Method and system for detection and classification of license plates
View Patent ↗Methods, systems, and processor-readable media for the detection and classification of license plates. In an example embodiment, an image of a vehicle can be captured with an image-capturing unit. A license plate region can then be located in the captured image of the vehicle by extracting a set of candidate regions from the image utilizing a weak classifier. A set of candidate regions can be ranked utilizing a secondary strong classifier. The captured image can then be classified according to a confidence driven classification based on classification criteria determined by the weak classifier and the secondary strong classifier.
1. A method for the detection and classification via an image processor of license plates displayed in images captured by an image-capturing unit, said method comprising:
capturing an image of a vehicle utilizing an image-capturing unit that communicates with an image processor;
locating a license plate region in said image of said vehicle after capturing said image with said image-capturing unit by extracting a set of candidate regions from said image utilizing a weak classifier of said image processor;
ranking said set of candidate regions utilizing a secondary strong classifier of said image processor; and
classifying said image according to a confidence driven classification based on classification criteria determined by said weak classifier and said secondary strong classifier, thereby automatically identifying and eliminating un-readable images from human review.
2. The method of claim 1 wherein said weak classifier comprises a fast classifier.
3. The method of claim 1 wherein said secondary strong classifier comprises a slow classifier.
4. The method of claim 1 wherein said secondary strong classifier comprises a neural network.
5. The method of claim 4 wherein said neural network comprises a CNN (Convolutional Neural network).
6. The method of claim 1 wherein classifying said image according to a confidence driven classification based on classification criteria determined by said weak classifier and said secondary strong classifier, further comprises:
classifying said image according to a confidence driven classification to exclude said image from review based on classification criteria determined by said weak classifier and said secondary strong classifier.
7. The method of claim 1 wherein said classification criteria with respect to said image comprises classification data indicative of at least one of the following:
a license plate not present in said image;
a license plate in said image is too bright;
a license plate in said image is too dark;
a vehicle in said image is not found;
a license plate in said image is too blurry;
a license plate in said image is obstructed; or
a license plate is present and readable.
8. A system for the detection and classification via an image processor of license plates displayed in images captured by an image-capturing unit, said system comprising:
an image processor; and
a computer-usable medium embodying computer program code, said computer-usable medium capable of communicating with said at least one processor, said computer program code comprising instructions executable by said image processor and configured for:
capturing an image of a vehicle utilizing an image-capturing unit that communicates with an image processor;
locating a license plate region in said image of said vehicle after capturing said image with said image-capturing unit by extracting a set of candidate regions from said image utilizing a weak classifier of said image processor;
ranking said set of candidate regions utilizing a secondary strong classifier of said image processor; and
classifying said image according to a confidence driven classification based on classification criteria determined by said weak classifier and said secondary strong classifier, thereby automatically identifying and eliminating un-readable images from human review.
9. The system of claim 8 wherein said weak classifier comprises a fast classifier.
10. The system of claim 8 wherein said secondary strong classifier comprises a slow classifier.
11. The system of claim 8 wherein said secondary strong classifier comprises a neural network.
12. The system of claim 11 wherein said neural network comprises a CNN (Convolutional Neural network).
13. The system of claim 8 wherein said instructions for classifying said image according to a confidence driven classification based on classification criteria determined by said weak classifier and said secondary strong classifier, further comprises instructions configured for:
classifying said image according to a confidence driven classification to exclude said image from review based on classification criteria determined by said weak classifier and said secondary strong classifier.
14. The system of claim 9 wherein said classification criteria with respect to said image comprises classification data indicative of at least one of the following:
a license plate not present in said image;
a license plate in said image is too bright;
a license plate in said image is too dark;
a vehicle in said image is not found;
a license plate in said image is too blurry;
a license plate in said image is obstructed; or
a license plate is present and readable.
15. A non-transitory processor-readable medium storing computer code representing instructions to cause a process for detecting and classifying via an image processor license plates displayed in images captured by an image capturing unit, said computer code comprising code to:
capture an image of a vehicle utilizing an image-capturing unit that communicates with an image processor;
locate a license plate region in said image of said vehicle after said capture of said image with said image-capturing unit by extracting a set of candidate regions from said image utilizing a weak classifier of said image processor;
rank said set of candidate regions utilizing a secondary strong classifier of said image processor; and
classify said image according to a confidence driven classification based on classification criteria determined by said weak classifier and said secondary strong classifier, thereby automatically identifying and eliminating un-readable images from human review.
16. The processor-readable medium of claim 15 wherein said weak classifier comprises a fast classifier.
17. The processor-readable medium of claim 15 wherein said secondary strong classifier comprises a slow classifier.
18. The processor-readable medium of claim 15 wherein said secondary strong classifier comprises a neural network.
19. The processor-readable medium of claim 15 wherein said code to classify said image according to a confidence driven classification based on classification criteria determined by said weak classifier and said secondary strong classifier, further comprises code to:
classify said image according to a confidence driven classification to exclude said image from review based on classification criteria determined by said weak classifier and said secondary strong classifier.
20. The processor-readable medium of claim 15 wherein said classification criteria with respect to said image comprises classification data indicative of at least one of the following:
a license plate not present in said image;
a license plate in said image is too bright;
a license plate in said image is too dark;
a vehicle in said image is not found;
a license plate in said image is too blurry;
a license plate in said image is obstructed; or
a license plate is present and readable.