 2.
- the color histogram shows that there are about 2000 pixels with bin number 20 in image 2.
- the color histogram indicates the number of pixels corresponding to each bin number in the other bin numbers in the image 2.
- the counting unit 112 stores the color histogram related to the image 1 in FIG. 4 and the color histogram related to the image 2 in FIG. 5 in the storage unit 120 as the image feature amount data 123, respectively.
- the calculation of similarity using a color histogram will be described later.
- the histogram created by the counting unit 112 is not limited to a color histogram, and other histograms may be created.
- the counting unit 112 may create a colony area distribution histogram by the following procedure. First, the counting unit 112 performs an edge extraction process on the image 1 and detects a closed portion as a colony. Next, the counting unit 112 calculates the area of each colony included in the image 1. The counting unit 112 calculates the area of each colony included in the image 2 in the same manner.
- the counting unit 112 divides the colonies in the image 1 into N stages according to the size of the area, and counts the number of colonies belonging to each stage. For example, when the colony area is divided into seven stages, the counting unit 112 counts the number of colonies belonging to the smallest area in the first stage. In addition, the counting unit 112 counts the number of colonies that belong to the next smallest area in the second stage. In this way, the counting unit 112 counts the number of colonies belonging to each stage. Next, the counting unit 112 creates a distribution histogram of the colony area of the image 1 by taking the number of colonies on the vertical axis and the area of the colonies on the horizontal axis. Note that the counting unit 112 similarly creates a colony area distribution histogram of the image 2.
- FIG. 6 is a diagram showing a first example of a distribution histogram of colony areas.
- the colony area distribution histogram shown in FIG. The colony area distribution histogram takes the number of colonies in the vertical axis direction and the colony area in the horizontal axis direction.
- the colony area distribution histogram divides the colony area into seven stages and indicates the number of colonies in each stage. For example, the colony area distribution histogram shows that the number of colonies in the first stage is about 30.
- the colony area distribution histogram shows that the number of colonies in the second stage is about 23.
- the colony area distribution histogram indicates the number of colonies belonging to other stages.
- FIG. 7 is a diagram showing a second example of a distribution histogram of colony areas. The colony area distribution histogram shown in FIG. The calculation of similarity using a colony area distribution histogram will be described later.
- the counting unit 112 may calculate the image feature amount by another method.
- the counting unit 112 may calculate the average value of the colony area as the image feature amount data.
- the counting unit 112 performs edge extraction processing of the image 1 and the image 2 and detects a closed portion as a colony.
- the counting unit 112 may detect the colony based on the area, color, size, and the like of the closed portion.
- the counting unit 112 calculates the total area of the colonies by counting the number of pixels of each detected colony.
- the counting unit 112 obtains the average value of the colony areas by dividing the total area of the colonies by the number of colonies.
- the counting unit 112 stores the average value of the colony area in the storage unit 120 as the image feature amount data 123.
- the counting unit 112 may calculate SIFT feature amounts of the image 1 and the image 2 and store them in the storage unit 120 as the image feature amount data 123.
- SIFT is an algorithm used for object recognition and the like, and is said to be resistant to image rotation, enlargement / reduction, and illumination change.
- the counting unit 112 obtains a SIFT feature value by detecting a feature point from the image and calculating a luminance change for each feature point. Then, the counting unit 112 causes the storage unit 120 to store the obtained SIFT feature amounts as the image feature amount data 123.
- the calculation unit 113 calculates the similarity between the corresponding petri dish images based on the image feature quantity related to each petri dish image stored as the image feature quantity data 123. For example, when the counting unit 112 calculates the color histograms of the image 1 and the image 2 as the image feature amount, the calculation unit 113 compares the histograms according to the following procedure using a method called Histogram Intersection. The value of each bin number indicates the number of pixels corresponding to each bin number. First, the calculation unit 113 compares the value of bin number 0 in the color histograms of image 1 and image 2 and adds the smaller value to the total value.
- calculation unit 113 adds the smaller “4000” to total value “0”.
- the total value is “4000”.
- calculation unit 113 adds the smaller “1500” to the total value “4000”.
- the total value is “5500”.
- calculation unit 113 adds the smaller “1000” to the total value “5500”.
- the total value is “6500”.
- calculation unit 113 similarly calculates the total value by adding the smaller value up to the bin number 3-63 to the total value. Further, the calculation unit 113 similarly calculates the total value X1 for the image 2 as well.
- the total value X1 calculated by the calculation unit 113 is expressed by the following equation when the bin number i of image 1 is H1 [i] and the bin number i of image 2 is H2 [i]. Can do.
- the calculation unit 113 calculates the similarity X2 expressed in the range of 0 to 1 by dividing the obtained total value by the total number of pixels of the image 1 or the image 2. That is, the similarity degree X2 can be expressed by the following equation when the bin number i of image 1 is H1 [i] and the bin number i of image 2 is H2 [i].
- the calculation unit 113 may compare the histograms by other methods.
- the calculation unit 113 may compare the histograms with the Bhattacharyya distance according to the following procedure.
- the counting unit 112 normalizes the value of each bin number of the histogram of the image 1 by dividing it by the total number of pixels of the image 1. Thereby, the histogram of the image 1 is expressed by the appearance probability distribution.
- the counting unit 112 expresses the histogram of the image 2 as an appearance probability distribution by the same procedure.
- the calculation unit 113 sets the sum of the square root of the products of the appearance probabilities in the image 1 and the image 2 as the similarity X3 between the image 1 and the image 2 for each bin number.
- the similarity has a value of 0 to 1. That is, in this case, the similarity degree X3 can be expressed by the following equation when the appearance probability of the bin number i of the image 1 is p [i] and the appearance probability of the bin number i of the image 2 is q [i]. it can.
- the calculation unit 113 may calculate the similarity according to the following procedure. First, the calculation unit 113 compares the values in the first stage in the colony area histograms of the image 1 and the image 2 and adds the smaller value to the total value. Next, the calculation unit 113 compares the second-stage values in the colony area histograms of the image 1 and the image 2 and adds the smaller value to the total value. The calculating unit 113 calculates the total value by repeating the above calculation up to the seventh stage, which is the largest range of the colony area.
- the calculation unit 113 calculates the similarity X4 between the image 1 and the image 2 by dividing the calculated total value by the total number of colonies of the image 1 or the image 2. That is, in this case, the similarity degree X4 can be expressed by the following equation when the number of colonies at the i-th stage of image 1 is H1 [i] and the number of colonies at the i-th stage of image 2 is H2 [i]. it can.
- the calculation unit 113 may calculate the similarity based on the average value of the area of the colonies of the image 1 and the image 2. For example, the calculation unit 113 calculates the similarity by dividing the image 1 having a small average colony area by the image 2 having a large average value. The similarity is considered to be close to 1 when the same kind of colonies exist in two petri dishes.
- the calculation unit 113 may calculate the similarity based on the SIFT feature amounts of the image 1 and the image 2. For example, the calculation unit 113 generates feature vectors from the SIFT feature amounts of the image 1 and the image 2, and calculates the similarity based on the comparison of the feature vectors.
- the determination unit 114 determines whether the inspection quality is low based on the difference in the number of colonies between the petri dishes and the similarity between the petri images.
- the determination unit 114 outputs an alarm when it is determined that the inspection quality is low. For example, when the difference in the number of colonies between the petri dishes is equal to or greater than the threshold value, the determination unit 114 determines that the petri dish to be inspected is defective in the inspection process, and outputs an alarm. Further, when the similarity between the petri images is equal to or less than the threshold value, the determination unit 114 determines that the petri dish to be inspected is defective in the inspection process, and outputs an alarm.
- the determination unit 114 determines that the petri dish to be inspected is deficient in the inspection process, there is a high possibility that the petri dish has deficiencies in the inspection process on the screen on which the responsible person determines the inspection result. Display an alarm to this effect.
- the threshold is set for each food group and inspection item. Details regarding the display on the determination screen will be described later.
- the determination unit 114 outputs an alarm when the count of the number of colonies between petri dishes is different by “7” or more, or when the similarity between petri images is “0.6” or less.
- the determination unit 114 determines that the alarm condition is satisfied because the similarity is “0.55” and the similarity is “0.6” or less in the inspection No. “105” of the inspection DB 121 of FIG. Output an alarm.
- the determination unit 114 determines that the condition of the alarm is satisfied because the difference between the count number 1 and the count number 2 is “12” and “7” or more in the inspection number “106”, and an alarm is displayed on the determination screen 400. Output.
- the difference between the count number 1 and the count number 2 is “1”, the count number is smaller than “7”, the similarity is “0.71”, and the similarity is larger than “0.6”. It is determined that the alarm condition is not satisfied, and no alarm is output on the determination screen 400. Further, the determination unit 114 determines that the condition of the alarm is satisfied because the similarity is “0.55” and the similarity is “0.6” or less in the inspection No. “109”, and outputs an alarm on the determination screen 400. The alarm output when the inspection number is “107” will be described later.
- the determination unit 114 may determine whether or not to output an alarm based on a count ratio of the number of colonies between petri dishes. For example, the determination unit 114 may output an alarm when the count ratio of the number of colonies between petri dishes is four times or more, or when the similarity between petri images is “0.6” or less. In this case, when the count number 1 is “4” and the count number 2 is “17”, the determination unit 114 determines that the alarm condition is satisfied because the count number 2 is four times or more than the count number 1. An alarm is output to the determination screen 400. On the other hand, the determination unit 114 determines that the alarm condition is not satisfied when the count number 1 is “4”, the count number 2 is “15”, and the similarity between petri images is larger than “0.6”. No alarm is output on the screen 400.
- FIG. 8 is a diagram showing a first example of alarm display on the determination screen.
- FIG. 9 is a diagram showing a second example of alarm display on the determination screen.
- FIG. 8 corresponds to the display of the image 1 related to the inspection No. “105” in FIG.
- FIG. 9 corresponds to the display of the image 2 related to the inspection No. “105” in FIG.
- the determination screen 400 displays the petri dish image related to the image 1 on the image display unit 401a as illustrated in FIG.
- the determination screen 400 displays the petri dish image related to the image 2 on the image display unit 401b as illustrated in FIG.
- the display unit 102 displays “examination No”, “examination date”, “sample name”, “cfu”, “dilution rate”, and “count number 1” in the examination information display column 410 of the determination screen 400. And “count number 2” are displayed. Further, when the determination unit 114 determines that there is a high possibility that there is a defect in the inspection process, the display unit 102 displays an alarm display unit 411 in the inspection information display column 410 as illustrated in FIGS. 8 and 9. An alarm indicating that there may be a problem with the inspection quality is displayed.
- the display unit 102 has an in-regulation button 421, a non-regulation button 422, an L.P. A.
- a button 423 and a confirmation button 430 are displayed.
- the colony inspection apparatus 100 causes the inspection DB 121 to store in the inspection DB 121 a determination result indicating “internal” when the in-regulation button 421 is pressed by the person in charge of the inspection department and the confirmation button 430 is further pressed. Further, the colony inspection apparatus 100 stores the determination result of “non-standard” in the inspection DB 121 when the non-standard button 422 is pressed by the person in charge of the inspection department and the confirmation button 430 is pressed. In addition, the colony inspection apparatus 100 is operated by the person in charge of the inspection department. A. When the button 423 is pressed and the confirm button 430 is pressed, the determination result indicating “L.A.” is stored in the examination DB 121.
- the examination department determines that the number of colonies of the examined sample is within the prescribed value. In addition, if the result of the determination is “Not Specified”, the testing department determines that the number of colonies of the tested sample exceeds the specified value, and immediately requests the inspection request source such as the manufacturing plant line. Make a report. In addition, if the determination result is “LA”, the inspection department determines that the inspection is necessary again, and notifies the inspector that the petri dish should be prepared again using the same specimen that has been stored frozen. . In addition, instruct the inspector to improve the inspection work.
- the colony inspection apparatus 100 is useful for determining whether or not there is a problem in the inspection quality by outputting an alarm on the determination screen 400 when there is a high possibility that there is a defect in the inspection process.
- Information can be provided.
- the display unit 102 is not limited to outputting an alarm on the determination screen 400, and may output an alarm by displaying a pop-up.
- the colony inspection apparatus 100 may output an alarm by sending an email to the person in charge.
- FIG. 10 is a diagram illustrating an example of a processing matrix of the colony inspection apparatus.
- the determination unit 114 determines that there is a high possibility that there is a defect in the inspection process in either petri dish. In this case, the display unit 102 outputs an alarm on the determination screen 400.
- the determination unit 114 determines that there is no problem in the inspection quality when the difference in the number of colonies between the petri dishes is within the threshold and the similarity between the petri images is equal to or greater than the threshold. In this case, the display unit 102 does not output an alarm on the determination screen 400. In addition, when the difference in the number of colonies between petri dishes is within the threshold value and the similarity between the petri dish images is less than or equal to the threshold value, the determination unit 114 predicts that the development status of the number of colonies is different. It is determined that there is a high possibility that the inspection process was defective. In this case, the display unit 102 outputs an alarm on the determination screen 400.
- FIG. 11 is a diagram illustrating a first example of a processing operation until the colony inspection apparatus outputs an alarm.
- the acquisition unit 111 divides one specimen into two petri dishes at the same dilution ratio, and then acquires images related to two petri dishes created by culturing each specimen in the same environment (step S10). ).
- the acquisition unit 111 stores two corresponding petri dish images in the inspection DB 121 in association with one inspection number.
- the counting unit 112 calculates the number of colonies from each corresponding petri dish stored in the inspection DB 121 (step S11).
- the counting unit 112 calculates image feature amounts from the corresponding two petri dish images (step S12). For example, the counting unit 112 calculates color histograms of two petri dish images as image feature amounts.
- the counting unit 112 stores the calculated image feature amount in the storage unit 120 as the image feature amount data 123.
- the calculation unit 113 calculates the similarity between the two petri images (step S13). For example, the calculation unit 113 compares the values at the bin numbers of the color histograms corresponding to the two petri dish images, and adds the smaller values at the bin numbers to obtain a total value. Then, the calculation unit 113 calculates the similarity by dividing the obtained total value by the total number of pixels of one of the two petri dish images.
- Step S16 when the difference in the number of colonies between petri dishes counted by the counting unit 112 is greater than or equal to the threshold value M (Yes at Step S14), the determination unit 114 outputs an alarm (Step S16) and ends the process. On the other hand, when the difference in the number of colonies between petri dishes counted by the counting unit 112 is smaller than the threshold M (No in step S14), the determination unit 114 proceeds to the process of step S15.
- Step S16 when the image similarity is smaller than the threshold value N in Step S15 (No in Step S15), the determination unit 114 outputs an alarm (Step S16) and ends the process.
- the determination unit 114 when the image similarity is greater than or equal to the threshold value N in step S15 (Yes in step S15), the determination unit 114 does not output an alarm and ends the process.
- the colony inspection apparatus 100 includes an acquisition unit 111 that acquires images captured for each of a plurality of petri dishes including bacterial colonies, and a calculation unit 113 that calculates a similarity between the plurality of images. . Furthermore, the colony inspection apparatus 100 includes a determination unit 114 that changes whether to output an alarm based on the calculated similarity.
- the determination unit 114 outputs an alarm when the calculated similarity indicates a difference greater than or equal to a predetermined value.
- the colony inspection apparatus 100 may further include a counting unit 112 that counts the number of bacterial colonies included in each of the plurality of images. Then, the determination unit 114 alarms when the value counted for each of the plurality of images includes a difference greater than a predetermined number and when the similarity indicates a difference greater than a predetermined value. May be output.
- the colony inspection apparatus 100 can appropriately evaluate the inspection quality in consideration of factors other than the difference in the number of colonies of the corresponding two petri dish images.
- the colony inspection apparatus 100 calculates the number of colonies of each petri dish and the image feature amount of each petri image. Without being limited thereto, each terminal device 300 in FIG. 1 calculates one or both of the number of colonies of each petri dish and the image feature amount of each petri dish based on each petri image captured by the imaging device 200.
- the transmitted data may be transmitted to the colony inspection apparatus 100, and the colony inspection apparatus 100 may use the data.
- the display unit 102 outputs an alarm on the determination screen 400 when it is determined that there is a high possibility that the determination unit 114 has a defect in the process of inspecting the petri dish.
- the determination unit 114 may output an alarm by displaying a pop-up separately from the determination screen 400. Further, the determination unit 114 may output an alarm by sending a mail to the person in charge or the like.
- the counting unit 112 calculates the SIFT feature value.
- the present invention is not limited to this, and the counting unit 112 may calculate the image feature amount by SURF (Speed Up Robust Features) or HOG (Histogram of Oriented Gradients).
- the counting unit 112 calculates the color histogram, the colony area histogram, the average value of the colony area, or the SIFT feature amount as the image feature amount of the petri dish image.
- the present invention is not limited to this, and the counting unit 112 may calculate the image feature amount as follows. For example, the counting unit 112 irradiates each coordinate position of the petri dish with light including a plurality of wavelength lights, and performs Fourier transform on the transmitted light. Next, the counting unit 112 creates a matrix based on the amount of transmitted light for each wavelength at each coordinate. Next, the calculation unit 113 calculates the similarity between petri images based on the created matrix.
- the counting unit 112 calculates any one of the color histogram, the colony area histogram, the average value of the colony area, or the SIFT feature amount as the image feature amount of the petri dish image.
- the colony inspection apparatus 100 may evaluate the inspection quality as follows. For example, the counting unit 112 calculates a color histogram, a colony area histogram, an average value of the colony area, and a SIFT feature amount as the image feature amount.
- the calculation unit 113 calculates the similarity of each of the color histogram, the colony area histogram, the average value of the colony area, and the SIFT feature amount.
- the determination unit 114 determines whether or not the petri dish to be inspected is defective in the inspection process by determining whether or not all the similarities are equal to or greater than the threshold values set for each.
- the inspection department of the food manufacturing factory uses the colony inspection apparatus 100 in order to improve the inspection quality, but the colony inspection apparatus 100 is used so that the quality control department of another department audits the inspection quality in the inspection department. May be used. Further, a public organization or an external third party organization may audit the inspection in the inspection department using the colony inspection apparatus 100.
- the determination unit 114 determines whether the petri dish to be inspected is defective in the inspection process, based on whether the similarity is equal to or higher than a threshold value.
- the threshold is set for each food group and inspection item.
- the threshold value may be updated as appropriate by the person in charge.
- the colony inspection apparatus 100 may update the threshold in the following cases.
- the display unit 102 outputs an alarm when the similarity is equal to or less than a threshold value.
- the colony inspection apparatus 100 may update the threshold value to a value lower than the current value when “within regulation” is selected as the determination result by the responsible person.
- the colony inspection apparatus 100 can set a more appropriate threshold value by feeding back the determination result made by the person in charge and reflecting it in the threshold data 123 and learning the threshold value appropriately based on the determination result. .
- the determination unit 114 determines that the petri dish to be inspected is defective in the inspection process when the similarity between the petri images is equal to or less than the first threshold value. Furthermore, the determination unit 114 may determine that the petri dish images are the same when the similarity between the petri dish images is equal to or greater than a second threshold value that is greater than the first threshold value. Thereby, the colony inspection apparatus 100 can prevent the same petri dish image from being confused and displayed on the determination screen 400 due to the misunderstanding of the person in charge. Note that the colony inspection apparatus 100 may output an alarm indicating that “the displayed petri dish images may be the same” when the similarity between the petri dish images is equal to or greater than the second threshold value. Thereby, it is possible to prevent an injustice that the inspection quality is evaluated using the same petri dish image.
- the determination unit 114 outputs an alarm when the count number is different by “7” or more, or when the similarity is “0.6” or less or “0.95” or more. In this case, the determination unit 114 determines that the condition of the alarm is satisfied because the similarity is “0.99” and the similarity is “0.95” or more in the inspection No. “107” of the inspection DB 121 of FIG. An alarm is output to.
- FIG. 12 is a diagram illustrating a second example of the processing operation until the colony inspection apparatus outputs an alarm.
- the acquisition unit 111 acquires images related to two petri dishes that are divided from one specimen and cultured at the same dilution rate (step S20).
- the counting unit 112 calculates the number of colonies from each corresponding petri dish stored in the inspection DB 121 (step S21).
- the counting unit 112 calculates image feature amounts from the corresponding two petri dish images (step S22).
- the calculation unit 113 calculates the similarity between the two petri dish images (step S23).
- step S26 when the difference in the number of colonies between petri dishes counted by the counting unit 112 is greater than or equal to the threshold value M (Yes in step S24), the determination unit 114 outputs an alarm (step S26) and ends the process.
- the determination unit 114 proceeds to the process in step S25.
- the determination unit 114 outputs an alarm (step S26) and ends the process.
- step S25 Yes when the image similarity is greater than or equal to the threshold value N and less than or equal to the threshold value O in step S25 (step S25 Yes), the determination unit 114 does not output an alarm and ends the process.
- the threshold value N corresponds to the first threshold value.
- the threshold value O corresponds to the second threshold value.
- the counting unit 112 may not be able to accurately count the number of colonies when the total area of the colonies in the petri dish becomes more than half due to the reason that one colony grows extremely. Therefore, when the total area of the colonies in the petri dish calculated by the calculation unit 113 is equal to or larger than the threshold value, the determination unit 114 may output an alarm to prompt the person in charge to perform an additional inspection. Thereby, the colony test
- the counting unit 112 calculates the total area of the colony as follows. For example, the counting unit 112 performs edge extraction processing of the image 1 and the image 2 and detects a closed portion as a colony. Next, the counting unit 112 calculates the total area of the colonies by counting the number of pixels of each detected colony. Alternatively, the counting unit 112 counts the number of white pixels included in the petri image taken on a dark-colored table, and based on how much of the total number of pixels in the petri dish is white Thus, the total area of the colony may be calculated.
- FIG. 13 is a diagram illustrating a third example of the processing operation until the colony inspection apparatus outputs an alarm.
- the acquisition unit 111 acquires images related to two petri dishes that are divided from one specimen and cultured at the same dilution rate (step S30).
- the counting unit 112 calculates the number of colonies from each corresponding petri dish stored in the inspection DB 121 (step S31).
- the counting unit 112 calculates an image feature amount and a total colony area from the corresponding two petri dish images (step S32).
- the calculation unit 113 calculates the similarity between the two petri dish images (step S33).
- Step S37 when the difference in the number of colonies between petri dishes counted by the counting unit 112 is greater than or equal to the threshold value M (Yes at Step S34), the determination unit 114 outputs an alarm (Step S37) and ends the process.
- the determination unit 114 proceeds to the process of step S35.
- the determination unit 114 outputs an alarm (Step S37) and ends the process.
- step S35 if the image similarity is greater than or equal to the threshold value N in step S35 (Yes in step S35), the determination unit 114 proceeds to the process in step S36.
- the determination unit 114 outputs an alarm (step S37) and ends the process.
- the determination unit 114 does not output an alarm and ends the process.
- FIG. 14 is a diagram illustrating a hardware configuration of a computer according to the colony inspection apparatus.
- the computer 500 includes a CPU 501 that executes various arithmetic processes, an input device 502 that receives data input from a user, and a monitor 503.
- the computer 500 also includes a medium reading device 504 that reads a program or the like from a storage medium, an interface device 505 for connecting to another device, and a wireless communication device 506 for connecting to another device wirelessly.
- the computer 500 also includes a RAM (Random Access Memory) 507 that temporarily stores various information and a hard disk device 508.
- Each device 501 to 508 is connected to a bus 509.
- the hard disk device 508 stores a colony inspection program having the same functions as the processing units of the acquisition unit 111, the counting unit 112, the calculation unit 113, and the determination unit 114 of the control unit 110 illustrated in FIG.
- the hard disk device 508 stores various data for realizing a colony inspection program.
- the CPU 501 reads out each program stored in the hard disk device 508, develops it in the RAM 507, and executes it to perform various processes.
- these programs can cause the computer 500 to function as the acquisition unit 111, the counting unit 112, the calculation unit 113, and the determination unit 114 illustrated in FIG.
- the computer 500 may read and execute a program stored in a storage medium readable by the computer 500.
- the storage medium readable by the computer 500 corresponds to, for example, a portable recording medium such as a CD-ROM, a DVD disk, a USB (Universal Serial Bus) memory, a semiconductor memory such as a flash memory, a hard disk drive, and the like.
- the program may be stored in a device connected to a public line, the Internet, a LAN (Local Area Network), or the like, and the computer 500 may read and execute the program.
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Organic Chemistry (AREA)
- Zoology (AREA)
- Wood Science & Technology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Biotechnology (AREA)
- Microbiology (AREA)
- Sustainable Development (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Genetics & Genomics (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Multimedia (AREA)
- Apparatus Associated With Microorganisms And Enzymes (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Image Processing (AREA)
Abstract
Description
次に、実施例1に係るシステム全体の構成について説明する。図1は、実施例1に係るシステム全体の構成を示す図である。図1に示すように、システム10は、撮像装置200a~200cと、端末装置300a~300cと、ネットワーク50と、コロニー検査装置100とを有する。
次に、各撮像装置200に設置するシャーレの作成について説明する。検査部門は、食品製造工場で衛生検査をおこなう部門である。検査部門に所属する検査員は、衛生検査を実施する。一方、同じく検査部門に所属する責任者は、検査員が行った衛生検査の最終判定を行うとともに、検査員がおこなった衛生検査の品質を評価する。
なお、コロニー数のカウント作業は、目視でおこなうのが一般的である。ところが、検査員が精度よくカウント作業をおこなうには、検査員にある程度の実務経験が必要となる。このため、検査部門は、実務経験が十分でない検査員にカウント作業を依頼することができない。また、検査部門は限られた検査員数にて定常的に業務をこなす必要があるため、検査実務経験を有する検査員が他の検査員にカウント作業のノウハウを伝えるのは困難という事情がある。さらに、検査部門は、各検査員の実務経験の差によりカウントに誤差が出るので、カウント作業における検査レベルを一定に保つのが難しいという問題もある。このような事情により検査部門は、検査員に目視でカウント作業をさせると、作業品質を一定に保つことが困難となる。
実施例1に係るコロニー検査装置100の機能構成の一例について説明する。図2は、実施例1に係るコロニー検査装置の構成を示す機能ブロック図である。図2に示すように、コロニー検査装置100は、I/F(Interface)101と、表示部102、制御部110と、記憶部120とを有する。I/F101は、ネットワーク50に接続され、ネットワーク50を介して各端末装置300にデータを送信するための通信インターフェースである。表示部102は、コロニー検査装置100でなされた処理結果をモニタに表示する。また、表示部102は、コロニー検査装置100から出力されたアラームを表示する。
記憶部120は、検査DB(Database)121と、画像データ122と、画像特徴量データ123と、閾値データ124とを記憶する。記憶部120は、例えば、RAM(Random access Memory)、ROM(Read Only Memory)、フラッシュメモリ(Flash Memory)などの半導体メモリ素子、ハードディスクや光ディスクなどの記憶装置に対応する。
制御部110は、取得部111と、計数部112と、算出部113と、判定部114とを有する。制御部110の機能は、例えば、CPU(Central Processing Unit)が所定のプログラムを実行することで実現することができる。また、制御部110の機能は、例えば、ASIC(Application Specific Integrated Circuit)やFPGA(Field Programmable Gate Array)などの集積回路により実現することができる。なお、判定部114は、出力部の一例である。
図8は、判定画面におけるアラーム表示の第一の例を示した図である。また、図9は、判定画面におけるアラーム表示の第二の例を示した図である。図8は、図3において検査No「105」に係る画像1の表示に対応する。また、図9は、図3において検査No「105」に係る画像2の表示に対応する。判定画面400は、例えば、タブ402aが選択状態の場合に、図8に示したように画像1に係るシャーレ画像を画像表示部401aに表示する。一方、判定画面400は、タブ402bが選択状態の場合に、図9に示したように画像2に係るシャーレ画像を画像表示部401bに表示する。また、表示部102は、判定画面400の検査情報表示欄410に「検査No」と、「検査日」と、「検体名」と、「cfu」と、「希釈倍率」と、「カウント数1」と、「カウント数2」とを表示する。また、表示部102は、判定部114が検査過程において不備があった可能性が高いと判定した場合に、図8および図9に示すように、検査情報表示欄410内のアラーム表示部411に「検査品質に問題がある可能性あり」という内容のアラームを表示する。
次に、図10の処理マトリクスを用いてコロニー検査装置100でなされる処理内容を説明する。図10は、コロニー検査装置の処理マトリクスの一例を示す図である。判定部114は、計数部112がカウントしたシャーレ間のコロニー数の相違が閾値以上の場合、どちらかのシャーレにて検査過程で不備があった可能性が高いと判定する。この場合、表示部102は、判定画面400にアラームを出力する。
次に、コロニー検査装置100における処理の流れについて説明する。図11は、コロニー検査装置がアラームを出力するまでの処理動作の第一の例を示す図である。まず、取得部111は、1つの検体を同一希釈倍率で2枚のシャーレに分割した後、それぞれを同一環境で培養することにより作成された2枚のシャーレに係る画像をそれぞれ取得する(ステップS10)。取得部111は、対応する2つのシャーレ画像を、一つの検査Noで対応付けて検査DB121に記憶させる。
すなわち、コロニー検査装置100は、細菌コロニーが含まれた複数のシャーレのそれぞれについて撮影された画像を取得する取得部111と、複数の画像の間で、類似度を算出する算出部113とを有する。さらに、コロニー検査装置100は、算出した類似度に基づいて、アラームを出力するか否かを変更する判定部114を有する。
実施例1においては、コロニー検査装置100が各シャーレのコロニー数および各シャーレ画像の画像特徴量を算出する。これに限定されず、図1の各端末装置300は、撮像装置200が撮影した各シャーレ画像に基づき、各シャーレのコロニー数、および各シャーレ画像の画像特徴量の一方または両方を算出し、算出されたデータをコロニー検査装置100に送信し、コロニー検査装置100が当該データを使用してもよい。
判定部114は、検査対象のシャーレが検査過程において不備があったか否かを、類似度が閾値以上であるか否かにより判定する。閾値は、食品グループ、検査項目ごとに設定される。閾値は、責任者により適宜更新されてもよい。
実施例1においては、判定部114は、シャーレ画像間の類似度が第一の閾値以下である場合に、検査対象のシャーレが検査過程において不備があったと判定する。さらに、判定部114は、シャーレ画像間の類似度が、第一の閾値よりも大きい第二の閾値以上である場合に、シャーレ画像が同一であると判定してもよい。これにより、コロニー検査装置100は、責任者の誤認により同じシャーレ画像を混同して判定画面400に表示させるのを防止することができる。なお、コロニー検査装置100は、シャーレ画像間の類似度が第二の閾値以上である場合に「表示されているシャーレ画像が同一の可能性あり」という内容のアラームを出力してもよい。これにより、同じシャーレ画像を使って検査品質を評価するという不正を防止することができる。
計数部112は、1つのコロニーが極度に成長する等の理由によりシャーレ内のコロニーの総面積が半分以上となった場合に、コロニー数を精度よくカウントすることができない場合がある。そこで、判定部114は、算出部113が算出したシャーレ内のコロニーの総面積が閾値以上の場合に、責任者に追加検査を促すためにアラームを出力してもよい。これにより、コロニー検査装置100は、成長の度合いが大きいコロニーが他のコロニーに重なることにより、コロニー数のカウントの精度が低下するのを防止することができる。
図14は、コロニー検査装置に係るコンピュータのハードウェア構成を示す図である。図14が示すように、コンピュータ500は、各種演算処理を実行するCPU501と、ユーザからのデータ入力を受け付ける入力装置502と、モニタ503とを有する。また、コンピュータ500は、記憶媒体からプログラム等を読み取る媒体読取装置504と、他の装置と接続するためのインターフェース装置505と、他の装置と無線により接続するための無線通信装置506とを有する。また、コンピュータ500は、各種情報を一時記憶するRAM(Random Access Memory)507と、ハードディスク装置508とを有する。また、各装置501~508は、バス509に接続される。
101 I/F
102 表示部
110 制御部
111 取得部
112 計数部
113 算出部
114 判定部
120 記憶部
121 検査DB
122 画像データ
123 画像特徴量データ
124 閾値データ
Claims (9)
- コンピュータに
細菌コロニーが含まれた複数のシャーレのそれぞれについて撮影された画像を取得し、
複数の前記画像の間で、類似度を算出し、
算出した前記類似度に基づいて、アラームを出力するか否か制御する処理を実行させることを特徴とする、コロニー検査プログラム。 - 前記アラームを出力するか否かを変更する処理は、算出した前記類似度が、所定の値以上の差分を示す場合に、アラームを出力することを特徴とする請求項1に記載のコロニー検査プログラム。
- さらに、複数の前記画像のそれぞれに含まれる前記細菌コロニーの数を計数し、
前記アラームを出力するか否かを変更する処理は、複数の前記画像のそれぞれについて計数された値が、予め決められていた数以上の差分がある場合、および、前記類似度が、所定の値以上の差分を示す場合に、アラームを出力することを特徴とする請求項1に記載のコロニー検査プログラム。 - 細菌コロニーが含まれた複数のシャーレのそれぞれについて撮影された画像を取得する取得部と、
複数の前記画像の間で、類似度を算出する算出部と、
算出した前記類似度に基づいて、アラームを出力するか否かを変更する出力部と、を有することを特徴とするコロニー検査装置。 - 前記出力部は、算出した前記類似度が、所定の値以上の差分を示す場合に、アラームを出力することを特徴とする請求項4に記載のコロニー検査装置。
- 複数の前記画像のそれぞれに含まれる前記細菌コロニーの数を計数する計数部をさらに有し、
前記出力部は、複数の前記画像のそれぞれについて計数された値が、予め決められていた数以上の差分がある場合、および、前記類似度が、所定の値以上の差分を示す場合に、アラームを出力することを特徴とする請求項4に記載のコロニー検査装置。 - コンピュータが
細菌コロニーが含まれた複数のシャーレのそれぞれについて撮影された画像を取得し、
複数の前記画像の間で、類似度を算出し、
算出した前記類似度に基づいて、アラームを出力するか否かを変更する処理を実行することを特徴とする、コロニー検査方法。 - 前記アラームを出力するか否かを変更する処理は、算出した前記類似度が、所定の値以上の差分を示す場合に、アラームを出力させることを特徴とする請求項7に記載のコロニー検査方法。
- さらに、複数の前記画像のそれぞれに含まれる前記細菌コロニーの数を計数し、
前記アラームを出力するか否かを変更する処理は、複数の前記画像のそれぞれについて計数された値が、予め決められていた数以上の差分がある場合、および、前記類似度が、所定の値以上の差分を示す場合に、アラームを出力させることを特徴とする請求項7に記載のコロニー検査方法。
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015538665A JPWO2015045012A1 (ja) | 2013-09-24 | 2013-09-24 | コロニー検査プログラム、コロニー検査装置およびコロニー検査方法 |
CN201380079721.XA CN105593359A (zh) | 2013-09-24 | 2013-09-24 | 菌落检查程序、菌落检查装置以及菌落检查方法 |
EP13894337.8A EP3050958A4 (en) | 2013-09-24 | 2013-09-24 | COLONY CONTROL PROGRAM, COLONY CONTROL DEVICE, AND COLONY CONTROL METHOD |
PCT/JP2013/075778 WO2015045012A1 (ja) | 2013-09-24 | 2013-09-24 | コロニー検査プログラム、コロニー検査装置およびコロニー検査方法 |
US15/066,781 US20160194597A1 (en) | 2013-09-24 | 2016-03-10 | Colony inspection device, colony inspection method, and recording medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2013/075778 WO2015045012A1 (ja) | 2013-09-24 | 2013-09-24 | コロニー検査プログラム、コロニー検査装置およびコロニー検査方法 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US15/066,781 Continuation US20160194597A1 (en) | 2013-09-24 | 2016-03-10 | Colony inspection device, colony inspection method, and recording medium |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015045012A1 true WO2015045012A1 (ja) | 2015-04-02 |
Family
ID=52742226
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2013/075778 WO2015045012A1 (ja) | 2013-09-24 | 2013-09-24 | コロニー検査プログラム、コロニー検査装置およびコロニー検査方法 |
Country Status (5)
Country | Link |
---|---|
US (1) | US20160194597A1 (ja) |
EP (1) | EP3050958A4 (ja) |
JP (1) | JPWO2015045012A1 (ja) |
CN (1) | CN105593359A (ja) |
WO (1) | WO2015045012A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019111365A1 (ja) * | 2017-12-06 | 2019-06-13 | オリンパス株式会社 | 検体サンプル評価装置、検体サンプル評価方法およびプログラム |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105579568A (zh) * | 2013-09-30 | 2016-05-11 | 富士通株式会社 | 菌落图像检查程序、菌落图像检查方法以及菌落图像检查装置 |
CN105671122A (zh) * | 2016-03-30 | 2016-06-15 | 李辰 | 细菌鉴定方法及装置 |
JP2020536541A (ja) * | 2017-10-05 | 2020-12-17 | ベクトン・ディキンソン・アンド・カンパニーBecton, Dickinson And Company | 生体試料評価処理のためのアプリケーション開発環境 |
CN108197598A (zh) * | 2018-01-25 | 2018-06-22 | 曹凯 | 一种噬线虫1号战线菌群的制配系统 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011212013A (ja) | 2010-03-17 | 2011-10-27 | Elmex Ltd | フィルム型培地による微生物検査方法およびこの微生物検査方法に用いる画像取込ツ−ル |
JP2011239683A (ja) | 2010-05-14 | 2011-12-01 | Hitachi High-Technologies Corp | 自動釣菌装置 |
JP2012135240A (ja) * | 2010-12-27 | 2012-07-19 | Hitachi High-Technologies Corp | 細菌コロニー同定装置およびその方法 |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040101954A1 (en) * | 2002-11-27 | 2004-05-27 | Graessle Josef A. | Back side plate illumination for biological growth plate scanner |
US20070015989A1 (en) * | 2005-07-01 | 2007-01-18 | Avantis Medical Systems, Inc. | Endoscope Image Recognition System and Method |
PT2827150T (pt) * | 2009-08-22 | 2020-12-09 | Univ Leland Stanford Junior | Imagiologia e avaliação de embriões, oócitos e células estaminais |
EP2497823B1 (en) * | 2009-11-05 | 2017-08-16 | Hitachi High-Technologies Corporation | Device for harvesting bacterial colony and method therefor |
EP2586873B1 (en) * | 2010-06-23 | 2015-11-18 | Kabushiki Kaisha N-Tech | Methods and devices for detecting a microbial colony |
GB2494202A (en) * | 2011-09-05 | 2013-03-06 | Bactroscan Ltd | Microorganism imaging and incubating apparatus able to maintain a temperature gradient |
-
2013
- 2013-09-24 JP JP2015538665A patent/JPWO2015045012A1/ja active Pending
- 2013-09-24 CN CN201380079721.XA patent/CN105593359A/zh active Pending
- 2013-09-24 WO PCT/JP2013/075778 patent/WO2015045012A1/ja active Application Filing
- 2013-09-24 EP EP13894337.8A patent/EP3050958A4/en not_active Withdrawn
-
2016
- 2016-03-10 US US15/066,781 patent/US20160194597A1/en not_active Abandoned
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011212013A (ja) | 2010-03-17 | 2011-10-27 | Elmex Ltd | フィルム型培地による微生物検査方法およびこの微生物検査方法に用いる画像取込ツ−ル |
JP2011239683A (ja) | 2010-05-14 | 2011-12-01 | Hitachi High-Technologies Corp | 自動釣菌装置 |
JP2012135240A (ja) * | 2010-12-27 | 2012-07-19 | Hitachi High-Technologies Corp | 細菌コロニー同定装置およびその方法 |
Non-Patent Citations (1)
Title |
---|
See also references of EP3050958A4 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019111365A1 (ja) * | 2017-12-06 | 2019-06-13 | オリンパス株式会社 | 検体サンプル評価装置、検体サンプル評価方法およびプログラム |
Also Published As
Publication number | Publication date |
---|---|
CN105593359A (zh) | 2016-05-18 |
US20160194597A1 (en) | 2016-07-07 |
EP3050958A4 (en) | 2016-10-26 |
EP3050958A1 (en) | 2016-08-03 |
JPWO2015045012A1 (ja) | 2017-03-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6845221B2 (ja) | プレート培地上にストリークされた試料からの自動化された微生物コロニーカウントのための方法及びシステム | |
JP6801000B2 (ja) | 細胞画像評価装置および細胞画像評価制御プログラム | |
JP6777726B2 (ja) | コロニーコントラスト収集 | |
JP5707399B2 (ja) | 微生物検出方法、微生物検出装置及びプログラム | |
KR101989202B1 (ko) | 미생물 성장을 분석하는 방법 및 소프트웨어 | |
WO2015045012A1 (ja) | コロニー検査プログラム、コロニー検査装置およびコロニー検査方法 | |
JP6490365B2 (ja) | 微生物検査装置の検証方法、微生物検査装置における検証装置及びプログラム | |
JP2010181402A (ja) | 受精卵品質評価支援システム、受精卵品質評価支援装置および受精卵品質評価支援方法 | |
JP7416136B2 (ja) | コロニー検出装置 | |
US20210327060A1 (en) | Discerning device, cell mass discerning method, and computer program | |
JP2022514427A (ja) | バクテリアコロニーのバクテリア増殖を監視しコロニーバイオマスを予測するシステム及び方法 | |
WO2021100191A1 (ja) | 細胞数情報の表示方法、システム、及び、プログラム | |
US20160203605A1 (en) | Recording medium, colony image inspection method, and colony image inspection device | |
JP2015231343A (ja) | コロニーの分類修正方法、分類修正プログラム及び分類修正装置 | |
da Silva et al. | An automatic phytopathometry system for chlorosis and necrosis severity evaluation of asian soybean rust infection | |
US20230289962A1 (en) | Method of generating quality control information, apparatus for generating quality control information, and program | |
JP2023131196A (ja) | 精度管理情報の生成方法、精度管理情報の生成装置、及びプログラム | |
JP6924398B2 (ja) | コロニー検出システム | |
JP2023131197A (ja) | 精度管理方法、精度管理装置、及びプログラム | |
JP2015171333A (ja) | 判定方法、判定プログラム及び判定装置 | |
Chatburn et al. | VAPI: low-cost, rapid automated visual inspection system for Petri plate analysis | |
BR122024005682A2 (pt) | Método automatizado para estimar um número de unidades de formação de colônia sobre meio laminado e sistema para avaliar o crescimento em um meio de cultura inoculado com uma amostra biológica |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13894337 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2015538665 Country of ref document: JP Kind code of ref document: A |
|
REEP | Request for entry into the european phase |
Ref document number: 2013894337 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2013894337 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |