Information processing apparatus, system, and control method for acquiring character string to sort articles
According to an embodiment, the information processing apparatus includes an image interface, an input interface, a communication interface, and a processor. The image interface is configured to acquire a display screen image from an input device for inputting a character string included in a captured image in which recognition of the character string according to a first algorithm fails. The processor is configured to search for the captured image corresponding to the display screen image, acquire the character string based on a result of character recognition processing of the searched for captured image according to a second algorithm, and input the character string to the input device.
1 . An information processing apparatus comprising:
a processor configured to:
acquire, through a capture board and from an image input device, a display screen image, the display screen image being generated by the image input device based on a first captured image of a plurality of captured images output from an image acquisition device, wherein recognition of a character string included in the first captured image according to a first algorithm fails, and a resolution of the display screen image is lower than a resolution of the first captured image;
acquire, from the image acquisition device through a communication interface, a subset of the plurality of captured images output from the image acquisition device as search candidates based on a time at which the display screen image was acquired, the subset of captured images being captured in an estimation period, the estimation period being a duration of time between a predetermined time preceding a capture time and another predetermined time elapsed from the capture time, wherein the capture time is a time at which the first captured image was captured, wherein the capture time is determined based on the time at which the display screen image was acquired;
search the search candidates for a second captured image that matches the display screen image based on a degree of similarity of the images;
acquire the character string included in the first captured image based on a result of the character recognition processing of the second captured image according to a second algorithm different from the first algorithm; and
input the character string to the image input device through an input interface.
2 . The information processing apparatus according to claim 1 , wherein the processor is further configured to:
transmit and receive data to and from a recognition apparatus through the communication interface, and
the processor is configured to acquire the second captured image and the character string based on the result of the character recognition processing of the second captured image from the recognition apparatus through the communication interface.
3 . The information processing apparatus according to claim 1 , wherein an image resolution of the character string included in the display screen image is lower than an image resolution of the character string included in the second captured image.
4 . The information processing apparatus according to claim 1 , wherein the processor is configured to input an operation signal indicating a key input operation for inputting the character string through the input interface.
5 . The information processing apparatus according to claim 1 , comprising:
an operation unit interface connected to an operation unit; and
a display interface connected to a display,
wherein the processor is configured to, if the processor fails to find the second captured image that matches the first captured image corresponding to the display screen image, display the display screen image on the display through the display interface, and input an operation signal indicating an operation that is input to the operation unit to the image input device through the input interface.
6 . The information processing apparatus according to claim 1 , wherein
the first captured image is an image obtained by capturing an image of a surface of an article on which a destination is written, and
the processor is configured to input the destination as the character string through the input interface.
7 . A system comprising a recognition apparatus and an information processing apparatus, wherein
the recognition apparatus includes a first processor configured to:
acquire a plurality of captured images from an image acquisition device through an image acquisition device interface;
transmit and receive data to and from the information processing apparatus through a first communication interface;
perform character recognition processing on the plurality of captured images according to a second algorithm different from a first algorithm; and
transmit the plurality of captured images and character strings based on a result of the character recognition processing to the information processing apparatus through the first communication interface, and
the information processing apparatus includes a second processor configured to:
acquire, through a capture board and from an image input device, a display screen image, the display screen image being generated by the image input device based on a first captured image of the plurality of captured images output from the image acquisition device, wherein recognition of a character string included in the first captured image according to the first algorithm fails, and a resolution of the display screen image is lower than a resolution of the first captured image;
transmit and receive data to and from the recognition apparatus through a second communication interface;
acquire a subset of the plurality of captured images as search candidates from the recognition apparatus through the second communication interface based on a time at which the display screen image was acquired, the subset of captured images being captured in an estimation period, the estimation period being a duration of time between a predetermined time preceding a capture time and another predetermined time elapsed from the capture time, wherein the capture time is a time at which the first captured image was captured, wherein the capture time is determined based on the time at which the display screen image was acquired;
search the search candidates for a second captured image that matches the display screen image based on a degree of similarity of the images;
acquire the character string included in the first captured image based on the result of the character recognition processing of the second captured image from the recognition apparatus through the second communication interface; and
input the character string to the image input device through an input interface.
8 . A control method executed by a processor, the method comprising:
performing character recognition processing on the plurality of captured images according to a second algorithm different from a first algorithm;
acquiring a display screen image from an image input device and through a capture board, the display screen image being generated by the image input device based on a first captured image of a plurality of captured images output from an image acquisition device, wherein recognition of a character string included in the first captured image according to the first algorithm fails, and a resolution of the display screen image is lower than a resolution of the first captured image;
acquiring, from the image acquisition device, a subset of the plurality of captured images as search candidates based on a time at which the display screen image was acquired, the subset of captured images being captured in an estimation period, the estimation period being a duration of time between a predetermined time preceding a capture time and another predetermined time elapsed from the capture time, wherein the capture time is a time at which the first captured image was captured, wherein the capture time is determined based on the time at which the display screen image was acquired;
searching search candidates for a second captured image that matches the display screen image based on a degree of similarity of the images;
acquiring a character string included in the first captured image based on a result of the character recognition processing of the second captured image according to the second algorithm; and
inputting, to the image input device, the character string based on a result of the character recognition processing of the searched for captured image.