Image processing device, image processing method, and storage medium storing program
An image processing device including: a first feature quantity selecting unit configured to select a first feature quantity of a document image that is a character recognition target among first feature quantities that are recoded in advance and represent features of character strings of an item; a character recognition processing unit configured to perform a character recognition process for the document image; a character string selecting unit configured to select a character string of a specific item corresponding to the first feature quantity among the character strings acquired as a result of the character recognition process; and a determination result acquiring unit configured to acquire a determination result indicating whether or not a character string that has been input in advance matches the character string of the specific item in a case in which the character string selecting unit has not selected any one of the character strings.
1. An image processing device comprising:
at least one memory configured to store instructions; and
at least one processor configured to execute the instructions to:
select a first feature quantity for a document image that is a character recognition target among first feature quantities that are recorded in advance based on a result of a character recognition process for a plurality of document images and represent position information of character strings of an item in the plurality of document images for each type of the document images and for each item;
perform a character recognition process for the document image that is the character recognition target;
select the character string of the item based on a comparison of the position information of the first feature quantity with position information of the character string that is acquired in the document image among the character strings acquired by the character recognition process; and
present the document image representing a position of the character string of the item that is acquired by the character recognition process and a character string of the item that has been input in advance, and acquire a determination result indicating whether or not the character string that has been input in advance of the item matches the character string of the item that is acquired by the character recognition process,
wherein the at least one processor is configured to execute the instructions to present, to a user, the document image representing the position of the character string of the item and the character string that has been input in advance, and acquire the determination result determined by the user, wherein the determination result indicates whether or not the character string of the item appearing in the document image matches the character string that has been input in advance.
2. The image processing device according to claim 1 ,
wherein the at least one processor is further configured to execute the instructions to:
perform, using the character string that has been input in advance, machine learning for acquiring the first feature quantity used for selecting the character string of the item among the character strings acquired by the character recognition process in a case in which none of the character strings acquired by the character recognition process are selected as the character string of the item, and the determination result indicates of the item that the character string that has been input in advance matches the character string of the item acquired by the character recognition process.
3. The image processing device according to claim 2 ,
wherein the at least one processor is configured to execute the instructions to:
perform the machine learning in any one of a case in which any one of the character strings acquired by the character recognition process is selected as the character string of the item and a case in which none of the character strings acquired by the character recognition process are selected as the character string of the item.
4. The image processing device according to claim 2 ,
wherein the at least one processor is configured to execute the instructions to:
perform the machine learning in a case in which none of the character strings acquired by the character recognition process are selected as the character string of the item, and suppress execution of the machine learning in a case in which any one of the character strings acquired by the character recognition process is selected as the character string of the item.
5. An image processing method comprising:
selecting a first feature quantity for a document image that is a character recognition target among first feature quantities that are recorded in advance based on a result of a character recognition process for a plurality of document images and represent position information of character strings of an item in the plurality of document images for each type of the document images and for each item;
performing a character recognition process for the document image that is the character recognition target;
selecting the character string of the item based on a comparison of the position information of the first feature quantity with position information of the character string that is acquired in the document image among the character strings acquired by the character recognition process; and
presenting the document image representing a position of the character string of the item that is acquired by the character recognition process and a character string of the item that has been input in advance, and acquiring a determination result indicating whether or not the character string that has been input in advance of the item matches the character string of the item that is acquired by the character recognition process,
wherein the presenting includes presenting, to a user, the document image representing the position of the character string of the item and the character string that has been input in advance, and
the acquiring includes acquiring the determination result determined by the user, wherein the determination result indicates whether or not the character string of the item appearing in the document image matches the character string that has been input in advance.
6. A non-transitory computer-readable storage medium storing a program causing a computer to execute processes comprising:
selecting a first feature quantity for a document image that is a character recognition target among first feature quantities that are recorded in advance based on a result of a character recognition process for a plurality of document images and represent position information of character strings of an item in the plurality of document images for each type of the document images and for each item;
performing a character recognition process for the document image that is the character recognition target;
selecting the character string of the item based on a comparison of the position information of the first feature quantity with position information of the character string that is acquired in the document image among the character strings acquired by the character recognition process; and
presenting the document image representing a position of the character string of the item that is acquired by the character recognition process and a character string of the item that has been input in advance, and acquiring a determination result indicating whether or not the character string that has been input in advance of the item matches the character string of the item that is acquired by the character recognition process,
wherein the presenting includes presenting, to a user, the document image representing the position of the character string of the item and the character string that has been input in advance, and
the acquiring includes acquiring the determination result determined by the user, wherein the determination result indicates whether or not the character string of the item appearing in the document image matches the character string that has been input in advance.