NO333499B1 - Method and system for detecting a lice on fish - Google Patents

Abstract

The present invention relates to a method for detecting a lice on a fish, comprising the steps of receiving an image of a fish, searching for pixels having colors within a background color range, and setting these pixels to a default pixel value; increase for pixels that have colors within a fish surface color range and set these pixels to the default pixel value, and search for a predetermined lice-shaped object in those parts of the image that have a pixel value different from the default value. Then, the method comprises the step of determining whether the predetermined loop shaped object is present in the image. If found, the method performs the steps: providing a sub-image of the image, wherein the sub-image contains the area of image where the predetermined loop-shaped object is found, and storing information about the sub-image, where information storage includes storing information about the location of the image. the sub-image in the image.

Description

FIELD OF THE INVENTION

The present invention relates to a method and system for detecting a louse on a fish.

BACKGROUND OF THE INVENTION

In the farming industry, lice have been and still are a major problem. For example, salmon (especially Salmo Salar) in farms are vulnerable to salmon lice (Lepeophtheirus salmonis). Other fish species, such as rainbow trout (Oncorhynchus mykiss), cod species etc. are also exposed to various types of lice. There have been several attempts both to monitor the number of lice in farms and to remove lice from fish in farms.

Salmon lice have a lifespan of ten life cycle stages, where stages four to seven are chalimus stages where the louse is attached to the salmon and feeds from the salmon, and where stages 8-10 are adult stages where the lice are mobile. In these last stages, it is also possible to distinguish between male lice and female lice (see for example

http:// en. wikipedia. org/ wiki/ Salmon louse). There are other types of fish lice that have a similar life cycle and similar appearance.

Today, monitoring the number of lice in a fish farming facility, for example a fish breeding tank, fish breeding mare, etc., is carried out manually by catching one or a number of fish from the facility and then counting the number of lice on each fish manually. Alternatively, an image recorder (film or single images) can be lowered into the system and the number of lice can be counted manually by looking at the image recording.

It should be noted that the total number of lice is at a significant level if there is an average of 0.5 lice per fish. At this level de-lice must be carried out. Consequently, it is a technical challenge to provide a method capable of detecting a louse on a fish.

The purpose of the invention is to provide a method and a system for detecting the presence of a louse on a fish. Furthermore, it is a purpose to count the number of lice if more than one louse is present. It is also an aim of the invention to provide a method and a system where it is possible to detect the phase to which each louse on the fish belongs. It is also an important purpose of the invention to provide a method and a system that is fast and efficient.

SUMMARY OF THE INVENTION

The present invention relates to a method for detecting a louse on a fish, comprising the following steps:

- receive a picture of a fish; - search for pixels with colors within a background color range and set these pixels to a default pixel value; - search for pixels with colors within a fish surface color range and set these pixels to the default pixel value; - searching for a predetermined louse-shaped object in those parts of the image that have a pixel value different from the default value; - determine whether the predetermined louse-shaped object is present in the image, and if found, perform the following steps: - provide a partial image of the image, where the partial image contains the area of the image where the predetermined louse-shaped object is found, and - store information about the partial image, where the storage of information includes storing information about the position of the partial image in the image.

In one aspect, the predetermined loop-shaped object comprises a first, substantially circular object, a second, substantially circular object coupled to the first object, and a third, substantially rectangular object coupled to the second object.

In one aspect, the louse-shaped object comprises an image of a louse.

In one aspect, the image of the louse is retrieved from a database of louse images.

In one aspect, the step of storing information about the partial image further comprises:

- store the width and length of the partial image.

In one aspect, the step of storing information about the partial image further comprises:

- save the contour of the louse in the partial image.

In one aspect, the method further comprises the step of:

- determine a life cycle stage of the louse based on the width and length of the partial image.

In one aspect, the received image of the fish is taken under controlled lighting conditions.

In one aspect, the method further comprises the step of performing an image differentiating algorithm prior to the step of searching for the predetermined loop shape.

The present invention also relates to a system for detecting a louse on a fish, comprising: - an image recorder for recording an image of a fish; - a computer memory; - a central processing device connected to the image recorder and to the computer memory, wherein the central processing device is configured to perform the above method.

The present invention also relates to a method for detecting a louse on a fish, comprising the following steps: - receiving an image of a fish; - search for pixels with colors within a background color range and set these pixels to a default pixel value; -search for pixels with colors within a fish surface color range and set these pixels to the default pixel value; - searching for a predetermined louse-shaped object in those parts of the image that have a pixel value different from the default value; - determine if the predetermined louse-shaped object exists in the image, and if found, perform the following steps:

- increase a louse counter for each louse found in the image.

In one aspect, the method comprises the step of:

- calculate the average number of lice per fish.

DETAILED DESCRIPTION

Embodiments of the invention will now be described in detail with reference to the attached drawings, where: Fig. 1 illustrates the system for detecting a louse on a fish; Fig. 2 illustrates the steps in a method for detecting a louse on a fish; Fig. 3 illustrates a predetermined louse-shaped object; Fig. 4 illustrates a screenshot of the system running on a computer device, where it is shown that a louse has been detected on the fish; Fig. 5 shows an image received from an image recorder, where a louse is marked with a dotted circle; Fig. 6a shows the image in fig. 5 after the color filtering process; Fig. 6b shows an enlarged image of the louse found in fig. 6a; Fig. 7a shows the image in fig. 5 and fig. 6a after a pixel recoding process;

Fig. 7b shows an enlarged image of the louse found in fig. 7a.

Reference is now made to fig. 1, which illustrates a system for detecting a louse on a fish. The system 1 comprises an image recorder 2 for recording an image of the fish. The image recorder can record still images (photographs) or film, in the present embodiment the image recorder takes still images of the side of the fish.

It should be noted that the system may comprise several image recorders, for example one image of each lateral surface of the fish. Alternatively, a further image recorder can be provided to take a picture from above of the fish, a picture from below of the fish, etc.

It should also be noted that the imager can take pictures of only parts of the fish instead of pictures of the whole fish, i.e. to analyze a fish, the imager has to take several pictures.

In the present embodiment, the image recorder is a digital camera.

The image recorder 2 is connected to a computer device 3, comprising a central processing device or CPU 4 and a computer memory 5. The computer device 3 can be any type of computer device and is considered known to a person skilled in the art. The computer device 3 is further connected to a user interface, such as a screen, a keyboard, a mouse, etc. However, it is also possible to provide the system as one device, where the device comprises the image recorder, computer memory and CPU in one device, and where the output signal from a such a device is a number display that shows the average number of lice per fish.

In an industrial setting, the system 1 may be provided with an input for the fish and an output for the fish, to ensure that only one fish passes the image recorder at a time. Furthermore, the sensors can be provided to be able to record a picture of the fish when the fish is in the correct position in front of the camera. Furthermore, the image of the fish can be provided when the fish is retrieved from water, or when the fish is submerged in water.

A method for detecting a louse on a fish is implemented as a computer program running on the CPU 4. Thus, the central processing device 4 of the computer device 3 is configured to carry out the method described below.

In a first step 10, the computer device 3 receives an image of a fish from

the image recorder 2. The image is delivered in an electronic file format, usually a JPG format, a PNG format or another suitable format. An example of such an image is shown in fig. 5, where a dashed circle indicates the position of a louse. The image in fig. 5 has a size of approximately 2.6 MB.

Then, the computer device 3 manipulates the image by performing the following steps:

In step 12, the computer device 3 searches for pixels with colors within a background color interval and sets these pixels to a standard pixel value. The background color range is a predetermined range of colors considered to define the background of the image. Thus, the image will only contain the colors in the background color interval if no fish are present in the image.

It should be noted that the term color is used here both for color images, where the pixel can have a value for each of the colors red, green and blue, alternatively a value for each of the colors cyan, magenta, yellow and black. However, the term color can also represent shades of gray in a black and white image.

The default pixel value can typically be a non-color value, such as -1 or pure black or white.

To achieve this, the imager can be aimed at a surface that has a color different from the color of the fish and the color of the fish surface.

In step 14, the computer device 3 searches for pixels with colors within a fish surface color range and sets these pixels to the default pixel value. The fish surface color interval is a predetermined range of colors considered to define the fish surface in the image.

It should be noted that steps 12 and 14 can be performed simultaneously. Therefore, the procedure iterates through pixels in the image only once while searching for pixels that have colors in a background color interval and while searching for pixels that have colors in a fish surface color interval.

Fig. 6a shows the image in fig. 5 after steps 12 and 14 have been carried out. Here the default pixel value has been set to white. An enlarged image of the louse in fig. 6a is shown in fig. 6b.

Since the background and the fish surface will normally make up the largest part of the image, search steps 12 and 14 will have reduced the amount of information in the image significantly. Usually, only a very small fraction of the pixels in the image are now not at the default value.

It should be noted that this will depend on the image, whether the image shows the whole fish (ie a large part of the image will contain background colors) or only part of the fish (ie the image will not contain background colors or only a small area of background colors).

The image in fig. 5 has a size of approx. 9 kB, i.e. the information in this image is significantly reduced.

In step 16, the computer device 3 searches for a predetermined louse-shaped object in those parts of the image that have a pixel value different from the standard value.

One example of such a predetermined louse-shaped object is shown in fig. 3. The predetermined louse-shaped object may be an object or a specification that makes it possible to determine whether a louse is actually present in those parts of the image that have a pixel value different from the default value or not. The predetermined louse-shaped object 30 may comprise a predetermined shape as in fig. 3, comprising a first, substantially circular object 31, a second, substantially circular object 32 which is connected to the first object 31, and a third, substantially rectangular object 33 which is connected to the second object 32. A threshold value can be used to determine how close to the image these objects must be to define a louse.

An additional criterion may be that these objects may partially overlap. Furthermore, an additional criterion can be that these objects are oriented along a line II.

In an alternative embodiment, the predetermined louse-shaped object comprises an image of a louse. Therefore, an image recognition algorithm is performed to compare the image of a louse and those parts of the image that have a pixel value different from the default value. It is possible to provide the system with a database of lice images and retrieve the image of lice from the database of lice images. The database can include several images and compare the parts of the image that have a pixel value different from the standard value with one or more of the images in the database.

In fig. 6a, the louse was found by searching for a predetermined louse-shaped object in the form of a predetermined shape, such as that shown and described above with respect to FIG. 3. One more test was carried out and the louse was also found by comparing fig. 6a with pictures of lice.

In step 18, the computer device 3 determines whether there is a predetermined louse-shaped object in the image. Thus, the computer device 3 decides whether one or more lice are present in the image.

If the predetermined louse-shaped object is found, the computer device 3 performs a step of providing a partial image of the image, where the partial image contains the area of the image where the predetermined louse-shaped object is found (step 20). Furthermore, the computer device 3 stores information about the partial image, where the storage of information includes storing information about the position of the partial image in the image (step 22). Then, in step 24, the method ends.

The partial image is shown with a dashed square in fig. 6b, where the length L and width W are also indicated.

If no predetermined lice-shaped object is found, the process begins again by receiving a new image in step 10. Alternatively, for example, if there are no more images, then the process terminates.

The step 22 for storing information about the partial image can further include storing the width and length of the partial image. The computer device 3 can determine a life cycle stage of the louse based on the width and length of the partial image.

The step 22 for storing information about the partial image can further comprise storing the contour of lice in the partial image. The contour of the louse can be stored in the database and can be used in the search for a predetermined louse-shaped object, step 16 in other images.

To improve the above method, the received image of the fish can be taken under controlled lighting conditions. The method is thus believed to be more reliable with respect to searching for pixels having colors within a background color range, searching for pixels having colors within a fish surface color range and searching for a predetermined louse-shaped object in those parts of the image with a pixel value different from the default value.

It should also be noted that the method may further include the step of performing an image differentiating algorithm after search steps 12 and 14 but before step 16 to search for the predetermined louse pattern. Such an image differentiating algorithm can be an algorithm where pixel values are recoded, for example into a binary image, for faster recognition of figures. The image differentiating algorithm can be performed in several iterations.

Fig. 7a shows the image in fig. 6a where such an image differentiating algorithm has been performed. Here, all pixels in the image are either black or white. An enlarged image of the louse as shown in fig. 7a is shown in fig. 7b. In fig. 7a the louse was found by searching for a predetermined louse-shaped object in the form of a predetermined shape, such as that shown and described above with respect to FIG. 3.

It is also possible to pre-process the image before steps 12 and 14.

Reference is now made to fig. 4, which shows the user interface 40 of a computer program executed by the computer device 3. It should be noted that this user interface is used for testing the prototype of the method, and thus there are several possibilities for adjusting different threshold values to perform the image differentiating algorithm(s). e). In addition, the user interface shows a lot of information about the image to the user, which is strictly speaking not necessary to be able to detect whether a lice is present on the fish or to be able to count the number of lice on a fish. It should therefore be noted that the method and system according to the present invention do not need a user interface such as that shown in fig. 4.

In fig. 4, it is shown that the user interface 40 displays the image 41 of the fish. Furthermore, the user interface 40 contains a text box 42 where information is displayed if a louse is detected. In fig. 4, the information contains the following information:

Lice position = {X = 1895, Y = 1290}

Lice height = 85

Louse length = 55

Accordingly, a louse has been detected, the upper right corner of the partial image of the louse is at position (X = 1895 pixels (from the right side of the image), Y = 1290 pixels (from the upper side of the image)) of the image, the height of the partial image is 85 pixels and the length of the partial image is 55 pixels.

The location of the louse is indicated by a dotted circle 43.

In the present embodiment, a color filter is used when performing step 12 and step 14. The color filter typically defines a color interval with a minimum value and a maximum value for a color value. Maximum and minimum values can be defined in any color system, such as RGB (by selecting values for the variables Red, Green, Blue), CMYK (by selecting values for the variables Cyan, Magenta, Yellow, Black), HSL (by selecting values for the variables Hue, Saturation, Light) or another color system. The color intervals can be defined as a minimum value and a maximum value for each variable in the color system, or for just one variable in the color system. In addition, a minimum value and a maximum value can be defined for additional properties such as opacity/transparency, reflectivity, etc. The type of color filter and type of color system are considered known to a person skilled in the art and will not be described here in detail.

To be able to implement a color filter in steps 12 and 14, there are libraries available in many programming languages. Furthermore, considered

figure recognition algorithms, alternatively image comparison algorithms, used in step 16, known to a person skilled in the art and will not be described here in detail. Libraries are available to implement these algorithms in many programming languages.

In addition, the method can include the step of increasing a lice counter for each louse found in the image. Furthermore, the method can include the step of counting the number of fish of which pictures are taken, and thus performing the step of calculating the average number of lice per fish.

According to the invention, a fast and efficient method and system for detecting a louse on a fish has been achieved.

Claims (1)

1. Method for detecting a louse on a fish, comprising the following steps: - receiving an image of a fish; - search for pixels with colors within a background color range and set these pixels to a default pixel value; - search for pixels with colors within a fish surface color range and set these pixels to the default pixel value; - searching for a predetermined louse-shaped object in those parts of the image that have a pixel value different from the default value; - determine whether the predetermined louse-shaped object is present in the image, and if found, perform the following steps: - provide a partial image of the image, where the partial image contains the area of the image where the predetermined louse-shaped object is found, and - store information about the partial image, where the storage of information includes storing information about the position of the partial image in the image. 2. Method according to claim 1, wherein the predetermined loop-shaped object comprises a first, substantially circular object, a second, substantially circular object connected to the first object and a third, substantially rectangular object connected to the second the object. 3. Method according to claim 1, where the louse-shaped object comprises an image of a louse. 4. Method according to claim 2, where the image of the louse is obtained from a database of louse images. 5. Method according to any one of the above-mentioned claims, where the step of storing information about the partial image further comprises: - storing the width and length of the partial image. 6. Method according to any one of the above-mentioned claims, where the step of storing information about the partial image further comprises: - storing the contour of the louse in the partial image. 7. Method according to claim 5, where the method further comprises the step: - determining a life cycle stage for the louse based on the width and length of the partial image. 12. Method according to any of the above claims, where the received image of the fish is taken under controlled lighting conditions. 13. A method according to any one of the above claims, wherein the method further comprises the step of performing an image differentiating algorithm before the step of searching for the predetermined loop shape. 14. System for detecting a louse on a fish, comprising: - an image recorder for recording an image of a fish; - a computer memory; - a central processing device connected to the image recorder and to the computer memory, where the central processing device is configured to carry out the method according to one of claims 1-13. 15. Method for detecting a louse on a fish, comprising the following steps: - receiving an image of a fish; - search for pixels with colors within a background color range and set these pixels to a default pixel value; -search for pixels with colors within a fish surface color range and set these pixels to the default pixel value; - searching for a predetermined louse-shaped object in those parts of the image that have a pixel value different from the default value; - determine if the predetermined louse-shaped object exists in the image, and if found, perform the following steps: - increment a louse counter for each louse found in the image. 16. Method according to claim 15, where the method includes the step: - calculate the average number of lice per fish.