US 11,816,681 B2
Image authentication method and real-time product authentication system
Zon-Yin Shae, Taipei Clty (TW); Zhi-Ren Tsai, Taichung (TW); and Jing-Pha Tsai, Taichung (TW)
Assigned to Asia University, Taichung (TW)
Filed by Asia University, Taichung (TW)
Filed on Jan. 4, 2021, as Appl. No. 17/247,974.
Claims priority of application No. 109121359 (TW), filed on Jun. 23, 2020.
Prior Publication US 2021/0397897 A1, Dec. 23, 2021
Int. Cl. G06Q 30/018 (2023.01); G06F 18/21 (2023.01); G06V 10/82 (2022.01)
CPC G06Q 30/018 (2013.01) [G06F 18/217 (2023.01); G06F 18/2163 (2023.01); G06V 10/82 (2022.01)] 8 Claims
OG exemplary drawing
 
1. A real-time product authentication system, comprising an intelligence model, wherein the intelligence model is configured to realize an image authentication method used for a deep learning model built for a plurality of categories of a product, the image authentication method comprising:
a training phase, comprising:
inputting a training image;
segmenting the training image into a plurality of training sub-images; and
training the deep learning model by using the plurality of training sub-images, wherein each of the plurality of training images includes a global feature property; and
a testing phase, comprising:
inputting a testing image and segmenting the testing image into a plurality of testing sub-images;
performing a test on each of the plurality of testing sub-images and checking whether any of the plurality of testing sub-images is associated with one of the plurality of categories; and
outputting an authentication result to identify whether the testing image is associated with one of the plurality of categories,
the real-time product authentication system further comprising a transaction identification barcode and an image uploader; wherein the transaction identification barcode is displayed or labeled on the product, the transaction identification barcode is embedded in a network link and a transaction code of the product, and the image uploader is provided for a user to upload a to-be-authenticated image and sent to the intelligence model to generate the authentication result; wherein the image uploader is located on a webpage opened via the network link, and the transaction code comprises one of a plurality of quality parameters defining quality of the product and an intelligence model index value defining a corresponding deep learning model of the product.