net.semanticmetadata.lire.impl.GenericImageSearcher.java Source code

Java tutorial

Introduction

Here is the source code for net.semanticmetadata.lire.impl.GenericImageSearcher.java

Source

/*
 * This file is part of the LIRE project: http://www.semanticmetadata.net/lire
 * LIRE is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * LIRE is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with LIRE; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 * We kindly ask you to refer the any or one of the following publications in
 * any publication mentioning or employing Lire:
 *
 * Lux Mathias, Savvas A. Chatzichristofis. Lire: Lucene Image Retrieval 
 * An Extensible Java CBIR Library. In proceedings of the 16th ACM International
 * Conference on Multimedia, pp. 1085-1088, Vancouver, Canada, 2008
 * URL: http://doi.acm.org/10.1145/1459359.1459577
 *
 * Lux Mathias. Content Based Image Retrieval with LIRE. In proceedings of the
 * 19th ACM International Conference on Multimedia, pp. 735-738, Scottsdale,
 * Arizona, USA, 2011
 * URL: http://dl.acm.org/citation.cfm?id=2072432
 *
 * Mathias Lux, Oge Marques. Visual Information Retrieval using Java and LIRE
 * Morgan & Claypool, 2013
 * URL: http://www.morganclaypool.com/doi/abs/10.2200/S00468ED1V01Y201301ICR025
 *
 * Copyright statement:
 * ====================
 * (c) 2002-2013 by Mathias Lux (mathias@juggle.at)
 *  http://www.semanticmetadata.net/lire, http://www.lire-project.net
 *
 * Updated: 11.07.13 10:51
 */
package net.semanticmetadata.lire.impl;

import net.semanticmetadata.lire.AbstractImageSearcher;
import net.semanticmetadata.lire.DocumentBuilder;
import net.semanticmetadata.lire.ImageDuplicates;
import net.semanticmetadata.lire.ImageSearchHits;
import net.semanticmetadata.lire.imageanalysis.LireFeature;
import net.semanticmetadata.lire.utils.ImageUtils;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.MultiFields;
import org.apache.lucene.util.Bits;

import java.awt.image.BufferedImage;
import java.io.IOException;
import java.util.HashMap;
import java.util.LinkedList;
import java.util.List;
import java.util.TreeSet;
import java.util.logging.Level;
import java.util.logging.Logger;

/**
 * This file is part of the Caliph and Emir project: http://www.SemanticMetadata.net
 * <br>Date: 01.02.2006
 * <br>Time: 00:17:02
 *
 * @author Mathias Lux, mathias@juggle.at
 * @deprecated
 */
public class GenericImageSearcher extends AbstractImageSearcher {
    protected Logger logger = Logger.getLogger(getClass().getName());
    Class<?> descriptorClass;
    String fieldName;

    private int maxHits = 10;
    protected TreeSet<SimpleResult> docs;
    private LireFeature cachedInstance;

    public GenericImageSearcher(int maxHits, Class<?> descriptorClass, String fieldName) {
        this.maxHits = maxHits;
        docs = new TreeSet<SimpleResult>();
        this.descriptorClass = descriptorClass;
        this.fieldName = fieldName;
        try {
            cachedInstance = (LireFeature) descriptorClass.newInstance();
        } catch (InstantiationException e) {
            e.printStackTrace();
        } catch (IllegalAccessException e) {
            e.printStackTrace();
        }
    }

    public ImageSearchHits search(BufferedImage image, IndexReader reader) throws IOException {
        logger.finer("Starting extraction.");
        LireFeature lireFeature = null;
        SimpleImageSearchHits searchHits = null;
        try {
            lireFeature = (LireFeature) descriptorClass.newInstance();
            // Scaling image is especially with the correlogram features very important!
            BufferedImage bimg = image;
            if (Math.max(image.getHeight(), image.getWidth()) > GenericDocumentBuilder.MAX_IMAGE_DIMENSION) {
                bimg = ImageUtils.scaleImage(image, GenericDocumentBuilder.MAX_IMAGE_DIMENSION);
            }
            lireFeature.extract(bimg);
            logger.fine("Extraction from image finished");

            float maxDistance = findSimilar(reader, lireFeature);
            searchHits = new SimpleImageSearchHits(this.docs, maxDistance);
        } catch (InstantiationException e) {
            logger.log(Level.SEVERE, "Error instantiating class for generic image searcher: " + e.getMessage());
        } catch (IllegalAccessException e) {
            logger.log(Level.SEVERE, "Error instantiating class for generic image searcher: " + e.getMessage());
        }
        return searchHits;
    }

    /**
     * @param reader
     * @param lireFeature
     * @return the maximum distance found for normalizing.
     * @throws java.io.IOException
     */
    protected float findSimilar(IndexReader reader, LireFeature lireFeature) throws IOException {
        float maxDistance = -1f, overallMaxDistance = -1f;
        float tmpDistance = 0f;
        // clear result set ...
        docs.clear();
        // Needed for check whether the document is deleted.
        Bits liveDocs = MultiFields.getLiveDocs(reader);

        int docs = reader.numDocs();
        Document d = null;
        for (int i = 0; i < docs; i++) {
            if (reader.hasDeletions() && !liveDocs.get(i))
                continue; // if it is deleted, just ignore it.

            d = reader.document(i);
            tmpDistance = getDistance(d, lireFeature);
            //            if (distance < 0 || Float.isNaN(distance))
            //                System.out.println("X");
            assert (tmpDistance >= 0);
            // calculate the overall max distance to normalize score afterwards
            if (overallMaxDistance < tmpDistance) {
                overallMaxDistance = tmpDistance;
            }
            // if it is the first document:
            if (maxDistance < 0) {
                maxDistance = tmpDistance;
            }
            // if the array is not full yet:
            if (this.docs.size() < maxHits) {
                this.docs.add(new SimpleResult(tmpDistance, d, i));
                if (tmpDistance > maxDistance)
                    maxDistance = tmpDistance;
            } else if (tmpDistance < maxDistance) {
                // if it is nearer to the sample than at least on of the current set:
                // remove the last one ...
                this.docs.remove(this.docs.last());
                // add the new one ...
                this.docs.add(new SimpleResult(tmpDistance, d, i));
                // and set our new distance border ...
                maxDistance = this.docs.last().getDistance();
            }
        }
        return maxDistance;
    }

    protected float getDistance(Document d, LireFeature lireFeature) {
        float distance = 0f;
        //            cachedInstance = (LireFeature) descriptorClass.newInstance();
        String[] cls = d.getValues(fieldName);
        if (cls != null && cls.length > 0) {
            cachedInstance.setStringRepresentation(cls[0]);
            distance = lireFeature.getDistance(cachedInstance);
        } else {
            logger.warning("No feature stored in this document!");
        }

        return distance;
    }

    public ImageSearchHits search(Document doc, IndexReader reader) throws IOException {
        SimpleImageSearchHits searchHits = null;
        try {
            LireFeature lireFeature = (LireFeature) descriptorClass.newInstance();

            String[] cls = doc.getValues(fieldName);
            if (cls != null && cls.length > 0)
                lireFeature.setStringRepresentation(cls[0]);
            float maxDistance = findSimilar(reader, lireFeature);

            searchHits = new SimpleImageSearchHits(this.docs, maxDistance);
        } catch (InstantiationException e) {
            logger.log(Level.SEVERE, "Error instantiating class for generic image searcher: " + e.getMessage());
        } catch (IllegalAccessException e) {
            logger.log(Level.SEVERE, "Error instantiating class for generic image searcher: " + e.getMessage());
        }
        return searchHits;
    }

    public ImageDuplicates findDuplicates(IndexReader reader) throws IOException {
        // get the first document:
        SimpleImageDuplicates simpleImageDuplicates = null;
        try {
            //            if (!IndexReader.indexExists(reader.directory()))
            //                throw new FileNotFoundException("No index found at this specific location.");
            Document doc = reader.document(0);

            LireFeature lireFeature = (LireFeature) descriptorClass.newInstance();
            String[] cls = doc.getValues(fieldName);
            if (cls != null && cls.length > 0)
                lireFeature.setStringRepresentation(cls[0]);

            HashMap<Float, List<String>> duplicates = new HashMap<Float, List<String>>();

            // Needed for check whether the document is deleted.
            Bits liveDocs = MultiFields.getLiveDocs(reader);

            int docs = reader.numDocs();
            int numDuplicates = 0;
            for (int i = 0; i < docs; i++) {
                if (reader.hasDeletions() && !liveDocs.get(i))
                    continue; // if it is deleted, just ignore it.
                Document d = reader.document(i);
                float distance = getDistance(d, lireFeature);

                if (!duplicates.containsKey(distance)) {
                    duplicates.put(distance, new LinkedList<String>());
                } else {
                    numDuplicates++;
                }
                duplicates.get(distance).add(d.getField(DocumentBuilder.FIELD_NAME_IDENTIFIER).stringValue());
            }

            if (numDuplicates == 0)
                return null;

            LinkedList<List<String>> results = new LinkedList<List<String>>();
            for (float f : duplicates.keySet()) {
                if (duplicates.get(f).size() > 1) {
                    results.add(duplicates.get(f));
                }
            }
            simpleImageDuplicates = new SimpleImageDuplicates(results);
        } catch (InstantiationException e) {
            logger.log(Level.SEVERE, "Error instantiating class for generic image searcher: " + e.getMessage());
        } catch (IllegalAccessException e) {
            logger.log(Level.SEVERE, "Error instantiating class for generic image searcher: " + e.getMessage());
        }
        return simpleImageDuplicates;

    }

    public String toString() {
        return "GenericSearcher using " + descriptorClass.getName();
    }

}