Lire源码解析一

Lucene image retrieval是以图搜图的java开源框架，这几天没什么事，就读了点源码，并写了点注释，特在这分享给大家。

这里主要给出的是BOVWBuilder.java、Kmeans.java及Cluster.java。就是用词频对特征进行编码，用到是BOF(bag of feature)模型，原理就是提取N张图片的特征(比如sift),放在一起就可以得到矩阵，然后对矩阵进行kmeans聚类，就会到到若干个聚类中心；对于新来的一副图像，我们分别计算该特征点与那个聚类中心最近，这样该聚类中心的量值就加1，这样就可以编码得到与聚类中心个数想等的维数向量。

一切都从BOVWBuilder中index函数开始...

BOVWBuilder.java(包含注释)

package lmc.imageretrieval.imageanalysis.bovw;

import java.io.File;
import java.io.IOException;
import java.text.DecimalFormat;
import java.text.NumberFormat;
import java.util.Arrays;
import java.util.HashSet;
import java.util.Iterator;
import java.util.LinkedList;

import javax.swing.ProgressMonitor;

import lmc.imageretrieval.imageanalysis.Histogram;
import lmc.imageretrieval.imageanalysis.LireFeature;
import lmc.imageretrieval.tools.DocumentBuilder;
import lmc.imageretrieval.utils.SerializationUtils;

import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StoredField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.index.IndexableField;
import org.apache.lucene.index.MultiFields;
import org.apache.lucene.index.Term;
import org.apache.lucene.util.Bits;
import org.apache.lucene.util.Version;

public class BOVWBuilder {
    IndexReader reader;
    // number of documents used to build the vocabulary / clusters.
    private int numDocsForVocabulary = 500;
    private int numClusters = 512;
    private Cluster[] clusters = null;
    DecimalFormat df = (DecimalFormat) NumberFormat.getNumberInstance();
    private ProgressMonitor pm = null;

    protected LireFeature lireFeature;
    protected String localFeatureFieldName;
    protected String visualWordsFieldName;
    protected String localFeatureHistFieldName;
    protected String clusterFile;

    public static boolean DELETE_LOCAL_FEATURES = true;
    /**
     *
     * @param reader
     * @deprecated
     */
    public BOVWBuilder(IndexReader reader) {
        this.reader = reader;
    }

    /**
     * Creates a new instance of the BOVWBuilder using the given reader. The numDocsForVocabulary
     * indicates how many documents of the index are used to build the vocabulary (clusters).
     *
     * @param reader               the reader used to open the Lucene index,
     * @param numDocsForVocabulary gives the number of documents for building the vocabulary (clusters).
     * @deprecated
     */
    public BOVWBuilder(IndexReader reader, int numDocsForVocabulary) {
        this.reader = reader;
        this.numDocsForVocabulary = numDocsForVocabulary;
    }

    /**
     * Creates a new instance of the BOVWBuilder using the given reader. The numDocsForVocabulary
     * indicates how many documents of the index are used to build the vocabulary (clusters). The numClusters gives
     * the number of clusters k-means should find. Note that this number should be lower than the number of features,
     * otherwise an exception will be thrown while indexing.
     *
     * @param reader               the index reader
     * @param numDocsForVocabulary the number of documents that should be sampled for building the visual vocabulary
     * @param numClusters          the size of the visual vocabulary
     * @deprecated
     */
    public BOVWBuilder(IndexReader reader, int numDocsForVocabulary, int numClusters) {
        this.numDocsForVocabulary = numDocsForVocabulary;
        this.numClusters = numClusters;
        this.reader = reader;
    }

    /**
     * Creates a new instance of the BOVWBuilder using the given reader. TODO: write
     *
     * @param reader               the index reader
     * @param lireFeature          lireFeature used
     */
    public BOVWBuilder(IndexReader reader, LireFeature lireFeature) {
        this.reader = reader;
        this.lireFeature = lireFeature;
    }

    /**
     * Creates a new instance of the BOVWBuilder using the given reader. The numDocsForVocabulary
     * indicates how many documents of the index are used to build the vocabulary (clusters).
     * TODO: write
     *
     * @param reader               the index reader
     * @param lireFeature          lireFeature used
     * @param numDocsForVocabulary the number of documents that should be sampled for building the visual vocabulary
     */
    public BOVWBuilder(IndexReader reader, LireFeature lireFeature, int numDocsForVocabulary) {
        this.numDocsForVocabulary = numDocsForVocabulary;
        this.reader = reader;
        this.lireFeature = lireFeature;
    }

    /**
     * Creates a new instance of the BOVWBuilder using the given reader. The numDocsForVocabulary
     * indicates how many documents of the index are used to build the vocabulary (clusters). The numClusters gives
     * the number of clusters k-means should find. Note that this number should be lower than the number of features,
     * otherwise an exception will be thrown while indexing. TODO: write
     *
     * @param reader               the index reader
     * @param lireFeature          lireFeature used
     * @param numDocsForVocabulary the number of documents that should be sampled for building the visual vocabulary
     * @param numClusters          the size of the visual vocabulary
     */
    public BOVWBuilder(IndexReader reader, LireFeature lireFeature, int numDocsForVocabulary, int numClusters) {
        this.numDocsForVocabulary = numDocsForVocabulary;
        this.numClusters = numClusters;
        this.reader = reader;
        this.lireFeature = lireFeature;
    }

    protected void init() {
        localFeatureFieldName = lireFeature.getFieldName();
        visualWordsFieldName = lireFeature.getFieldName() + DocumentBuilder.FIELD_NAME_BOVW;
        localFeatureHistFieldName = lireFeature.getFieldName()+ DocumentBuilder.FIELD_NAME_BOVW_VECTOR;
        clusterFile = "./clusters-bovw" + lireFeature.getFeatureName() +  ".dat";
    }

    /**
     * Uses an existing index, where each and every document should have a set of local features. A number of
     * random images (numDocsForVocabulary) is selected and clustered to get a vocabulary of visual words
     * (the cluster means). For all images a histogram on the visual words is created and added to the documents.
     * Pre-existing histograms are deleted, so this method can be used for re-indexing.
     *
     * @throws java.io.IOException
     */
    public void index() throws IOException {
        init();
        df.setMaximumFractionDigits(3);
        // find the documents for building the vocabular