Information processing system, information processing device, and information processing method that performs at least any one of plural kinds of image processing on a taken image
An information processing system includes an imaging unit that generates an image signal by imaging and an information processing device. The information processing device performs at least any one of plural kinds of image processing on a taken image corresponding to the image signal. The information processing device specifies an object corresponding to a partial image included in the taken image on the basis of a state of the object corresponding to the partial image included in the taken image or a degree of reliability given to a processing result of the performed image processing.
1. An information processing system comprising:
an imaging unit that generates an image signal by imaging; and
an information processing device that performs at least any one of plural kinds of image processing on a taken image corresponding to the image signal,
wherein
in a case where the degree of reliability each of the processing results of first processing that is object recognition processing using character recognition and second processing that is object recognition processing using machine learning is equal to or lower than a threshold value, the information processing device performs, on the taken image, third processing that is object recognition processing using feature matching and is different from the second processing among the plural kinds of image processing, and
in a case where the degree of reliability of the processing result of the third processing is higher than the threshold value, the information processing device specifies the object on a basis of the processing result of the third processing.
2. The information processing system according to claim 1 , wherein
at least any one of symbol recognition, machine learning, and feature matching is used in the image processing.
3. The information processing system according to claim 1 , wherein
the information processing device performs at least two of the plural kinds of image processing, gives degrees of reliability to processing results of the performed image processing, and specifies the object on a basis of a processing result given a highest degree of reliability among the processing results.
4. The information processing system according to claim 3 , wherein
in a case where a plurality of objects are detected from the taken image, the information processing device performs at least two of the plural kinds of image processing for each of partial images corresponding to the objects, gives degrees of reliability to processing results of the performed image processing, and specifies each of the objects on a basis of a processing result given a highest degree of reliability among the processing results.
5. The information processing system according to claim 1 , wherein
the information processing device performs at least two of the plural kinds of image processing, gives degrees of reliability to processing results of the performed image processing, and in a case where a highest degree of reliability is higher than a threshold value, specifies the object on a basis of a processing result given the highest degree of reliability among the processing results.
6. The information processing system according to claim 5 , wherein
in a case where a plurality of objects are detected from the taken image, the information processing device specifies each of the objects or specifies a candidate for each of the objects by performing at least two of the plural kinds of image processing for each of partial images corresponding to the objects.
7. The information processing system according to claim 1 , wherein
the information processing device performs at least two of the plural kinds of image processing, gives degrees of reliability to processing results of the performed image processing, and in a case where a highest degree of reliability is equal to or lower than a threshold value, specifies a candidate for the object on a basis of a processing result given the highest degree of reliability among the processing results.
8. The information processing system according to claim 7 , wherein
in a case where a plurality of objects are detected from the taken image, the information processing device specifies each of the objects or specifies a candidate for each of the objects by performing at least two of the plural kinds of image processing for each of partial images corresponding to the objects.
9. The information processing system according to claim 1 , wherein
in a case where a plurality of objects are detected from the taken image, the information processing device sequentially performs the first processing, the second processing, and the third processing for each of partial images corresponding to the objects.
10. The information processing system according to claim 1 , wherein
in a case where an object in a predetermined state is detected from the taken image, the information processing system specifies the object by performing image processing according to the predetermined state among the plural kinds of image processing on a partial image corresponding to the object.
11. The information processing system according to claim 10 , wherein
in a case where an overlapping object is detected from the taken image, the information processing device specifies the object by performing second processing that is object recognition processing using machine learning among the plural kinds of image processing on a partial image corresponding to the object.
12. The information processing system according to claim 10 , wherein
in a case where a deformed object is detected from the taken image, the information processing device specifies the object by performing third processing that is object recognition processing using feature matching among the plural kinds of image processing on a partial image corresponding to the object.
13. The information processing system according to claim 10 , wherein
in a case where an object detected from the taken image is not an overlapping object nor a deformed object, the information processing device specifies the object by performing first processing that is object recognition processing using character recognition among the plural kinds of image processing on a partial image corresponding to the object.
14. The information processing system according to claim 10 , wherein
in a case where a plurality of objects are detected from the taken image, the information processing device specifies each of the objects by performing image processing according to a state of the object among the plural kinds of image processing on a corresponding partial image.
15. The information processing system according to claim 1 , further comprising a placing table on which an item that is the object is placed,
wherein the imaging unit is disposed so as to be capable of imaging a placing surface of the placing table.
16. An information processing device comprising:
a communication unit that is communicable with an imaging unit that generates an image signal by imaging; and
a control unit that causes the communication unit to acquire a taken image corresponding to the image signal and performs at least any one of plural kinds of image processing on the acquired taken image,
wherein
in a case where the degree of reliability each of the processing results of first processing that is object recognition processing using character recognition and second processing that is object recognition processing using machine learning is equal to or lower than a threshold value, the control unit performs, on the taken image, third processing that is object recognition processing using feature matching and is different from the second processing among the plural kinds of image processing, and
in a case where the degree of reliability of the processing result of the third processing is higher than the threshold value, the control unit specifies the object on a basis of the processing result of the third processing.
17. An information processing method comprising:
generating an image signal by imaging;
acquiring a taken image corresponding to the image signal and performing at least any one of plural kinds of image processing on the acquired taken image;
in a case where the degree of reliability each of the processing results of first processing that is object recognition processing using character recognition and second processing that is object recognition processing using machine learning is equal to or lower than a threshold value, performing, on the taken image, third processing that is object recognition processing using feature matching and is different from the second processing among the plural kinds of image processing; and
in a case where the degree of reliability of the processing result of the third processing is higher than the threshold value, specifying the object on a basis of the processing result of the third processing.