NL1038400C2

NL1038400C2 - An automatic sorting apparatus and method for same.

Info

Publication number: NL1038400C2
Application number: NL1038400A
Authority: NL
Inventors: Henk Stemerdink
Original assignee: Henk Stemerdink
Priority date: 2010-11-22
Filing date: 2010-11-22
Publication date: 2012-05-23

Description

AN AUTOMATIC SORTING APPARATUS AND METHOD FOR SAME FIELD OF THE INVENTION

5 The invention relates to an automatic sorting apparatus, for sorting a plurality of irregularly shaped, differently sized and differently weighing delicate objects.

BACKGROUND

10 Several types of weighing, sorting and packaging machines and methods for the same are known in the art. However, the processes of weighing, sorting and packaging of most fruits and vegetables are commonly done by hands, particularly when they are delicate and bruisable. Commonly, if the fruits or the vegetables appear to be bruised or damaged, their values become less or they become unsellable. Consumers are generally 15 very picky when choosing fruits or vegetables. Besides, in the case of fruits and vegetables, it may be clear that the shapes and the weights for the individual pieces are not identical, hence these are not always suitable for fully automated handling. Generally, for the processes of weighing, sorting and packaging of fruits and vegetables, manual handling is involved at least partially. Such manual handling reduces the 20 productivity.

There are systems known that can grab products in a box or in a crate, but in such cases the products are mainly uniform regarding dimensions and weight, such as for bolts. The bolts are practically identical to one another and are not likely to be damaged. The 25 patent application W094/20230 discloses a machine where every apple is weighed and classified separately. The patent USA4428179 discloses a machine that uses trays that are partially pre-fllled with chicken meat and extra amounts of the meat are made to fall onto the pre-filled trays for adjusting their final weights to a predetermined value.

There are many fruits and vegetables that need delicate handling while weighing, 30 sorting and packaging. For an example, chicory stumps are extremely sensitive to bruising, which leads to brown spots. The consumers do not like to buy chicory stumps 1038400 2 with brown spots. Also in the case of chicory stumps, there is a large variation in size, shape and colour which makes automatic handling difficult.

There is a need for a fully automated apparatus that is suitable for handling delicate fruits and vegetables for weighing, sorting and packaging, without damaging or bruising 5 them in the process.

SUMMARY OF THE INVENTION

In one embodiment, the invention discloses an automatic sorting apparatus, for sorting a plurality of irregularly shaped, differently sized and differently weighing delicate 10 objects. The apparatus comprises a computation means and a pick and place robot communicable with the computation means. The robot further comprises an image recognition means and image recognition software for detecting image information from a supply of the plurality of the objects wherein each object is in any orientation. The software is further capable of feeding the image information to the computation means 15 for programming a grip for the robot for picking and placing each object. The grip is programmable differently for each object based on the following factors for each object: its type, dimensions and orientation, such that the robot can perform the picking and placing operation of the object without causing visible bruise/damage to the object. The proposed apparatus is fully automatic and without the need of human hands, hence 20 capable of providing improved productivity. Since the objects in the supply can be in any orientation, a further step of placing the objects in a particular orientation for automatic handling thereafter can be avoided, for improving productivity.

In another embodiment, the apparatus further comprises at least one first weighing 25 means, the robot being programmable for picking from the supply and placing at least one object on the first weighing means to form a first set of objects, such that a first weight as determined from the first set of objects by the first weighing means is lesser than a pre-programmed target weight range. The first weighing means is capable of passing information on the first weight to the computation means. The apparatus also 30 comprises a plurality of second weighing means and the robot is further programmable for picking from the supply and placing at least one object into each of the plurality of second weighing means to form a plurality of second sets of objects. A plurality of 3 second weights is determined correspondingly and the information on the plurality of second weights can be automatically passed to the computation means. The computation means is further capable of selecting at least one out of the plurality of second sets of objects to form a third set of objects such that when the third set of 5 objects is picked and placed on the first set of objects by the robot to form a final set of objects, the first weight becomes within the target weight range. The apparatus is capable of producing a plurality of the final sets of objects whether serially or parallel or in a mixture of both. The apparatus thus is advantageous in automatically selecting the most optimum third set of objects, which otherwise would take much longer time if 10 done manually for handling such delicate objects.

In an alternate embodiment, the apparatus further comprises a plurality of weighing means, the robot being programmable for picking from the supply and placing at least one object on each of the plurality of weighing means to form a plurality of sets of 15 objects. A plurality of weights can then be determined correspondingly and the information on the plurality of weights can be passed to the computation means. The computation means is capable of selecting an optimum combination from the plurality of sets of objects to form a combined weight, that is within a pre-programmed target weight range. The combination can then be picked and placed on a containing member 20 by the robot to form a final set of objects. The apparatus is capable of producing a plurality of such final sets of objects whether serially or parallel or in a mixture of both. The apparatus thus is advantageous in automatically selecting the most optimum final set of objects, which otherwise would take much longer time if done manually for handling such delicate objects.

25

The apparatus is particularly suitable for handling the object when in the form of a fruit or a vegetable.

In another embodiment, the image recognition means comprises a 3D line camera with 30 built in line-scanner, that can detect grey scales for recognising contours and shapes.

4

In another embodiment, the factors for programming the grip include colour of each object. This feature is advantageous where the colour of the object is an indication of how delicate the object is, so that the grip may be programmed accordingly.

5 The object may be a chicory stump. In another embodiment, the robot is capable of placing 3 to 6 or 6 to 12 chicory stumps to form the final set of chicory stumps that weighs about 500 gram or 1000 gram respectively.

In another embodiment, the apparatus is capable of fully automatically forming a 10 plurality of the final sets of chicory stumps, with more than 1500 kg of chicory stumps per hour.

In another embodiment, the robot comprises a cushioning material on at least a portion of its exterior surface for further helping prevent visible bruises or damages to the object 15 during the picking and placing operation of the object.

In another embodiment, the robot has a plurality of arms for the picking and placing operation, such that multiple operations can be executed simultaneously.

20 In another embodiment, the apparatus comprises a plurality of the first weighing means for increasing productivity.

In another embodiment, the apparatus further comprises a forwarding means for forwarding the final sets of objects for packaging. The forwarding means may comprise 25 a conveyor means.

In another aspect of the invention, a method of automatically sorting a plurality of irregularly shaped, differently sized and differently weighing delicate objects is disclosed. The method comprises the steps of: a) detecting image information of the 30 objects from a supply of the plurality of objects by an image recognition software, wherein each the object is in any orientation; b) automatically feeding the image information to a computation means by the software; and c) programming a grip for the 5 robot by the computation means for picking and placing operation, the grip being programmed differently for each object based on the following factors for each object: its type, dimensions and orientation. The method is fully automatic, without the need of human hands, hence improving on the productivity.

5 In an embodiment, the method further comprises the steps of: a) operating the robot for picking from the supply and placing at least one object on a first weighing means to form a first set of objects; b) automatically determining a first weight of the first set of objects by the first weighing means, wherein the first weight is lesser than a preprogrammed target weight range; c) automatically passing information on the first 10 weight to the computation means; d) operating the robot for picking from the supply and placing at least one object into each of a plurality of second weighing means for correspondingly forming a plurality of second sets of objects; e) automatically determining a plurality of second weights correspondingly from the plurality of second sets; f) automatically passing information on the plurality of second weights to the 15 computation means; g) automatically selecting at least one out of the plurality of second sets of objects by the computation means to form a third set of objects such that when the third set of objects is picked and placed on the first set of objects by the robot to form a final set of objects, the first weight becomes within the target weight range; h) forming the final set of objects; and i) automatically repeating the above steps for 20 producing a plurality of the final sets of objects whether serially or parallel or in a mixture of both. The method thus is advantageous in automatically selecting the most optimum third set of objects, which otherwise would take much longer time if done manually for handling such delicate objects.

25 In an alternate embodiment, the method further comprises the steps of: a) operating the robot for picking from the supply and placing at least one of the object on each of a plurality of weighing means; b) automatically determining a plurality of weights correspondingly by the plurality of weighing means; c) automatically passing information on the plurality of weights to the computation means; d) automatically 30 selecting an optimum combination by the computation means from the plurality of weighing means to form a combined weight, such that the combined weight is within a pre-programmed target weight range; e) picking and placing the combination on a 6 containing member by the robot to form a final set of objects; and f) automatically producing a plurality of the final sets of objects whether serially or parallel or in a mixture of both. The method thus is advantageous in automatically selecting the most optimum final set of objects, which otherwise would take much longer time if done 5 manually.

In an embodiment of the method disclosed, the object is a fruit or a vegetable. The method of picking from the supply may be in random order.

10 In an embodiment of the method disclosed, the robot places each of the objects in the final set of objects at a predetermined orientation, without having to handle again for adjusting orientation, such as before packaging.

In an embodiment, the method further comprises the step of detecting grey scales for 15 recognising contours and shapes of the plurality of objects, by using a 3D line camera with built in line-scanner.

In an embodiment, the method further comprises the step of programming the grip wherein the factors include colour of each object. This feature is advantageous where 20 the colour of the object is an indication of how delicate the object is, so that the grip may be programmed accordingly.

In an embodiment of the method disclosed, the object is a chicory stump. The method may further comprise a step of placing 3 to 6 or 6 to 12 chicory stumps by the robot, for 25 forming the final set of chicory stumps that weigh about 500 gram or 1000 gram respectively.

In an embodiment, the method further comprises a step of providing a plastic tray or a continuous plastic film for accommodating the final set of objects, for safe guarding the 30 objects from getting damaged or bruised after the sorting.

7

In an embodiment, the method further comprises a step of fully automatically picking and placing more than 1500 kg of the chicory stumps per hour to form the plurality of the final sets of objects.

5 In an embodiment of the method disclosed, the picking and placing operation by the robot is performed by a plurality of arms, such that multiple operations can be executed simultaneously.

In an embodiment, the method further comprises a step of using a plurality of the first 10 weighing means for increasing productivity.

In an embodiment, the method further comprises a step of forwarding the final set of objects by a forwarding means, for packaging.

15 In an embodiment, the method further comprises a step of calibrating the apparatus by using a representative sample comprising a plurality of the objects.

The present invention consists of certain novel features and a combination of parts hereinafter fully described and illustrated in the accompanying drawings and 20 particularly pointed out in the appended claims; it being understood that various changes in the details may be possible without departing from the scope of the invention or sacrificing any of the advantages of the present invention.

25 BRIEF DESCRIPTION OF THE DRAWINGS

In the following drawings, same reference numbers generally refer to the same parts throughout. The drawings are not necessarily to scale, instead emphasis is placed upon illustrating the principles of the invention. The various embodiments and advantages of the present invention will be more fully understood when considered with respect to the 30 following detailed description, appended claims and accompanying drawings wherein: 8 FIG. 1 illustrates a top view for the apparatus according to an embodiment of the invention.

FIG. 2 illustrates a top view for the apparatus according to an embodiment of the 5 invention, the arrangement being different from that in FIG. 1.

DETAILED DESCRIPTION

The following description presents several preferred embodiments of the present 10 invention in sufficient detail such that those skilled in the art can make and use the invention.

Before describing in detail embodiments that are in accordance with the present invention, it should be noted that all of the figures are drawn for ease of explanation of 15 the basic teachings of the present invention only. The extension of the figures with respect to the number, position, relationship and dimension of the parts of the preferred embodiment will be within the skill of the art after the following teachings of the present invention have been read and understood. Further, the exact dimensions and dimensional proportions to conform to specific force, weight, strength and similar 20 requirements will likewise be within the skill of the art after the following teachings of the present invention have been read and understood.

FIG. 1 and FIG. 2 show two embodiments of the present invention. The automatic sorting apparatus 100 is for sorting a plurality of irregularly shaped, differently sized 25 and differently weighing delicate objects 101. The apparatus 100 comprises a computation means (not shown) and a pick and place robot 125 that is communicable with the computation means. The robot 125 is shown only as a representative module. Any kind of configuration for the robot 125 may be used. The robot 125 further comprises an image recognition software (not shown) for detecting image information 30 from a supply 105 of the plurality of objects 101 wherein each object 101 is in any orientation. There may be a common supply 105 or a plurality of supplies 105 as shown. The figures show the objects 101 in each of the supplies 105 to be oriented in a 9 particular direction. However, this is not a limitation under the embodiments of the present invention. An extra step of orienting the objects 101 before the picking by the robot 125 from the supply 105 can thus be avoided, thereby increasing productivity. The software is further capable of feeding the image information to the computation means 5 for programming a grip for the robot 125 for picking and placing each object 101. The grip is programmable differently for each object 101 based on the following factors for each object 101: its type, dimensions and orientation, such that the robot 125 can perform picking and placing operation of the object 101 without causing visible bruise/damage to the object 101. The factor termed as ‘type’ may indicate the specific 10 fruit or vegetable, whether the fruit or the vegetable is raw and harder or too ripe and softer, and any other information on quality that would help in programming the grip appropriately. Bigger the dimension of the object 101, wider may the grip need to be. Based on the orientation of the object 101 in the supply 105, the robot 125 will need to adapt physically for the picking the same. The apparatus 100 is fully automatic, without 15 the need of human hands, hence improving on the productivity.

As illustrated in FIG. 1, in this embodiment, the apparatus 100 includes loading tracks 110, where the robot can place the objects in groups 115, such that the weight of each group 115 is expectedly lesser than a pre-programmed target weight range. The robot 20 125 is programmed for picking from the supply 105 and placing at least one object 101 on the loading tracks 110 to form each group 115. The loading tracks 110 are shown to be in the form of a conveyor belt system for transferring each of these groups 115 to each first weighing means 120, whereby each group 115 forms a first set 102. The weight of each first set 102 is determined automatically and is lesser than the pre-25 programmed target weight range. Alternatively, the robot 125 may be programmed for picking from the supply 105 and placing at least one object 101 directly on each of the first weighing means 120, for forming the first set 102. A plurality of the first weighing means 120 are shown for increased productivity. The first weighing means 120 then passes information on the first weight to the computation means. Multiple second 30 weighing means 130 are shown and the robot 125 is programmed for picking from the supply 105 and placing at least one object 101 into each of the second weighing means 130 to form a plurality of second sets 132. A plurality of corresponding second weights 10 are then determined and the information on the plurality of second weights can then be passed to the computation means. The computation means then selects at least one out of the plurality of second sets 132 to form a third set (not shown). The third set is then picked and placed on the first set 102 by the robot 125 to form a final set 140, such that 5 the first weight becomes within the target weight range. As may be understood by those skilled in the art, such plurality of the final sets 140 can be generated whether serially or parallel or in a mixture of both. The apparatus thus is advantageous in automatically selecting the most optimum third set, which otherwise would take much longer time if done manually.

10 As illustrated in FIG. 2, in this alternate embodiment, the apparatus 100 comprises a plurality of weighing means 150. The robot 125 is programmed for picking from the supply 105 and placing at least one object 101 on each of the plurality of weighing means 150 to form a plurality of sets 160. A plurality of weights is determined correspondingly for the plurality of sets 160 and the information on the plurality of 15 weights is automatically passed to the computation means. The computation means selects an optimum combination from the plurality of sets 160 to form a combined weight, that is within a pre-programmed target weight range. The combination can be picked and placed on a containing member 170 by the robot 125 to form a final set 140. As may be understood by those skilled in the art, such plurality of the final sets 140 can 20 be generated whether serially or parallel or in a mixture of both. The apparatus 100 thus is advantageous in automatically selecting the most optimum final set 140, which otherwise would take much longer time if done manually.

In both FIG. 1 and FIG. 2, a plurality of the final sets 140 that are formed, are shown to 25 be getting collected in a containing member 170, for packaging. Any type of the containing member 170 may be used, such as any kind of trays or boxes or conveyor means and the like, that is capable of containing the final set 140. For the embodiment of FIG. 1, each final set 140 may first be formed on a first weighing means 120 and then be transferred to the containing member 170. A forwarding means 180 such as a 30 conveyor means for forwarding the final set 140 to the containing member 170 is shown. Any other type of forwarding means 180 may equally be used. The final sets 11 140 may be forwarded by the forwarding means 180 into a continuous plastic foil (not shown), that can subsequently be used for individually wrapping the final sets 140.

In both the embodiments as aforesaid in FIG. 1 and FIG. 2, the object 101 may be a fruit 5 or a vegetable and the picking from the supply 105 may be in random order based on the image information or in an orderly fashion, such as in a predetermined direction.

In both the embodiments as aforesaid in FIG. 1 and FIG. 2, in the final set 140, the robot 125 may place each object 101 at a predetermined orientation, such that a step of 10 handling the objects 101 again for adjusting orientation before packaging can be eliminated. Reduced handling is preferred for increased productivity.

In both the embodiments as aforesaid in FIG. 1 and FIG. 2, at least a portion of the software may be a 3D line camera with built in line-scanner (not shown), that can detect 15 grey scales for recognising contours and shapes.

In both the embodiments as aforesaid in FIG. 1 and FIG. 2, the factors for programming the grip may also include colour of each object 101, where the colour of the object 101 is an indication of how delicate the object 101 is, so that the grip may be programmed 20 accordingly.

In both the embodiments as aforesaid in FIG. 1 and FIG. 2, the object 101 may be a chicory stump. Chicory stumps need delicate handling as they are prone to forming brown spots upon being damaged and bruised. The robot 125 may particularly be 25 capable of placing 3 to 6 or 6 to 12 chicory stumps to form the final set 140 that weighs about 500 gram or 1000 gram respectively, as this is a common package for sale. A combination of any other number of chicory stumps in the final set 140 having any other pre-programmed target weight range is also possible.

30 In both the embodiments as aforesaid in FIG. 1 and FIG. 2, the final set 140 may be accommodated in a foamed plastic tray (not shown) or in a continuous plastic film (not 12 shown). This is advantageous for safe guarding the objects 101 from getting bruised after the sorting.

In both the embodiments as aforesaid in FIG. 1 and FIG. 2, the apparatus 100 may 5 particularly be capable of fully automatically forming a plurality of the final sets 140, with more than 1500 kg of chicory stumps per hour.

In both the embodiments as aforesaid in FIG. 1 and FIG. 2, the robot 125 may comprise a cushioning material (not shown) on at least a portion of its exterior surface for further 10 helping prevent visible bruise or damage to the object 101 during the picking and placing operation of the object 101. The cushioning material may be at the exterior surface that comes in contact with the object 101 during the picking and placing operation.

15 In both the embodiments as aforesaid in FIG. 1 and FIG. 2, the robot 125 may preferably have a plurality of arms (not shown) for the picking and placing operation, such that multiple operations can be executed simultaneously.

In the embodiments as aforesaid in FIG. 1, the apparatus 100 may comprise a plurality 20 of the first weighing means 120 for increasing productivity.

As to further discussion of the manner of usage and operation of the present invention, the same should be apparent from the above description. Accordingly, no further discussion relating to the manner of usage and operation will be provided.

While the foregoing description presents preferred embodiments of the present 25 invention along with many details set forth for purpose of illustration, it will be understood by those skilled in the art that many variations or modifications in details of design, construction and operation may be made without departing from the present invention as defined in the claims. The scope of the invention is as indicated by the appended claims and all changes that come within the meaning and range of 30 equivalency of the claims are intended to be embraced therein.

1 0 3 8 4 0 0

Claims

An automatic sorting device, for sorting a plurality of irregularly shaped, delicate objects of different weights and different dimensions, which device comprises: calculating means, and a pack and place robot which communicates with the calculating means, which robot further comprises image recording means and comprises image recognition software for detecting image information on a supply of said plurality of objects in which each object can be located in any orientation, which software is further capable of transmitting this image information to these calculating means for programming a gripper of this robot for Picking up and placing each object, which gripper is individually programmable for each object based on the following factors for each object: type, dimensions and orientation, such that this robot can perform this picking and placing operation for each object without visible damage / injuries to this condition to cause erp. 20

2. Device as claimed in claim 1, further comprising: at least one first means for weighing, said robot being programmable to pick up at least one object from said feed so as to form a first set of objects and apply it to said weighing means so that a first weight determined by weighing this first set of objects is less than a pre-programmed target weight range, the first weighing means being further capable of sending information about the first weight to the computing means; 30 and 1038400 a plurality of second weighing means, said robot being programmable to pick up at least one object from said feed so as to form a plurality of second sets of objects and to place it on said second weighing means for determining a plurality of second weights, and to pass on the plurality of second weights to the computing means, the computing means further being able to select at least one set of objects from the plurality of second sets of objects and thus form a third set of objects, so that when this third set of objects is picked up by the robot and placed on the first set of objects to form a final set of objects, this first weight coming within the target weight range, this device being capable of producing a plurality of these last sets of objects, either serial or parallel or a com combination of both. 15

3. Device as claimed in claim 1 or 2, further comprising: a plurality of weighing means, wherein the robot is programmable to take at least one object from said supply and thus form a plurality of sets of objects and place them on each of the plurality of placing weighing means for determining a plurality of weights accordingly and for forwarding information about this plurality of weights to the computing means, said computing means being able to select an optimum combination of this plurality of sets of articles to thereby create a combined forming weight that falls within a pre-programmed target weight range such that this combination can be picked up and placed on a packaging means by the robot to form a final set of objects, the device being capable of carrying a plurality of these final sets of objects or serially or in parallel or a combin ation of both.

Device as claimed in claim 1, 2 or 3, wherein the object is a fruit.

Device as claimed in claim 1, 2 or 3, wherein the object is a vegetable.

Device as claimed in claim 1, 2 or 3, wherein the image recording means comprises a 3D line camera with a built-in line scanner, which can recognize gray shades for recognizing contours and shapes.

7. Device as claimed in claim 1, 2 or 3, wherein the factors further comprise the color of each object.

Device as claimed in claim 5, wherein the object is a chicory sprout.

9. Device as claimed in claim 8, wherein the robot is able to place 3 to 6 or 6 to 12 chicory stumps so as to form a final collection of chicory stumps that weighs approximately 500 g and 1000 g respectively

10. Device as claimed in claim 9, which is capable of fully automatically forming a plurality of final sets of chicory stumps with a rate of more than 1500 kg of chicory stumps per hour.

11. Device as claimed in claim 1, 2 or 3, wherein the robot comprises a protective material on at least a part of the outside so as to help prevent visible injuries or damage to the objects during picking up and placing of the objects.

Device according to claim 1, 2 or 3, wherein the robot comprises a plurality of arms for picking up and placing.

Device as claimed in claim 2 or 3, which comprises a plurality of first weighing means.

Device as claimed in claim 2 or 3, which comprises further transport means for transporting the final sets of articles for packaging.

Device as claimed in claim 14, wherein the transport means comprise a conveyor belt 5.

16. A method for automatically sorting a plurality of irregularly shaped, fragile objects of different weights and sizes, comprising the steps of: obtaining image information from each object in a feed of a plurality of objects by means of an image recognition software, wherein every object can be in any orientation; Automatically supplying this image information by the software to computing means; and programming a grab of the robot by the computing means for a pick and place operation, wherein the grab for each object is programmed separately based on the factors for each object: type, dimensions and orientation.

17. Method as claimed in claim 16, further comprising the steps of: operating the robot to take at least one object from the supply so as to form a first collection of objects on first weighing means; automatically determining a first weight of the first set of articles by the first weighing means, said first weight being less than a pre-programmed target weight range; automatic forwarding of information about this first weight to the calculation means; operating the robot to take at least one object from the feed so as to form a second collection of objects on second weighing means; automatically determining a plurality of second weights of the second set of objects; 10 automatic forwarding of information about this second weight to the calculating means; automatically select a collection of objects from the plurality of second collections of objects and thus form a third collection of objects, so that when this third collection of objects is picked up by the robot and placed on the first collection of objects to form a final collection of objects, this first weight comes within the target weight range; Forming a final collection of articles; and automatically repeating the above steps, either serially or in parallel, or a combination of both, to form a plurality of final collections of objects. 25

The method of claim 16 or 17, further comprising the steps of: operating the robot to take at least one item from the feed and place it on each of a plurality of weighing means; automatically determining a plurality of weights by the plurality of weighing means; Automatically forwarding information about this plurality of weights to the calculating means; 5 automatically selecting an optimum combination by the calculating means from the plurality of weighing means to form a combined weight, this combined weight falling within a pre-programmed target weight range. Forming a final collection of articles by grasping and placing this combination on packaging means by the robot; and automatically produce either serially or in parallel, or a combination of both, of a plurality of final collections of articles. 15

The method of claims 16-18, wherein the article is a fruit.

The method of claims 16-18, wherein the article is a vegetable.

A method according to claim 16 or 17, wherein the picking from the supply takes place in random order.

The method of claim 16 or 17, wherein the robot places the objects in the final set of objects in a predetermined orientation. 25

A method according to claim 16 or 17, further comprising the step of: recognizing gray shading software for recognizing contours and forming the plurality of objects by means of a 3D line camera with built-in line scanner. 30

The method of claim 16 or 17, wherein the factors further include the color of the articles.

The method of claim 20 wherein the article is a chicory sprout.

The method of claim 25 further comprising the step of: 5 placing by robot 3 to 6 or 6 to 12 chicory stumps so as to form a final set of chicory stumps that weighs about 500 g and 1000 g, respectively.

The method of claim 25, further comprising the step of: placing the chicory stumps on a plastic tray or a continuous plastic film.

A method according to claim 25, wherein fully automatic 1500 kg of chicory stumps are picked up and combined. 15

The method of claim 16 wherein a plurality of first weighing means is used.

The method of claim 16 further comprising the step of: transporting the final set of articles for packaging.

The method of claim 16, further comprising the step of: calibrating the device by means of a representative sample comprising a plurality of the objects. 25 1038400