Image processing apparatus for extracting a desired character string from a scanned image
In the case of learning a printed character region selected by a user, it is determined whether a handwritten character region is present near the printed character region. If it is determined that the handwritten character region is present near the printed character region, information about the handwritten character region present near the printed character region and information about another printed character region present near the printed character region are learned in association with information about the selected printed character region. This makes it possible to appropriately determine a circled character string and a character string selected with a check mark from among a plurality of options during a scanned image analysis.
1. An image processing apparatus comprising:
at least one memory that stores a program; and
at least one processor that executes the program to perform:
obtaining a plurality of regions including a printed character region and a handwritten character region from a first scanned image;
learning information about a region selected by a user from among the plurality of regions obtained; and
outputting a character string of a corresponding region in a second scanned image similar to the first scanned image based on the learned information,
wherein, in the learning, in a case where the region selected by the user is the printed character region, it is determined whether the handwritten character region is present near the selected printed character region, and in a case where it is determined that the handwritten character region is present near the selected printed character region, information about the handwritten character region present near the selected printed character region and information about another printed character region present near the selected printed character region are learned in association with information about the selected printed character region.
2. The image processing apparatus according to claim 1 , wherein the handwritten character region present near the selected printed character region is a handwritten symbol region surrounding the selected printed character region.
3. The image processing apparatus according to claim 1 , wherein the handwritten character region present near the selected printed character region is a handwritten check mark region in a checkbox present near the selected printed character region.
4. The image processing apparatus according to claim 1 ,
wherein, in a case where information about the handwritten character region present near the selected printed character region is learned in association with the selected printed character region, it is determined in the outputting whether the second scanned image includes the handwritten character region corresponding to the handwritten character region associated with the learned printed character region,
wherein, in a case where it is determined in the outputting that the second scanned image includes the handwritten character region corresponding to the handwritten character region associated with the learned printed character region, a character string corresponding to the learned printed character region in the second scanned image is output, and
wherein, in a case where it is determined in the outputting that the second scanned image includes no handwritten character region corresponding to the handwritten character region associated with the learned printed character region, a handwritten character region corresponding to another printed character region associated with the learned printed character region is searched, and in a case where the handwritten character region corresponding to the other printed character region is found, a character string corresponding to the other printed character region is output.
5. The image processing apparatus according to claim 1 , wherein in a case where the output character string is corrected by the user, the at least one processor further performs relearning based on the corrected content.
6. An image processing method comprising:
obtaining a plurality of regions including a printed character region and a handwritten character region from a first scanned image;
learning information about a region selected by a user from among the plurality of regions obtained; and
outputting a character string of a corresponding region in a second scanned image similar to the first scanned image based on the learned information,
wherein, in the learning, in a case where the region selected by the user is the printed character region, it is determined whether the handwritten character region is present near the selected printed character region, and in a case where it is determined that the handwritten character region is present near the selected printed character region, information about the handwritten character region present near the selected printed character region and information about another printed character region present near the selected printed character region are learned in association with information about the selected printed character region.
7. A non-transitory computer-readable storage medium storing a program for causing a processor of an information processing apparatus to perform:
obtaining a plurality of regions including a printed character region and a handwritten character region from a first scanned image;
learning information about a region selected by a user from among the plurality of regions obtained; and
outputting a character string of a corresponding region in a second scanned image similar to the first scanned image based on the learned information,
wherein, in the learning, in a case where the region selected by the user is the printed character region, it is determined whether the handwritten character region is present near the selected printed character region, and in a case where it is determined that the handwritten character region is present near the selected printed character region, information about the handwritten character region present near the selected printed character region and information about another printed character region present near the selected printed character region are learned in association with information about the selected printed character region.