Image processing using random forest classifiers
A method of performing image retrieval includes training a random forest RF classifier based on low-level features of training images and a high-level feature, using similarity values generated by the RF classifier to determine a subset of the training images that are most similar to one another, and classifying input images for the high-level feature using the RF classifier and the determined subset of images.
1. A method of performing image processing, the method comprising:
training a random forest RF classifier based on low-level features of training images and a high-level feature of the training images;
using similarity values generated by the RF classifier to determine a subset of the training images that are most similar to one another; and
classifying an input image for the high-level feature using the RF classifier and the determined subset of training images.
2. The method of claim 1 , wherein each similarity value is a proportion of trees of the RF classifier where two or more of the training images are located in a same terminal node.
3. The method of claim 1 , wherein the high-level feature is human generated by the human manually annotating at least one of the training images.
4. The method of claim 1 , wherein the low-level features are automatically generated by a computer analysis of the training images and the high-level feature is manually generated by a human analysis of the training images.
5. The method of claim 1 , where the method further includes extracting a high-level feature from the input image and the classifying is further based on the extracted high-level feature.
6. The method of claim 1 , wherein the RF classifier is selected from among a plurality of classifiers based on an input search query that requests images that are similar with respect to predicting the high level feature.
7. The method of claim 6 , wherein the plurality of classifiers are initially trained, and this training comprises:
selecting a subset of a plurality of high-level features;
training each classifier based on at least one high-level feature of the subset; and
training each classifier based on a corresponding one of the remaining high-level features.
8. The method of claim 7 , wherein the subset of high-level features may include at least one of contrast agent phase, lesion focaility, lesion surrounding, rim continuity, margin, and margin definition.
9. The method of claim 7 , wherein the remaining high-level features may include at least one of tissue density, benignancy, or lesion type.
10. The method of claim 1 , wherein the input training images are of liver lesions.
11. The method of claim 1 , wherein the training of the RF classifier comprises:
initializing an RF structure based on the subset of training images;
updating Gaussian statistics based on features of a next one of the training images until a certain number of the training images are observed given a source of randomness; and
refining the RF structure based on the updated Gaussian statistics.
12. The method of claim 11 , further comprising:
determining whether a memory limit is reached by a tree of the RF structure; and
deactivating at least one tree node of the tree when the memory limit is reached.
13. The method of claim 11 , wherein the refining comprising adding a node to a leaf in the tree.
14. The method of claim 11 , wherein each leaf in a tree in the RF structure includes a part of the Gaussian Statistics.
15. A method of training a Random Forest RF classifier, the method comprises:
initializing a RF structure based on only a batch subset of sample images among a larger set of sample images;
updating Gaussian statistics based on features of a next one of the larger set of sample images other than the subset until a certain number of samples are observed given a source of randomness; and
refining the RF structure based on the updated Gaussian statistics.
16. The method of claim 15 , wherein the source of randomness is modeled via a Poisson distribution defining a weight for each sample image.
17. The method of claim 15 , further comprising:
determining whether a memory limit is reached by a tree of the RF structure; and
deactivating at least one tree node of the tree when the memory limit is reached.
18. The method of claim 15 , wherein the subset is determined by:
training a random forest RF classifier based on low-level features of the larger set of samples images and a high-level feature of the larger set of sample images; and
using similarity values generated by the RF classifier to determine the subset that are most similar to one another.
19. The method of claim 18 , wherein each similarity value is a proportion of trees of the RF classifier where two or more of the sample images are located in a same terminal node.
20. The method of claim 18 , wherein the low-level features are automatically generated by a computer analysis of the sample images and the high-level feature is manually generated by a human analysis of the sample images.