public Document createDocument(BufferedImage image, String identifier) {
assert (image != null);
BufferedImage bimg = image;
// Scaling image is especially with the correlogram features very important!
// All images are scaled to guarantee a certain upper limit for indexing.
if (Math.max(image.getHeight(), image.getWidth()) > MAX_IMAGE_DIMENSION) {
bimg = ImageUtils.scaleImage(image, MAX_IMAGE_DIMENSION);
}
Document doc = null;
logger.finer("Starting extraction from image [CEDD - fast].");
CEDD vd = new CEDD();
vd.extract(bimg);
logger.fine("Extraction finished [CEDD - fast].");
doc = new Document();
doc.add(new Field(DocumentBuilder.FIELD_NAME_CEDD, vd.getByteArrayRepresentation()));
if (identifier != null)
doc.add(
new Field(
DocumentBuilder.FIELD_NAME_IDENTIFIER,
identifier,
Field.Store.YES,
Field.Index.NOT_ANALYZED));
return doc;
}
public double testIndexing() throws IOException, IllegalAccessException, InstantiationException {
LocalitySensitiveHashing.generateHashFunctions();
LocalitySensitiveHashing.readHashFunctions();
DocumentBuilder builder = new ChainedDocumentBuilder();
((ChainedDocumentBuilder) builder).addBuilder(DocumentBuilderFactory.getCEDDDocumentBuilder());
// System.out.println("-< Getting files to index >--------------");
ArrayList<String> images = FileUtils.getAllImages(new File(testExtensive), true);
// System.out.println("-< Indexing " + images.size() + " files >--------------");
IndexWriter iw =
LuceneUtils.createIndexWriter(indexPath, true, LuceneUtils.AnalyzerType.WhitespaceAnalyzer);
int count = 0;
long time = System.currentTimeMillis();
for (String identifier : images) {
CEDD cedd = new CEDD();
cedd.extract(ImageIO.read(new FileInputStream(identifier)));
Document doc = new Document();
doc.add(new Field(DocumentBuilder.FIELD_NAME_CEDD, cedd.getByteArrayRepresentation()));
doc.add(
new Field(
DocumentBuilder.FIELD_NAME_IDENTIFIER,
identifier,
Field.Store.YES,
Field.Index.NOT_ANALYZED));
int[] hashes = LocalitySensitiveHashing.generateHashes(cedd.getDoubleHistogram());
StringBuilder hash = new StringBuilder(512);
for (int i = 0; i < hashes.length; i++) {
hash.append(hashes[i]);
hash.append(' ');
}
// System.out.println("hash = " + hash);
doc.add(new Field("hash", hash.toString(), Field.Store.YES, Field.Index.ANALYZED));
iw.addDocument(doc);
count++;
// if (count % 100 == 0) System.out.println(count + " files indexed.");
}
long timeTaken = (System.currentTimeMillis() - time);
float sec = ((float) timeTaken) / 1000f;
// System.out.println(sec + " seconds taken, " + (timeTaken / count) + " ms per image.");
iw.close();
return testSearch();
}