private void indexFiles(ArrayList<String> images, DocumentBuilder builder, String indexPath)
throws IOException {
// eventually check if the directory is there or not ...
IndexWriter iw = LuceneUtils.createIndexWriter(testIndex, false);
int count = 0;
long time = System.currentTimeMillis();
for (String identifier : images) {
// TODO: cut toes from the image ... -> doesn't work out very well. Stable at first,
// decreasing then.
// TODO: Joint Histogram ...
// TODO: LSA / PCA on the vectors ...-> this looks like a job for me :-D
// TODO: local features ...
Document doc = null;
if (cutImages) {
BufferedImage bimg =
ImageUtils.cropImage(ImageIO.read(new FileInputStream(identifier)), 0, 0, 200, 69);
doc = builder.createDocument(bimg, identifier);
} else doc = builder.createDocument(new FileInputStream(identifier), identifier);
iw.addDocument(doc);
count++;
if (count % 100 == 0) {
int percent = (int) Math.floor(((double) count * 100.0) / (double) images.size());
double timeTemp = (double) (System.currentTimeMillis() - time) / 1000d;
int secsLeft =
(int) Math.round(((timeTemp / (double) count) * (double) images.size()) - timeTemp);
System.out.println(percent + "% finished (" + count + " files), " + secsLeft + " s left");
}
}
long timeTaken = (System.currentTimeMillis() - time);
float sec = ((float) timeTaken) / 1000f;
System.out.println(sec + " seconds taken, " + (timeTaken / count) + " ms per image.");
iw.commit();
iw.close();
}
private Document indexFiles() throws IOException {
System.out.println("---< indexing >-------------------------");
int count = 0;
DocumentBuilder builder = getDocumentBuilder();
ArrayList<String> allImages = FileUtils.getAllImages(new File("wang-1000"), true);
IndexWriter iw = LuceneUtils.createIndexWriter(indexPath, true);
Document document = null;
for (Iterator<String> iterator = allImages.iterator(); iterator.hasNext(); ) {
String filename = iterator.next();
BufferedImage image = ImageIO.read(new FileInputStream(filename));
document = builder.createDocument(image, filename);
iw.addDocument(document);
count++;
if (count % 50 == 0)
System.out.println("finished " + (count * 100) / allImages.size() + "% of the images.");
}
iw.close();
return document;
}
private void indexFiles(ArrayList<String> images, DocumentBuilder builder, String indexPath)
throws IOException {
// System.out.println(">> Indexing " + images.size() + " files.");
// DocumentBuilder builder = DocumentBuilderFactory.getExtensiveDocumentBuilder();
// DocumentBuilder builder = DocumentBuilderFactory.getFastDocumentBuilder();
IndexWriter iw = LuceneUtils.createIndexWriter(indexPath, true);
int count = 0;
long time = System.currentTimeMillis();
for (String identifier : images) {
Document doc = builder.createDocument(new FileInputStream(identifier), identifier);
iw.addDocument(doc);
count++;
if (count % 100 == 0) System.out.println(count + " files indexed.");
// if (count == 200) break;
}
long timeTaken = (System.currentTimeMillis() - time);
float sec = ((float) timeTaken) / 1000f;
System.out.println(sec + " seconds taken, " + (timeTaken / count) + " ms per image.");
iw.commit();
iw.close();
}
/**
* Index for each builder type
*
* @param image
* @param picture_id
* @param prefix
* @param builder
* @param conf
* @throws IOException
*/
private static void luceneIndexer(
BufferedImage image,
UUID picture_id,
String prefix,
DocumentBuilder builder,
IndexWriterConfig conf)
throws IOException {
File path = getPath(prefix);
log.debug("creating indexed path " + path.getAbsolutePath());
IndexWriter iw = new IndexWriter(FSDirectory.open(path), conf);
try {
Document document = builder.createDocument(image, picture_id.toString());
iw.addDocument(document);
} catch (Exception e) {
System.err.println("Error reading image or indexing it.");
e.printStackTrace();
}
// closing the IndexWriter
iw.close();
}