Apparatus and methods of obtaining multi-scale feature vector using CNN based integrated circuits
US11526723B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 9, 2019 |
| Grant date | Dec 13, 2022 |
| Priority date | — |
| Expiry date | Aug 29, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/82
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A pixel feature vector extraction system for extracting multi-scale features contains a cellular neural networks (CNN) based integrated circuit (IC) for extracting pixel feature vector out of input imagery data by performing convolution operations using pre-trained filter coefficients of ordered convolutional layers in a deep learning model. The ordered convolutional layers are organized in a number of groups with each group followed by a pooling layer. Each group is configured for a different size of feature map. Pixel feature vector contains a combination of feature maps from at least two groups, for example, concatenation of the feature maps. The first group of the at least two groups contains the largest size of the feature maps amongst all of the at least two groups. Feature maps of the remaining of the at least two groups are modified to match the size of the feature map of the first group.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.