Google patents image resizer that works with AI to spot objects better
This patent describes a method for resizing images that works alongside AI models to help them recognize objects more accurately. Instead of just shrinking an image, it splits the picture into different frequency bands, adjusts each part, and combines them to preserve important details.
In the filing’s own words
The technology provides an image resizer that is jointly trainable with neural network classification (recognition) models, and is designed to improve classification performance. Systems and method include applying an input image to a baseline resizer to obtain a default resized image, and applying the input image to a plurality of filters. Each respective filter in the plurality is configured to perform sub-band filtering on the input image to obtain a sub-band filtered result. This includes applying the sub-band filtered result to the baseline resizer to obtain a respective resized result, and also includes applying to the respective resized result a scaling parameter, a bias parameter, and a nonlinear function to obtain a respective filtered image. The process then combines the default resized image and the respective filtered images to generate a combined resized image.
What exactly they claim (claim 1)
1. A computer-implemented image resizing method comprising: obtaining, by one or more processors of a computing system, an input image having a first resolution; applying, by the one or more processors, the input image to a baseline resizer to obtain a default resized image; applying, by the one or more processors, the input image to a plurality of filters, for each respective filter in the plurality: performing sub-band filtering on the input image to obtain a sub-band filtered result; applying the sub-band filtered result to the baseline resizer to obtain a respective resized result; and applying, to the respective resized result, a scaling parameter, a bias parameter, and a nonlinear function to obtain a respective filtered image; and combining, by the one or more processors, the default resized image and the respective filtered images to generate a combined resized image.
Facts
- Company
- Google (Google LLC)
- Official title
- Multilayer laplacian resizer for computer vision systems
- Patent number
- US12737845B2
- Application number
- 18621434
- Filed
- Mar 29, 2024
- Granted
- Sep 15, 2026
- Inventors
- 3
- Claims
- 21
Classified under
G06T 5/20 Physics & computingG06T 5/50 Physics & computingG06T 2207/20024 Physics & computingG06T 2207/20212 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.