Content-based image retrieval (CBIR), also known as query by image content (QBIC) and content-based visual information retrieval (CBVIR) is the application of computer vision techniques to the image retrieval problem, that is, the problem of searching for digital images in large databases. Content-based image retrieval is opposed to traditional concept-based approaches (see Concept based image indexing). "Content-based" means that the search analyzes the contents of the image rather than the metadata such as keywords, tags, or descriptions associated with the image. The term "content" in this context might refer to colors, shapes, textures, or any other information that can be derived from the image itself.
The full documentation will located here: https://github.com/loic911/CBIRetrieval/wiki
Implementation with Cytomine
The retrieval is usefull in Cytomine to provide term suggestion.
- You draw an annotation,
- Cytomine compute the annotation crop (annotation image) and do a request on the retrieval,
- The retrieval return a list of similar annotation id/crop,
- Cytomine retrieve the term for each annotation in response and compute "suggested term" for the request annotation.
Cytomine - Retrieval integration
- Index: When you add an annotation, Cytomine compute its crop image and index this image on the Retrieval,
- Search: When you draw/click on an annotation, Cytomine will compute the crop and ask for similar images,
When you create/edit a project, you can choose if indexed annotations needs to come from:
- All project with the same ontology,
- Only specific project with this ontology,
- Only the current project,
- Disable retrieval
The diagram below show the main search step:
- User draw a new annotation,
- Cytomine compute the crop area (diagram: top-left),
- Cytomine perform a request on the Retrieval system,
- Retrieval response a list of indexed crop that are similar to the request crop