Apparatus and methods for spoofing detection using machine learning processes
Methods, systems, and apparatuses are provided to automatically determine whether an image is spoofed. For example, a computing device may obtain an image, and may execute a trained convolutional neural network to ingest elements of the image. Further, and based on the ingested elements of the image, the executed trained convolutional neural network generates an output map that includes a plurality of intensity values. In some examples, the trained convolutional neural network includes a plurality of down sampling layers, a plurality of up sampling layers, and a plurality of joint spatial and channel attention layers. Further, the computing device may determine whether the image is spoofed based on the plurality of intensity values. The computing device may also generate output data based on the determination of whether the image is spoofed, and may store the output data within a data repository.
1. An apparatus comprising:
a non-transitory, machine-readable storage medium storing instructions; and
at least one processor coupled to the non-transitory, machine-readable storage medium, the at least one processor being configured to:
obtain image data;
apply a trained machine learning process to the image data and, based on the application of the trained machine learning process to the image data, generate an output map comprising a plurality of intensity values;
determine a total intensity value based on the plurality of intensity values;
determine whether the image data depicts an unauthentic object based on the total intensity value; and
generate, based on the determination, output data characterizing whether the image data depicts the unauthentic object.
2. The apparatus of claim 1 , wherein the trained machine learning process comprises establishing a convolutional neural network.
3. The apparatus of claim 2 , wherein the convolutional neural network comprises a plurality of down sampling layers, a plurality of up sampling layers, and a joint spatial and channel attention layer following each of the plurality of down sampling layers and each of the plurality of up sampling layers.
4. The apparatus of claim 3 , wherein each of the plurality of up sampling layers is configured to receive an output from a corresponding one of the plurality of down sampling layers and an output from a preceding one of the joint spatial and channel attention layers.
5. The apparatus of claim 1 , wherein the at least one processor is configured to:
determine that the image data depicts the unauthentic object based on the intensity values; and
deny access to at least one function of the apparatus based on the determination.
6. The apparatus of claim 5 , wherein the at least one processor is further configured to transmit a message to a device of a preauthorized user, wherein the message characterizes the denied access.
7. The apparatus of claim 1 , wherein the at least one processor is further configured to:
compare the total intensity value to a predetermined threshold; and
determine whether the image data depicts the unauthentic object based on the comparison.
8. The apparatus of claim 1 comprising a camera configured to capture the image data.
9. The apparatus of claim 1 comprising a display configured to display the image data.
10. A method comprising:
obtaining image data;
applying a trained machine learning process to the image data and, based on the application of the trained machine learning process to the image data, generate an output map comprising intensity values;
determining a total intensity value based on the plurality of intensity value;
determining whether the image data depicts an unauthentic object based on the total intensity value; and
generating, based on the determination, output data characterizing whether the image data depicts the unauthentic object.
11. The method of claim 10 , wherein the trained machine learning process comprises establishing a convolutional neural network.
12. The method of claim 11 , wherein the convolutional neural network comprises a plurality of down sampling layers, a plurality of up sampling layers, and a joint spatial and channel attention layer following each of the plurality of down sampling layers and each of the plurality of up sampling layers.
13. The method of claim 12 , wherein each of the plurality of up sampling layers is configured to receive an output from a corresponding one of the plurality of down sampling layers and an output from a preceding one of the joint spatial and channel attention layers.
14. The method of claim 10 , further comprising:
determining that the image data depicts the unauthentic object based on the intensity values; and
denying access to at least one function of the apparatus based on the determination.
15. The method of claim 14 , further comprising transmitting a message to a device of a preauthorized user, wherein the message characterizes the denied access.
16. The method of claim 10 , further comprising:
comparing the total intensity value to a predetermined threshold; and
determining whether the image data depicts the unauthentic object based on the comparison.
17. A non-transitory, machine-readable storage medium storing instructions that, when executed by at least one processor, causes the at least one processor to perform operations that include:
obtaining image data;
applying a trained machine learning process to the image data and, based on the application of the trained machine learning process to the image data, generate an output map comprising intensity values;
determining a total intensity value based on the plurality of intensity value;
determining whether the image data depicts the unauthentic object based on the total intensity value; and
generating, based on the determination, output data characterizing whether the image data depicts the unauthentic object.
18. The non-transitory, machine-readable storage medium of claim 17 , wherein the trained machine learning process comprises establishing a convolutional neural network.
19. The non-transitory, machine-readable storage medium of claim 18 , wherein the convolutional neural network comprises a plurality of down sampling layers, a plurality of up sampling layers, and a joint spatial and channel attention layer following each of the plurality of down sampling layers and each of the plurality of up sampling layers.
20. The non-transitory, machine-readable storage medium of claim 19 , wherein each of the plurality of up sampling layers is configured to receive an output from a corresponding one of the plurality of down sampling layers and an output from a preceding one of the joint spatial and channel attention layers.