Pattern detection and location in a processed image

• US 10,410,047 B2
• Filed: 11/02/2017
• Issued: 09/10/2019
• Est. Priority Date: 08/12/2014
• Status: Active Grant

• Current Assignee: Cortigent Incorporated
• Original Assignee: Second Sight Medical Products, Inc. (Vivani Medical, Inc.)
• Inventors: Greenberg, Robert, Caspi, Avraham, Merlini, Francesco, Roy, Arup
• Primary Examiner(s): Schaetzle, Kennedy
• Application Number:
  US15/801,861
• Publication Number:
  US 20180068175A1
• Time in Patent Office: 677 Days
• Field of Search: None
• CPC Class Codes: A61B 5/1176 Recognition of faces
• CPC Class Codes: A61F 9/08 Devices or methods enabling eye-patients to replace direct visual perception by another kind of perception
• CPC Class Codes: A61N 1/36046 of the eye
• CPC Class Codes: A61N 1/36185 Selection of the electrode configuration
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/172 Classification, e.g. identification

Abstract

The present invention is a method of processing a video image in an electronic video processor including the steps of receiving an input image having an input field of view, generating a processed image from the input image, and having an output field of view smaller than the input field of view, searching for a predetermined pattern within the input image, providing an indication when the predetermined pattern is found in the input image, and zooming the processed image to the input field of view and highlighting the predetermined pattern in the processed image in response to the indication.

Claims

1. A method of processing a video image in an electronic video processor for a visual prosthesis comprising:

providing a visual prosthesis including an electronic video processor and an implantable neural stimulator including an array of electrodes adapted to stimulate visual neurons;

receiving an input image having an input field of view;

generating a processed image from the input image, having an output field of view smaller than the input field of view, the output field of view defined by the field of view of visual neurons stimulated by the array of electrodes;

searching for a predetermined pattern within the input image; and

providing a cue to a user when the predetermined pattern is found in the input image.

2. The method according to claim 1, further comprising accepting input from the user to zoom the processed image to the input field of view and highlight the predetermined pattern in the processed image in response to the user input.

3. The method according to claim 1, wherein the predetermined pattern is a face.

4. The method according to claim 1, wherein the predetermined pattern is a hazard.

5. The method according to claim 1, wherein the step of searching further includes recognizing features of the detected pattern.

6. The method according to claim 1, wherein the predetermined pattern is stored in a look up table of patterns and identifying information.

7. The method according to claim 6, wherein the predetermined pattern is a face and the look up table associates the faces with a name.

8. The method according to claim 7, further comprising announcing the name associated with the detected face.