Gamified alphanumeric character identification
AssigneeElectronic Transaction Consultants, LLC
InventorsJoshua LittleSun, Thomas J. Owen, Benjamin McCord, Scott Cote
Life of this patent
Estimating the term…
Abstract
A method includes receiving from a first detection system, an image of a license plate, applying an optical recognition function to characters of the license plate, and assigning a confidence value to each of the characters. The method further includes, in response to determining that the confidence value for a particular character is below a threshold, sending an image of the character to a gamified human reviewer application, receiving from the gamified human reviewer application, a human response indicative of a characteristic of the character, and updating the optical recognition function based on the characteristic of the character.
Claims20
A method performed by a computing system, the method comprising:
- receiving from a first detection system, an image of a license plate;
- applying an optical recognition function to characters of the license plate;
- assigning a confidence value to each of the characters;
- in response to determining that the confidence value for a particular character is below a threshold, sending an image of the character to a gamified human reviewer application;
- receiving from the gamified human reviewer application, a human response indicative of a characteristic of the character;
- and
- updating the optical recognition function based on the characteristic of the character,
- wherein the characteristic includes at least one of:
- the character being darker than a background, the character being lighter than the background, and the character being blurry, or the character being at least partially obstructed.
A method comprising:
- receiving a plurality of character images from a license plate recognition system, each character image comprising a single character from an image of a license plate;
- presenting the plurality of character images to a user in a gamified manner;
- presenting the user with information regarding a user's performance of identifying characters from the plurality of character images;
- receiving from the user, an identification of the characters and characteristics of the characters, where the characteristics of the characters include at least one of:
- one of the characters being darker than the background, one of the characters being lighter than the background, one of the characters being blurry, and one of the characters being at least partially obstructed;
- and
- returning the identification and the characteristics to the license plate recognition system.
A system comprising:
- a processor;
- and
- a memory comprising machine readable instructions that when executed by a processor, cause the system to:
- receive from a detection system, an image of a license plate;
- apply an optical recognition function to characters of the license plate;
- assign a confidence value to each of the characters;
- in response to determining that the confidence value for a particular character is below a threshold, send an image of the character to a gamified human reviewer application;
- receive from the gamified human reviewer application, a human response indicative of a characteristic of the character;
- and update the optical recognition function based on the characteristic of the character,
- wherein the characteristic comprises at least one of:
- the character being darker than the background, the character being lighter than the background, the character being blurry, and the character being at least partially obstructed.
Dependencies are inferred from the claim text.