CPC G06V 10/82 (2022.01) [G06F 18/214 (2023.01); G06N 3/045 (2023.01); G06V 20/62 (2022.01); G06V 30/10 (2022.01); G06V 30/41 (2022.01)] | 18 Claims |
1. A character recognition method, comprising:
performing a feature extraction on an image to be recognized to obtain a first feature map; the image to be recognized including at least one character and at least one character carrier; the first feature map carrying features of the at least one character carrier and the at least one character;
processing the first feature map to at least obtain N first candidate carrier detection boxes; each first candidate carrier detection box being configured to outline a region of a character carrier in the at least one character carrier; N being a positive integer;
screening the N first candidate carrier detection boxes to obtain K first target carrier detection boxes; K being a positive integer, and K being less than or equal to N;
performing a feature extraction on the first feature map to obtain a second feature map; the second feature map carrying at least one feature of at least one character;
processing the second feature map to obtain L first candidate character detection boxes; each first candidate character detection box being configured to outline a region containing at least one character; L being a positive integer;
screening the L first candidate character detection boxes to obtain J first target character detection boxes according to the K first target carrier detection boxes; J being a positive integer, and J being less than or equal to L; and
recognizing characters in the J first target character detection boxes to obtain J target character informations.
|