Graph image representation from convolutional neural networks

• US 9,418,458 B2
• Filed: 01/04/2016
• Issued: 08/16/2016
• Est. Priority Date: 01/05/2015
• Status: Expired due to Fees

• Current Assignee: Superfish Incorporated
• Original Assignee: Superfish Incorporated
• Inventors: Chertok, Michael, Lorbert, Alexander
• Primary Examiner(s): Park, Soo
• Application Number:
  US14/987,479
• Publication Number:
  US 20160196672A1
• Time in Patent Office: 225 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06T 11/206 Drawing of charts or graphs
• CPC Class Codes: G06V 10/426 Graphical representations
• CPC Class Codes: G06V 10/454 Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]

Abstract

A method for producing a graph representation of an input image, the method including the procedures of applying convolutional layers of a trained convolutional neural network on the input image, defining a receptive field of a last convolutional layer of the trained convolutional neural network as a vertex of the graph representation, defining a vector of a three dimensional output matrix of the last convolutional layer that is mapped to the receptive field as a descriptor for the vertex and determining an edge between a pair of vertices of the graph representation by applying an operator on a pair of descriptors respective of the pair of vertices.

Claims

1. A method for producing a graph representation of an input image, the method comprising the procedures of:

applying convolutional layers of a trained convolutional neural network on said input image;

defining a receptive field of a last convolutional layer of said trained convolutional neural network as a vertex of said graph representation;

defining a vector of a three dimensional output matrix of said last convolutional layer that is mapped to said receptive field as a descriptor for said vertex; and

determining an edge between a pair of vertices of said graph representation by applying an operator on a pair of descriptors respective of said pair of vertices.

2. The method according to claim 1, further comprising a procedure of employing said graph representation of said input image for performing a visual task.

3. The method according to claim 1, wherein said procedure of determining an edge further comprises a sub-procedure of scaling said edge according to a distance between said vertices of said pair of vertices.

4. The method according to claim 1, wherein only a portion of said convolutional layers are applied on said input image.

5. The method according to claim 1, further comprising a procedure of applying at least one fully connected layer of said trained convolutional neural network on said input image after said procedure of applying convolutional layers, and further comprising a procedure of backtracking an output of said at least one fully connected layer to said last convolutional layer.