Determining images having unidentifiable license plates

• US 10,657,370 B2
• Filed: 06/07/2019
• Issued: 05/19/2020
• Est. Priority Date: 04/11/2013
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Johansson, Per Olof
• Primary Examiner(s): Lu, Tom Y
• Application Number:
  US16/434,657
• Publication Number:
  US 20190286903A1
• Time in Patent Office: 347 Days
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06V 10/987 with the intervention of an operator
• CPC Class Codes: G06V 20/20 in augmented reality scenes
• CPC Class Codes: G06V 20/62 Text, e.g. of license plates, overlay texts or captions on TV images
• CPC Class Codes: G06V 20/625 License plates

Abstract

An approach for processing an image is presented. A category specifying characteristics of a shape of a license plate of a vehicle is determined. Characteristics of objects in the image are determined to match the characteristics of the shape. The image is determined to include the license plate and an identifier. A category specifying characteristics of an order of alphanumeric characters in the identifier is determined. Characteristics of the objects in the image are determined to not match the characteristics of the order of the alphanumeric characters in the identifier and based on the lack of a match, the image is determined to not include an identifiable license plate. Responsive to determining the image does not include the identifiable license plate, the image is determined to be invalid and a manual character recognition process for determining identifiers on license plates is bypassed.

Claims

1. A method of processing an image, the method comprising the steps of:

a computer determining a category specifying characteristics of a shape of a license plate of a vehicle;

based on the category specifying the characteristics of the shape of the license plate, the computer determining characteristics of objects in the image match the characteristics of the shape of the license plate;

the computer determining the image includes the license plate and an identifier included in the license plate;

the computer determining a category specifying characteristics of an order of alphanumeric characters in the identifier, the order required to be a characteristic of identifiable license plates;

based on the category specifying the characteristics of the order of the alphanumeric characters in the identifier, the computer determining characteristics of the objects in the image do not match the characteristics of the order of the alphanumeric characters in the identifier;

based on the characteristics of the objects in the image not matching the characteristics of the order of the alphanumeric characters in the identifier, the computer determining the image does not include an identifiable license plate; and

in response to the step of determining the image does not include the identifiable license plate, the computer determining the image is invalid and bypassing a manual character recognition process for determining identifiers on license plates.

2. The method of claim 1, further comprising the steps of:

the computer determining the category further specifying characteristics of a shape of a second license plate of a second vehicle;

based on the category specifying the characteristics of the shape of the second license plate, the computer determining characteristics of objects in a second image match the characteristics of the shape of the second license plate;

based on the characteristics of the objects in second image matching the characteristics of the shape of the second license plate, the computer determining the second image includes a second identifiable license plate;

in response to the step of determining the second image includes the second identifiable license plate, the computer determining the shape of the second license plate includes a plurality of alphanumeric characters;

the computer determining one or more alphanumeric characters included in the plurality of alphanumeric characters are not identifiable; and

in response to the step of determining the one or more alphanumeric characters are not identifiable, the computer sending the second image to a manual character recognition process for identifying the one or more alphanumeric characters.

3. The method of claim 2, further comprising the steps of:

subsequent to the step of sending the second image to the manual character recognition process for identifying the one or more alphanumeric characters, the computer receiving an indication that the second image is valid, receiving an identifier included in the second license plate, and receiving a first confidence value of the identifier resulting from the manual character recognition process for identifying the one or more alphanumeric characters;

the computer receiving metadata specifying a characteristic of the second image, the characteristic of the second image selected from the group consisting of a charging point at which a camera captured the second image, a traffic lane in which the second vehicle was traveling as the camera captured the second image, an identification of the camera that captured the second image, a time at which the camera captured the second image, a date on which the camera captured the second image, and the received first confidence value;

the computer updating another category with the characteristic of the second image specified by the received metadata;

the computer receiving a third image including the second license plate;

the computer determining the third image has a characteristic that matches the characteristic of the second image specified by the received metadata; and

based on the third image having the characteristic that matches the characteristic of the second image specified by the received metadata, the computer determining the identifier of the second license plate in the third image has a second confidence value which is greater than the first confidence value.

4. The method of claim 1, further comprising the step of:

providing at least one support service for at least one of creating, integrating, hosting, maintaining, and deploying computer-readable program code in the computer, the program code being executed by a processor of the computer to implement the steps of determining the category specifying the characteristics of the shape, determining the characteristics of the objects in the image match the characteristics of the shape of the license plate, determining the image includes the license plate and the identifier, determining the category specifying the characteristics of the order of the alphanumeric characters in the identifier, determining the characteristics of the objects in the image do not match the characteristics of the order of the alphanumeric characters in the identifier, determining the image does not include the identifiable license plate, determining the image is invalid, and bypassing the manual character recognition process for determining the identifiers on license plates.

5. A computer system comprising:

a central processing unit (CPU);

a memory coupled to the CPU;

a computer-readable, tangible storage device coupled to the CPU, the storage device containing instructions that are executed by the CPU via the memory to implement a method of processing an image, the method comprising the steps of;

the computer system determining a category specifying characteristics of a shape of a license plate of a vehicle;

based on the category specifying the characteristics of the shape of the license plate, the computer system determining characteristics of objects in the image match the characteristics of the shape of the license plate;

the computer system determining the image includes the license plate and an identifier included in the license plate;

the computer system determining a category specifying characteristics of an order of alphanumeric characters in the identifier, the order required to be a characteristic of identifiable license plates;

based on the category specifying the characteristics of the order of the alphanumeric characters in the identifier, the computer system determining characteristics of the objects in the image do not match the characteristics of the order of the alphanumeric characters in the identifier;

based on the characteristics of the objects in the image not matching the characteristics of the order of the alphanumeric characters in the identifier, the computer system determining the image does not include an identifiable license plate; and

in response to the step of determining the image does not include the identifiable license plate, the computer system determining the image is invalid and bypassing a manual character recognition process for determining identifiers on license plates.

6. The computer system of claim 5, wherein the method further comprises the steps of:

the computer system determining the category further specifying characteristics of a shape of a second license plate of a second vehicle;

based on the category specifying the characteristics of the shape of the second license plate, the computer system determining characteristics of objects in a second image match the characteristics of the shape of the second license plate;

based on the characteristics of the objects in second image matching the characteristics of the shape of the second license plate, the computer system determining the second image includes a second identifiable license plate;

in response to the step of determining the second image includes the second identifiable license plate, the computer system determining the shape of the second license plate includes a plurality of alphanumeric characters;

the computer system determining one or more alphanumeric characters included in the plurality of alphanumeric characters are not identifiable; and

in response to the step of determining the one or more alphanumeric characters are not identifiable, the computer system sending the second image to a manual character recognition process for identifying the one or more alphanumeric characters.

7. The computer system of claim 6, wherein the method further comprises the steps of:

subsequent to the step of sending the second image to the manual character recognition process for identifying the one or more alphanumeric characters, the computer system receiving an indication that the second image is valid, receiving an identifier included in the second license plate, and receiving a first confidence value of the identifier resulting from the manual character recognition process for identifying the one or more alphanumeric characters;

the computer system receiving metadata specifying a characteristic of the second image, the characteristic of the second image selected from the group consisting of a charging point at which a camera captured the second image, a traffic lane in which the second vehicle was traveling as the camera captured the second image, an identification of the camera that captured the second image, a time at which the camera captured the second image, a date on which the camera captured the second image, and the received first confidence value;

the computer system updating another category with the characteristic of the second image specified by the received metadata;

the computer system receiving a third image including the second license plate;

the computer system determining the third image has a characteristic that matches the characteristic of the second image specified by the received metadata; and

based on the third image having the characteristic that matches the characteristic of the second image specified by the received metadata, the computer system determining the identifier of the second license plate in the third image has a second confidence value which is greater than the first confidence value.

8. A computer program product, comprising:

a computer-readable, tangible storage device; and

a computer-readable program code stored in the computer-readable, tangible storage device, the computer-readable program code containing instructions that are executed by a central processing unit (CPU) of a computer system to implement a method of processing an image, the method comprising the steps of;

the computer system determining a category specifying characteristics of a shape of a license plate of a vehicle;

based on the category specifying the characteristics of the shape of the license plate, the computer system determining characteristics of objects in the image match the characteristics of the shape of the license plate;

the computer system determining the image includes the license plate and an identifier included in the license plate;

the computer system determining a category specifying characteristics of an order of alphanumeric characters in the identifier, the order required to be a characteristic of identifiable license plates;

based on the category specifying the characteristics of the order of the alphanumeric characters in the identifier, the computer system determining characteristics of the objects in the image do not match the characteristics of the order of the alphanumeric characters in the identifier;

based on the characteristics of the objects in the image not matching the characteristics of the order of the alphanumeric characters in the identifier, the computer system determining the image does not include an identifiable license plate; and

in response to the step of determining the image does not include the identifiable license plate, the computer system determining the image is invalid and bypassing a manual character recognition process for determining identifiers on license plates.

9. The computer program product of claim 8, wherein the method further comprises the steps of:

the computer system determining the category further specifying characteristics of a shape of a second license plate of a second vehicle;

based on the category specifying the characteristics of the shape of the second license plate, the computer system determining characteristics of objects in a second image match the characteristics of the shape of the second license plate;

based on the characteristics of the objects in second image matching the characteristics of the shape of the second license plate, the computer system determining the second image includes a second identifiable license plate;

in response to the step of determining the second image includes the second identifiable license plate, the computer system determining the shape of the second license plate includes a plurality of alphanumeric characters;

the computer system determining one or more alphanumeric characters included in the plurality of alphanumeric characters are not identifiable; and

in response to the step of determining the one or more alphanumeric characters are not identifiable, the computer system sending the second image to a manual character recognition process for identifying the one or more alphanumeric characters.

10. The computer program product of claim 9, wherein the method further comprises the steps of:

subsequent to the step of sending the second image to the manual character recognition process for identifying the one or more alphanumeric characters, the computer system receiving an indication that the second image is valid, receiving an identifier included in the second license plate, and receiving a first confidence value of the identifier resulting from the manual character recognition process for identifying the one or more alphanumeric characters;

the computer system receiving metadata specifying a characteristic of the second image, the characteristic of the second image selected from the group consisting of a charging point at which a camera captured the second image, a traffic lane in which the second vehicle was traveling as the camera captured the second image, an identification of the camera that captured the second image, a time at which the camera captured the second image, a date on which the camera captured the second image, and the received first confidence value;

the computer system updating another category with the characteristic of the second image specified by the received metadata;

the computer system receiving a third image including the second license plate;

the computer system determining the third image has a characteristic that matches the characteristic of the second image specified by the received metadata; and

based on the third image having the characteristic that matches the characteristic of the second image specified by the received metadata, the computer system determining the identifier of the second license plate in the third image has a second confidence value which is greater than the first confidence value.