Accenture patents anti-counterfeit AI platform

Consulting firm Accenture has been awarded a US patent on the application of artificial intelligence system that can tell whether an item is fake or genuine from an image.

The AI algorithm can be trained using deep learning to detect counterfeits using simulated counterfeit images or images of actual faked items. As an example, it could be used to detect variables such as the curvature of a pill in an image, the font used on a tablet or capsule, or packaging features.

"The presence of counterfeit products in a market can negatively impact the value of authentic products," says the patent. "For customers desiring to purchase authentic products, the presence of counterfeit products can deter such customers from purchasing products that may in fact be authentic."

The abstract of the patent appears below:

Artificial intelligence counterfeit detection

Abstract: A counterfeit detection system provides an artificial intelligence (AI) platform that implements a Generative Adversarial Network (GAN) to classify an image as one of a fake or genuine item and integrates a Classification Activation Module (CAM) to refine counterfeit detection. The GAN may include a generator that generates simulated counterfeit images for a discriminator. The discriminator may be trained to identify faked items by learning from the simulated counterfeit images and/or images of actual faked items. The discriminator may implement a deep neural network of convolutional layers that each analyse a region of an image and produce a weighted output that contributes to the classification based on the analysed region. The CAM may identify the regions and weights relied upon by the discriminator, provide corresponding heatmaps to subject matter experts, receive annotations from the subject matter experts, and use the annotations as feedback to refine the classifier of the discriminator.

US Patent No. 10,885,531

Related articles:

     Want our news sent directly to your inbox?

Yes please 2


Home  |  About us  |  Contact us  |  Advertise  |  Links  |  Partners  |  Privacy Policy  |   |  RSS feed   |  back to top