AutoColorCorrelation Image Feature

This descriptor is based on the publication Image Indexing Using Color Correlograms of Jing Huang et al. from Cornell University and presents an alternative to the MPEG-7 descriptors. Main features:

In my subjective opinion it provides a better color search than ScalableColor, but it is extracted more slowly (see above mentioned paper for details).

For basic LIRE usage see [search](]] and index creation

To use the descriptor try the

To create an appropriate searcher use

Very important:

* Ensure that the analyzed image is big enough for the descriptor, otherwise the descriptor cannot be extracted.

Sample code

public void testCorrelationSearch() throws IOException {
    String[] testFiles = new String[]{"img01.JPG", "img02.JPG", "img03.JPG", "img04.JPG", "img05.JPG",
            "img06.JPG", "img07.JPG", "img08.JPG", "img08a.JPG"};
    String testFilesPath = "./src/test/resources/images/";
    String indexPath = "test-index";

    IndexReader reader =;
    int numDocs = reader.numDocs();
    System.out.println("numDocs = " + numDocs);
    // create the appropriate correlogram searcher:
    ImageSearcher searcher = new GenericFastImageSearcher(10, AutoColorCorrelogram.class, true, reader);
    FileInputStream imageStream = new FileInputStream(testFilesPath + testFiles[0]);
    BufferedImage bimg =;
    ImageSearchHits hits = null;
    // search for the image in the index
    hits =, reader);
    for (int i = 0; i < hits.length(); i++) {
        System.out.println(hits.score(i) + ": " + reader.document(hits.documentID(i)).getValues(DocumentBuilder.FIELD_NAME_IDENTIFIER)[0]);