Systems and methods for image search
AssigneeShanghai United Imaging Healthcare Co., Ltd.
InventorsJiyong Wang, Xiangyang Xu, Wanwan Cao, Qingfeng Chang, Qiancheng Sun
Life of this patent
Estimating the term…
Abstract
The present disclosure relates to a method and system for image searching. In the image searching process, different images comprising specific regions are obtained respective, and features in the specific regions of the different images are extracted respectively based on a convolution neural network algorithm. Feature data related to the features corresponding to the different images is calculated, and the different images are ranked based on the feature data so as to identify the image needed.
Claims20
A method, comprising:
- obtaining a first image;
- determining a first region in the first image;
- obtaining a second image;
- determining a second region in the second image;
- obtaining a third image;
- determining a third region in the third image;
- before feature extraction based on a convolution neural network algorithm, determining, based on resolution of the first image, a count of convolution kernels for each convolution layer of the convolution neural network algorithm;
- extracting a first group of features of the first region based on the convolution neural network algorithm;
- extracting a second group of features of the second region based on the convolution neural network algorithm;
- extracting a third group of features of the third region based on the convolution neural network algorithm;
- calculating first similarity between the first region and the second region based on the first group of features and the second group of features;
- calculating second similarity between the first region and the third region based on the first group of features and the third group of features;
- and
- ranking the second image and the third image based on the first similarity between the first region and the second region and the second similarity between the first region and the third region.
A system, comprising:
- at least one storage device storing a set of instructions;
- and
- at least one processor being in communication with the at least one storage device, wherein when executing the set of instructions, the at least one processor is configured to cause the system to perform operations including:
- obtaining a first image;
- determining a first region in the first image;
- obtaining a second image;
- determining a second region in the second region;
- obtaining a third image;
- determining a third region in the third image;
- before feature extraction based on a convolution neural network algorithm, determining, based on resolution of the first image, a count of convolution kernels for each convolution layer of the convolution neural network algorithm;
- extracting a first group of features of the first region based on the convolution neural network algorithm;
- extracting a second group of features of the second region based on the convolution neural network algorithm;
- extracting a third group of features of the third region based on the convolution neural network algorithm;
- calculating first similarity between the first region and the second region based on the first group of features and the second group of features;
- calculating second similarity between the first region and the third region based on the first group of features and the third group of features;
- and
- ranking the second image and the third image base on the first similarity between the first region and the second region and the second similarity between the first region and the third region.
The system of 16, wherein the second group of features is selected from the second feature set according to a feature selection algorithm.
The system of 16, wherein the second parameter comprises at least one of a number of convolution neural network layers, a size of a convolution kernel, or a number of generated features.
Dependencies are inferred from the claim text.