Checkout counter
A classification device ( 2 ) for identification of articles ( 3 ) in an automated checkout counter is presented. The device comprises a memory unit ( 5 ) capable of storing digital reference signatures, each of which digital reference signatures corresponds to an article identity, a processor ( 6 ) connected to the memory unit ( 5 ), and at least one sensor ( 4, 7, 14, 15, 16, 17, 18, 24 ) configured to determine a measured signature of an article ( 3 ) wherein said processor ( 6 ) is configured to compare said measured signature with the digital reference signatures, and to calculate a matching probability of a predetermined number of article identities.
1. A classification device for identification of articles in an automated checkout counter, comprising:
a memory unit capable of storing digital reference signatures, each of which digital reference signatures corresponds to an article identity,
a processor connected to the memory unit, and
at least two different sensors configured to determine a measured signature of an article, wherein at least one said sensor is a spectroscopy sensor in the form of a spectrometer configured to operate in a wave length interval of 850-2500 nm, wherein the measured signature determined from the at least one sensor is a digital representation of a reflectance spectrum in the wave length interval;
wherein said processor is configured to compare said measured signature with the digital reference signatures, and to calculate a matching probability of a predetermined number of article identities, wherein the processor is configured to determine the article identities by comparing the matching probability from the different sensors and selecting the article identities having the highest matching probability from at least one of the different sensors regardless of whether any of the article identities associated with the different sensors are the same.
2. The classification device according to claim 1 , wherein said spectrometer is a single array spectrometer.
3. The classification device according to claim 1 , further comprising a further sensor being selected from the group consisting of: a spectroscopy sensor, a contour sensor, a barcode reader, a symbol reading sensor, a color texture sensor, a color histogram sensor, or a scale.
4. The classification device according to claim 1 , comprising at least two different sensors, wherein said processor is configured to determine specific article identities by comparing the matching probability from the different sensors, and selecting the article identities having the highest matching probability.
5. The classification device according to claim 1 , wherein the classification device is incorporated in to an automated checkout counter.
6. A method for classifying articles in an automated checkout counter, comprising the steps of:
providing a classification device comprising a memory unit capable of storing digital reference signatures, each of which digital reference signatures corresponds to an article identity, a processor connected to the memory unit, and at least two different sensors configured to determine a measured signature of an article, wherein said sensor is a spectroscopy sensor in the form of a spectrometer configured to operate in a wave length interval of 850-2500 nm, wherein the measured signature determined from the at least one sensor is a digital representation of a reflectance spectrum in the wave length interval,
comparing said measured signature with the digital reference signatures
calculating a matching probability of a predetermined number of article identities; and
determining the article identities by comparing the matching probability from the different sensors and selecting the article identities having the highest matching probability from at least one of the different sensors regardless of whether any of the article identities associated with the different sensors are the same.
7. The method according to claim 6 , further comprising:
comparing the highest matching probability with an alarm threshold and, in case the highest matching probability is below the alarm threshold, awaiting manual input before proceeding.
8. The method according to claim 7 , further comprising:
comparing the highest matching probability with a two alarm threshold,
in case the highest matching probability is below the lowest alarm threshold, awaiting manual input from an attendant before proceeding, and
in case the highest matching probability is above the lowest alarm threshold but below the upper alarm threshold, awaiting manual input from a user before proceeding.
9. The method according to claim 7 , wherein the step of comparing the highest matching probability with an alarm threshold comprises the step of comparing the weight of the article with a weight interval associated with the article identity corresponding to the reference signature having the highest matching probability.
10. The method according to claim 7 , wherein the step of comparing the highest matching probability with an alarm threshold comprises the step of comparing the shape of the article with a shape interval associated with the article identity corresponding to the reference signature having the highest matching probability.
11. The method according to claim 7 , wherein the step of comparing the highest matching probability with an alarm threshold comprises the step of scanning a barcode of the article and comparing the information of the scanned barcode with barcode information associated with the article identity corresponding to the reference signature having the highest matching probability.