FB pixel

Smart Engines granted US patent for method of more efficient image processing

Smart Engines granted US patent for method of more efficient image processing

Smart Engines has been granted a patent for an innovation utilizing Hough Transformations to improve the image recognition performance of neural network architectures.

The U.S. Patent and Trademark Office granted the patent for ‘Artificial Intelligence Using Convolutional Neural Network with Hough Transform,’ which lists Smart Engines CEO Vladimir Arlazarov, CTO Dmitry Nikolaev, Senior Researcher-Programmer Alexander Sheshkus, and famed Computer Science Professor Vladimir Lvovich Arlazarov as inventors.

The invention proposes a new neural network architecture

The Hough Transform is a feature extraction technique which according to the announcement is commonly used to find and highlight straight lines. The lines examined in image processing and analysis for ID documents and other objects, however, are often not perfectly straight, have varying lengths, and may be only partially visible. The invention described in the patent enables neural networks to handle these types of images more economically, the inventors say.

“The proposed architecture using the Hough Transform provides competitive quality with a much smaller number of teachable parameters and the need for less computing power,” says Nikolaev.

The patent also references the Mobile Identity Document Video dataset, and a 2019 paper introducing it.

“Neural networks are great at extracting information from examples, but it is virtually impossible to train them on the immutable laws of physics or mathematics,” explains Vladimir Lvovich Arlazarov, Smart Engines’ scientific director, professor, and doctor of computer science. “Recent ChatGPT network exercises in arithmetic are illustrative. When multiplying large numbers, it correctly places the first and last digits of the result and even guesses its length, but puts the middle digits out of the blue. This is a strange result, because the correct solution requires a billion times fewer resources than the neural network has at its disposal. This begs the question: is it even possible to study mathematics by example?”

“Immanuel Kant believed that human cognition is based on a priori forms that are independent of experience,” he continues. “We believe that we have succeeded in building into a neural network an additional a priori geometric representation that underlies the laws of perspective. This allows it to build solutions to computer vision problems, such as determining the orientation of objects in space or determining one’s own position.”

The patent is the third filed in the U.S. by Smart Engines, including one granted earlier this year for on-device ID document analysis.

Related Posts

Article Topics

 |   |   |   |   |   | 

Latest Biometrics News


Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Most Read This Week

Featured Company

Biometrics Research

Biometrics White Papers

Biometrics Events

Explaining Biometrics