DETECTING SURFACE CHARACTERISTICS OF FOOD OBJECTS

Abstract

An apparatus for detecting surface characteristics on food objects conveyed by a conveyor, has a first imaging device for capturing two-dimensional image data (2D) and a second imaging device for capturing three-dimensional image data (3D) of a food object. At least one image processing unit is configured to utilize either one of the 2D or the 3D image data in determining whether a potential defect is present on the surface of the food object. In case such a potential defect property is found, the image processing unit determines a surface position of the potential defect, and utilizes the remaining one of the 2D or the 3D image data in determining whether an actual defect is present on the surface of the food object at the indicated surface position. Further, the apparatus has an output unit for outputting defect related data in case both of the 2D and the 3D image data indicate that an actual defect is present on the surface of the food object at the indicated surface position.

Claims

1.-10. (canceled)

11. An apparatus for detecting surface characteristics on incoming food objects, comprising: a first imaging device for capturing two-dimensional image data and a second imaging device for capturing three-dimensional image data of a food object; at least one image processing unit configured to: utilize either one of said 2D or said 3D image data in determining whether a potential defect is present on the surface of said incoming food object, where, in case such a potential defect property is detected, determining a surface position of said potential defect; and utilize the remaining one of said 2D or said 3D image data in determining whether an actual defect is present on the surface of said incoming food object at said determined surface position; an output unit for outputting defect related data in case both of said 2D and said 3D image data indicate that an actual defect is present on the surface of said incoming food object at said determined surface position.

12. The apparatus according to claim 11, wherein the first imaging device is arranged to acquire the two-dimensional image data before the second imaging device acquires the three-dimensional image data.

13. The apparatus according to claim 11, wherein the second imaging device is arranged to acquire the three-dimensional image data before the first imaging device acquires the two-dimensional image data.

14. The apparatus according to claim 11, wherein the first imaging device and the second imaging device are arranged to concurrently acquire the two-dimensional image data and the three-dimensional image data.

15. The apparatus according to claim 11, wherein said incoming food objects are conveyed by a conveyor apparatus while said surface detection takes place.

16. A method for detecting surface characteristics of food objects, comprising the steps of: capturing two-dimensional image data of a food object using a first imaging device and capturing three-dimensional image data of the food object using a second imaging device, using at least one image processing unit to process either one of said 2D or said 3D image data to determine whether a potential defect is present on the surface of said incoming food object, and in case such a potential defect property is detected, determine a surface position of said potential defect, and using the at least one image processing unit to process the remaining one of said 2D or said 3D image data to determine whether an actual defect is present on the surface of said incoming food object at said determined surface position.

17. The method according to claim 16, wherein the method comprises a further step: outputting defect related data in case both of said 2D and said 3D image data indicate that an actual defect is present on the surface of said incoming food object at said determined surface position, using an output unit.

18. The method according to claim 16, wherein the first imaging device is arranged to acquire the two-dimensional image data before the second imaging device acquires the three-dimensional image data.

19. The method according to claim 16, wherein the second imaging device is arranged to acquire the three-dimensional image data before the first imaging device acquires the two-dimensional image data.

20. The method according to claim 16, wherein the first imaging device and the second imaging device are arranged to concurrently acquire the two-dimensional image data and the three-dimensional image data.

21. An apparatus for detecting surface characteristics on incoming food objects, comprising: a first imaging device for capturing two-dimensional image data and a second imaging device for capturing three-dimensional image data of a food object; at least one image processing unit configured to: utilize either one of said 2D or said 3D image data in determining whether a potential defect is present on the surface of said incoming food object, where, in case such a potential defect property is detected, determining a surface position of said potential defect; and utilize the remaining one of said 2D or said 3D image data in determining whether an actual defect is present on the surface of said incoming food object at said determined surface position; an output unit for outputting defect related data in case both of said 2D and said 3D image data indicate that an actual defect is present on the surface of said incoming food object at said determined surface position; wherein the first imaging device is arranged to acquire the two-dimensional image data before the second imaging device acquires the three-dimensional image data; wherein the second imaging device is arranged to acquire the three-dimensional image data before the first imaging device acquires the two-dimensional image data.

22. The apparatus according to claim 21, wherein the first imaging device and the second imaging device are arranged to concurrently acquire the two-dimensional image data and the three-dimensional image data.

23. The apparatus according to claim 21, wherein said incoming food objects are conveyed by a conveyor apparatus while said surface detection takes place.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The aspects and optional details of the invention will be explained below with reference to the drawings. In the drawings:

[0018] FIGS. 1 and 2 show two embodiments of a detecting apparatus according to an embodiment of the invention; and

[0019] FIGS. 3A to 3C show flowcharts of embodiments of a method according to the present invention for detecting surface characteristics on food objects.

[0020] FIGS. 4A to 4D and FIGS. 5A and 5B show objects (20) analyzed with 2D image data and 3D image data.

DESCRIPTION OF EMBODIMENTS

[0021] FIG. 1 schematically depicts a detecting apparatus 10 according to an embodiment of the invention. Food objects 20 are in this embodiment transported on a conveyor system 30 in a conveying direction as indicated by the arrow from an infeed end 40 to an outfeed end 50. The apparatus 10 comprises a first imaging device 60 for capturing two-dimensional image data (2D) of the food objects, and a second imaging device 70 for capturing three-dimensional image data (3D) of the food objects 20. The imaging device may be arranged adjacent the transport path of the conveyor system 30 so that the imaging devices 60, 70 may obtain their respective images of the food object 20 passing by the respective imaging device.

[0022] In FIG. 1 the 2D imaging device 60 is shown upstream of the 3D imaging device 70, with respect to the travel direction of the food objects 20 on the conveyor system 30. Alternatively, and still according to the invention, the 3D imaging system 70 may be arranged upstream of the 2D imaging system 60 (not shown). The imaging devices 60, 70 may be arranged in any position relative to the food objects 20 as long as they can obtain the image data associated with each food object.

[0023] The obtained image data (2D and 3D) are processed in at least one image processing unit 80 which may comprise a computer running image processing data software and having access to the image data stored in a computer memory.

[0024] The at least one image processing unit 80 may utilize the 2D image data in determining whether a potential defect is present on the surface of the food object 20. In case such a potential defect property is detected, the processing unit determines a surface position of the potential defect on the food object. Following this, the at least one image processing unit 80 may utilize the 3D image data in determining whether an actual defect is present on the surface of the food object within the determined surface position. For example, the 2D image data may indicate a discoloration at a certain surface location on the food object. The 3D image data may then be utilized to ascertain whether the discoloration is a void (hole or shadow or recess) in the surface or an actual discoloration (e.g. a blood stain).

[0025] The at least one image processing unit 80 may utilize an output unit 90, e.g. a display or an automatic message, for outputting defect related data in case both of said 2D and said 3D image data indicate that an actual defect is present on the surface of the food object within the surface position.

[0026] Alternatively, the at least one image processing unit 80 may utilize the 3D image data in determining whether a potential defect is present on the surface of the food object 20. In case such a potential defect property is detected, the processing unit determines a surface position of the potential defect on the food object. Following this, the at least one image processing unit 80 may utilize the 2D image data in determining whether an actual defect is present on the surface of the food object within the determined surface position. For example, the 3D image data may indicate a void (hole or shadow or recess) at a certain surface location on the food object. The 2D image data may then be utilized to ascertain whether the void (hole or shadow or recess) in the surface is an actual discoloration (e.g. a blood stain).

[0027] A further embodiment of the invention is shown in FIG. 2, where the apparatus utilizes an imaging device 65 that is able to acquire both 2D as well as 3D image data concurrently, thus combining the first imaging device and the second imaging device into one imaging device. All other technical features are similar to what is shown in FIG. 1 and keep the same reference numbers. The 2D data set and the 3D data set is manipulated as has been disclosed above for the embodiment according to FIG. 1.

[0028] FIGS. 3A to 3C show different flowcharts of embodiments of a method according to the present invention for detecting surface characteristics on food objects, where the objects may be conveyed by a conveyor apparatus.

[0029] In step (S1) 110, two-dimensional image data (2D) of a food object 20 is captured using a first imaging device, and three-dimensional image data (3D) of the food object is captured using a second imaging.

[0030] In step (S2) 120, either one of the 2D or the 3D image data is processed to determine whether a potential defect is present on the surface of the food object, where in case such a potential defect property is detected, a surface position of the potential defect is determined.

[0031] In step (S3) 130, the remaining one of the 2D or the 3D image data is processed to determine whether an actual defect is present on the surface of the food object within the determined surface position.

[0032] In step (S4) 140, defect related data is output in case both of the 2D and the 3D image data indicate that an actual defect is present on the surface of the food object within the determined surface position.

[0033] FIG. 3A indicates one type of image data is processed in step S2 and afterwards the other type of image data is processed in step S3, followed by an output in step S4.

[0034] FIGS. 3B and 3C indicate simultaneously processing of the two types image data either by different processors as in FIG. 3B or by one processor as in FIG. 3C where the 2D and 3D data is processed together.

[0035] FIGS. 4A to 4D show an object (20) analyzed with 2D data and possible different 3D data indicating positive or false-positive result from 2D data. A fish fillet is conveyed along imaging devices for capturing two-dimensional image data and three-dimension image data. The fish fillet is located flat on the conveyor belt. In situation A, a 2D image illustrates the fish fillet seen from above. A black spot is identified. An arrow points towards this spot. The black spot indicates a possible defect of the fish fillet, this defect may e.g. be a blood spot, a melanin spot, a hole or something positioned onto the fish fillet. The dotted line indicates the location of the view along the fish fillet which is obtained from the 3D data and shown in the three independent situations illustrated by B to D.

[0036] Situation B illustrates no defect at the surface position of the fish fillet as detected by 2D data (arrow points to this surface position). As no defect is determined based on the acquired 3D data, there is no defects inside the fish fillet nor on the surface of the fish fillet and the 2D data indicated a positive result and the spot identified may be e.g. a blood spot or melanin spot.

[0037] Situation C illustrates a hole in the fish filled (indicated by the arrow) at the surface position of the black spot as detected from the acquired 2D data. If holes in the fish fillet are accepted the 3D data indicates a false-positive result obtained from the 2D data.

[0038] Situation D illustrates something located on the surface of the fish fillet as indicated by the arrow. This may be e.g. a small piece of fish material released from a fish during the processing steps performed before detecting surface characteristics of the fish fillets. Here the fish material stick to the fish fillet and looks like a small bubble on the fish fillet. The material on the fish fillet is not a default of the fish fillet and hereby the 3D data indicates a false-positive result obtained from the 2D data.

[0039] FIGS. 5A and 5B show an object analyzed with 2D data and where 3D data supplies further data to the result from 2D data which may be because of shadow due to the form of the object. In situation A, a fish fillet is conveyed along an imaging device for capturing two-dimensional image data. The fish fillet is located flat on the conveyor belt and the 2D image illustrates the fish fillet seen from above. A black area is identified. An arrow points towards this area. The black area indicates a possible defect of the fish fillet. The dotted line indicates the location of the view along the fish fillet which is obtained from the 3D data and shown in the situation illustrated in B.

[0040] Situation B obtained from 3D data illustrates no hole or dirt on the fish fillet, but it shows that the defect are found on a steep part of the fillet. As can be seen in situation B the fish fillet is higher in the left part than in the middle and right part and hereby the fish fillet may not be evenly illuminated when the imaging device capturing two-dimensional image data acquires data. The area which is shadowed may in the 2D data be indicated as a black area, and hereby the 3D data indicates a false positive result obtained from the 2D data.

[0041] The above description of possible embodiments of the present invention should not be interpreted as limiting the scope of the present invention.