A method of processing poultry portions determines at a control unit a target weight of a cut poultry portion; inspects a poultry portion using an inspection unit to determine a mass distribution of said poultry portion and providing said mass distribution to the control unit; calculates a cutting plan of the poultry portion based on the target weight and the mass distribution using the control unit; uses a mechanical gripper so as to grip the poultry portion and arrange said poultry portion for execution of the cutting plan; and cuts the poultry portion using a cutting unit in accordance with the cutting plan so as to produce a cut poultry portion in accordance with the target weight. A system for processing poultry portions is configured to perform the foregoing method, among others.

A method and device for detection of bone in meat identifies fragments larger than about 1 mm using spectral optical imaging and ultrasound. Spectral imaging can detect foreign material proximate to the surface and ultrasound can detect material within the sample. The sample is irradiated by light and reflected light or Raman scattered light measured. The sample is similarly irradiated by ultrasound and reflected or transmitted sound waves give a set of amplitude data points, which include temporal delay. These data points are then processed by statistical methods to derive a set of vectors in n-dimensional space, which are compared to a calibrated data set of derived vectors which have distinct identifying loci for each type of surface, are indicative of the presence or absence of defects.

According to this feature point recognition system (1), data of a feature point of a first group obtained by a first algorithm calculation unit (12) with no mask processing is compared with data of a feature point of a second group detected by a third algorithm calculation unit (16) obtained through mask processing performed by a second algorithm calculation unit (14), whether the data is abnormal is determined, and thereby feature points of a subject P can be recognized more accurately and stably than in the related art.

A system includes an engagement tool (100) having a suction device (224), a movement system (166) configured to move the engagement tool (100), an imaging system (316) configured to capture an image of a surface of a meat product (202), and a computing device. The computing device is configured to (i) determine, from the image of the surface of the meat product (202), a target region (2061) on the surface of the meat product (202) based on an estimated fat content in the meat product (202) at the target region (2061), (ii) cause the movement system to move the engagement tool (100) with respect to the meat product (202) such that the suction device (224) engages the target region (2061), and (iii) initiate a vacuum within the suction device (224) such that the engagement tool (100) exerts a force on the target region of the surface of the meat product (202) at the suction device (224).

An animal ribcage primal cut having a bone array located therein is portioned into one or more sub primal cuts, each having at least one bone located therein. The primal cut is scanned at scanning station 14 while being conveyed on a conveyor 12 to determine the physical characteristics of the primal cut. A processor 18 determines how to portion the primal cut into desired sub primal cuts in accordance with desired physical characteristics of the sub primal cut and production requirements for the sub primal cuts. A controller controls a cutter to divide the primal cut into one or more sub primal cuts according to the determination previously made on how to portion the primal cut into desired sub primal cuts.

An image processing device acquires an image in which a subject having a predetermined posture and a predetermined shape is visualized, a first reference image in which the subject having a first posture of which a relationship with the predetermined posture is known and a first shape of which a relationship with the predetermined shape is known is visualized, and a second reference image in which the subject having at least one of a second posture different from the predetermined posture and a second shape different from the predetermined shape is visualized, extract feature data indicating a feature of the subject visualized in the image, extract first reference data indicating a feature of the subject visualized in the first reference image, extract second reference data indicating a feature of the subject visualized in the second reference image, identify a position at which the feature indicated by the feature data is located in the first reference image using the first reference data, and identify a position at which the feature indicated by the feature data is located in the subject having at least one of the second posture and the second shape using at least one of a relationship between the first posture and the second posture and a relationship between the first shape and the second shape.

A method of estimating weight of food objects, includes training an artificial neural network software module, and using the trained artificial neural network software module to provide a weight correlated data estimate for said food object based on a three-dimensional image of the food object

A method and system are provided for automatically portioning workpieces, such as food products, by simulating portioning the workpieces in accordance with the one or more desired shapes of the final piece(s) as a directly controlled physical characteristic (parameter/specification) as well as one or more resulting indirectly controlled physical characteristics (parameters/specifications). The desired shape(s) of the final piece(s) are defined by a plurality of manipulatable reference coordinates. A workpiece is scanned to obtain scanning information, then portioning of the workpiece is simulated in accordance with the desired shape(s) of the final piece(s) defined by the directly controlled reference coordinates, thereby to determine the one or more indirectly controlled physical characteristics of the one or more final pieces to be portioned from the workpiece. The simulated portioning of the workpiece is performed for multiple combinations of directly controlled shapes as defined by the modified or edited reference coordinates and indirectly controlled physical characteristics until an acceptable set of a directly controlled shape and resulting one or more indirectly controlled physical characteristics is determined.

A method and a system provide a feedback data indicating quality of a food processing performed by an operator. The method and system involve acquiring at least one image data of a food product from an operator; and processing the acquired image data. The processing includes detecting whether undesired objects are present in the food product, obtaining, in case undesired objects are detected, position data of the undesired objects within the food product, and utilizing the position data in issuing a feedback indicator indicating a position where the detected undesired objects are present within the food product processed by the operator.

A food processing device comprising a conveyor, a processor configured for receiving image data representing images of the food items, and a plurality of workstations arranged along the conveyor system. The avoid time consuming processing of food items, the processor is configured to provide a processing indicator which indicates whether the food items need further processing or not and the device comprises an identification structure configured to identify food items which are selected for further processing such that they are distinguished from food items not being selected for further processing based on the processing indicator.