Logo image indentification system
An image identification system may identify key points on a known image, variations of the known image in different levels of blur, and an unidentified image. One or more geometric shapes may be formed from the key points. A match between the unidentified image and either the known image or a blurred variation of the known image may be determined by comparison of the respective geometric shapes.
1. A method for image identification using a secure autonomous intelligent server, the method comprising:
creating a database of known logos, the database comprising vertices of geometric shapes formed from the known logos;
creating one or more variations of each known logo, the variations comprising the known logo portrayed in varying levels of blur;
creating geometric shapes formed from the blurred logos;
calculating vertices of the geometric shapes formed from the blurred logos and adding the vertices to the database;
obtaining an unidentified logo;
identifying key points on the unidentified logo;
constructing a geometric shape from the key points of the unidentified logo;
calculating vertices of the geometric shape of the unidentified logo; and
matching the vertices of the geometric shape of the unidentified logo with the vertices of the geometric shape of at least one of the known logos and the blurred logos.
2. The method of claim 1 , wherein creating the database of known logos comprises:
obtaining a known logo;
identifying key points on the known logo and the blurred logos;
constructing a geometric shape from the key points of the known logo and the blurred logos;
calculating vertices of the geometric shape of the known logo and the blurred logos; and
storing the vertices of the geometric shape of the known logo and the blurred logos in the database and associating the vertices with the known logo.
3. The method of claim 1 , wherein constructing the geometric shape from the key points of the unidentified logo comprises:
identifying ordered pairs of the key points;
identifying ordered pairs that have one key point in common; and
constructing the geometric shape from the ordered pairs having one key point in common.
4. The method of claim 1 , wherein the database of vertices of geometric shapes formed from the known logos and the blurred logos comprises vertices of triangles.
5. The method of claim 2 , wherein constructing the geometric shape from the key points of the known logo and the blurred logos comprises constructing a triangle from the key points of the known logo.
6. The method of claim 1 , further comprising:
constructing multiple geometric shapes from the key points of the known logo and the blurred logos;
calculating vertices of each of the multiple geometric shapes of the known logo and the blurred logos;
constructing multiple geometric shapes from the key points of the unidentified logo;
calculating vertices of each of the multiple geometric shapes of the unidentified logo; and
matching the vertices of two or more of the geometric shapes of the unidentified logo with the vertices of the geometric shapes of the at least one of the known logos or the blurred logos.
7. The method of claim 1 , wherein obtaining the unidentified logo comprises:
scanning a computer network for posted images; and
identifying logos within the posted images.
8. The method of claim 7 , wherein the computer network comprises social media sites.
9. Non-transitory computer readable media as executed by a system controller comprising a specialized chip to perform a method for image identification, the method comprising:
creating a database of known logos, the database comprising vertices of geometric shapes formed from the known logos;
creating one or more variations of each known logo, the variations comprising the known logo portrayed in varying levels of blur;
creating geometric shapes formed from the blurred logos;
calculating vertices of the geometric shapes formed from the blurred logos and adding the vertices to the database;
obtaining an unidentified logo;
identifying key points on the unidentified logo;
constructing a geometric shape from the key points of the unidentified logo;
calculating vertices of the geometric shape of the unidentified logo; and
matching the vertices of the geometric shape of the unidentified logo with the vertices of the geometric shape of at least one of the known logos and the blurred logos.
10. The non-transitory computer readable media of claim 9 , wherein creating a database of known logos comprises:
obtaining a known logo;
identifying key points on the known logo;
constructing a geometric shape from the key points of the known logo;
calculating vertices of the geometric shape of the known logo; and
storing the vertices of the geometric shape of the known logo in the database and associating the vertices with the known logo.
11. The non-transitory computer readable media of claim 9 , wherein constructing a geometric shape from the key points of the unidentified logo comprises:
identifying ordered pairs of the key points;
identifying ordered pairs that have one key point in common; and
constructing the geometric shape from the ordered pairs having one key point in common.
12. The non-transitory computer readable media of claim 9 , wherein the database of vertices of geometric shapes formed from the known logos and the blurred logos comprises vertices of triangles.
13. The non-transitory computer readable media of claim 10 , wherein constructing the geometric shape from the key points of the known logo comprises constructing a triangle from the key points of the known logo.
14. The non-transitory computer readable media of claim 9 , further comprising:
constructing multiple geometric shapes from the key points of the known logo and the blurred logos;
calculating vertices of each of the multiple geometric shapes of the known logo and the blurred logos;
constructing multiple geometric shapes from the key points of the unidentified logo;
calculating vertices of each of the multiple geometric shapes of the unidentified logo; and
matching the vertices of two or more of the geometric shapes of the unidentified logo with the vertices of the geometric shapes of one of the known logos or blurred logos.
15. The non-transitory computer readable media of claim 9 , wherein obtaining an unidentified logo comprises: scanning a computer network for posted images; and identifying logos within the posted images.
16. The non-transitory computer readable media of claim 15 , wherein the computer network comprises social media sites.