Character recognition using candidate frames to determine character location
First Claim
1. A character recognition method comprising the steps of:
- obtaining, from an input binary-quantized image, an input pattern of plural rectangles, each rectangle having a rectangle position and circumscribing a respective character-bearing area;
collectively comparing, for each of plural candidate frames, the rectangle positions of the plural rectangles of the input pattern with respective plural predetermined rectangle positions of the plural candidate frames;
selecting one of the candidate frames having the least inconformity with the input pattern as a selected candidate frame; and
then recognizing characters in the input pattern based on the rectangle positions of the selected candidate frame.
1 Assignment
0 Petitions
Accused Products
Abstract
A character recognition method for recognizing characters on an article having multiple character-bearing areas, such as a license plate, first involves obtaining image data from an image of the article. The method then assigns at least one parameter to a selected character-bearing area on the article. The method then attempts to obtain a correct frame which expresses the correct positional relationship between the selected character-bearing area on the article with other character-bearing areas of the article, and then uses that correct frame to perform character recognition with respect to each of the character-bearing areas of the article. To obtain the correct frame, the invention compares the image data of the article with plural candidate frames. The plural candidate frames are calculated using the predetermined positional correlation between (1) the selected character-bearing area [as represented by the at least one parameter] and (2) other character-bearing areas of the article.
35 Citations
12 Claims
-
1. A character recognition method comprising the steps of:
-
obtaining, from an input binary-quantized image, an input pattern of plural rectangles, each rectangle having a rectangle position and circumscribing a respective character-bearing area;
collectively comparing, for each of plural candidate frames, the rectangle positions of the plural rectangles of the input pattern with respective plural predetermined rectangle positions of the plural candidate frames;
selecting one of the candidate frames having the least inconformity with the input pattern as a selected candidate frame; and
thenrecognizing characters in the input pattern based on the rectangle positions of the selected candidate frame. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
for each candidate frame;
calculating a degree of inconformity with respect to each rectangle position in the input pattern, determining a total of the calculated inconformity values over all rectangle positions of the input pattern, and using the total to select the selected candidate frame.
-
-
3. A character recognition method as defined in claim 1, wherein the step of recognizing characters includes recognizing a string of characters by selecting a character string having a largest average value of similarity of component characters.
-
4. The method of claim 1, wherein the input pattern is obtained from an article having multiple character-bearing areas circumscribed by respective ones of the plural rectangles, and wherein the method further comprises:
-
assigning at least one parameter to a selected character-bearing area on the article;
calculating the plural candidate frames using a predetermined positional correlation between the selected character-bearing area as represented by the at least one parameter and other character-bearing areas of the article.
-
-
5. The method of claim 4, further comprising assigning a position parameter and a width parameter to the selected character-bearing area.
-
6. The method of claim 4, wherein the at least one parameter is assigned by iterating between a maximum and a minimum value of the at least one parameter, and wherein for each iterated value of the parameter the comparing step is performed with the candidate frames being prepared using the predetermined positional correlation between the selected character-bearing area as represented by the iterated value of the parameter and the other character-bearing areas of the article, and wherein the correct frame is obtained considering all iterations of the parameter.
-
7. The method of claim 6, wherein the iterated at least one parameter is area width.
-
8. The method of claim 4, wherein the comparing step involves determining a degree of inconformity of each of the plural candidate frames with respect to predetermined criteria.
-
9. The method of claim 8, wherein the predetermined criteria includes criteria pertaining to plural ones of the character-bearing areas.
-
10. The method of claim 8, wherein the correct frame has a least inconformity with respect to each of the character-bearing areas.
-
11. The method of claim 1, wherein the input image is obtained from a license plate.
-
12. The method of claim 11, wherein the selected character-bearing area is in a predetermined portion of the license plate.
Specification