从乐谱中提取每行的音符量
我想知道有没有办法提取乐谱中的每一行小节。我不太确定是否已经有这样的算法，所以我想到了从左到右扫描乐谱，提取每一行上方和下方的空白区域。
我并不是想把乐谱转换成MusicXML格式或者提取其他有用的信息。其实我处理的就是一份普通的文档。我需要把段落分开。我对段落传达的信息不感兴趣，只是想把它们从文档的不同区域分开。在这种情况下，一个段落就是一行小节。我不需要单独的小节，只需要每行乐谱上的所有小节。
这是我希望从完整乐谱中得到的输出，但不包括标题、作曲家等信息。
1 个回答
5
假设你有一份包含乐谱的PDF文件，我会使用Apache PDFBox来从这个PDF文件中提取出图片。接着，你需要找到你想要的整段乐谱的位置坐标，然后用选定的图片来定义裁剪的坐标，最后对图片进行处理，直到得到你想要的效果。
PDDocument document = null;
document = PDDocument.load(inFile);
List pages = document.getDocumentCatalog().getAllPages();
Iterator iter = pages.iterator();
while (iter.hasNext()) {
PDPage page = (PDPage) iter.next();
PDResources resources = page.getResources();
Map pageImages = resources.getImages();
if (pageImages != null) {
Iterator imageIter = pageImages.keySet().iterator();
while (imageIter.hasNext()) {
String key = (String) imageIter.next();
PDXObjectImage image = (PDXObjectImage) pageImages.get(key);
image.write2OutputStream(/* some output stream */);
}
}
}
这里有一段在Apache PDFBox中可以用的示例代码。
import java.io.File;
import java.io.IOException;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDResources;
import org.apache.pdfbox.pdmodel.encryption.AccessPermission;
import org.apache.pdfbox.pdmodel.encryption.StandardDecryptionMaterial;
import org.apache.pdfbox.pdmodel.graphics.xobject.PDXObject;
import org.apache.pdfbox.pdmodel.graphics.xobject.PDXObjectForm;
import org.apache.pdfbox.pdmodel.graphics.xobject.PDXObjectImage;
/**
* This will read a read pdf and extract images. <br/><br/>
*
* usage: java org.apache.pdfbox.ExtractImages <pdffile> <password> [imageprefix]
*
* @author <a href="mailto:ben@benlitchfield.com">Ben Litchfield</a>
* @version $Revision: 1.7 $
*/
public class ExtractImages
{
private int imageCounter = 1;
private static final String PASSWORD = "-password";
private static final String PREFIX = "-prefix";
private static final String ADDKEY = "-addkey";
private static final String NONSEQ = "-nonSeq";
private ExtractImages()
{
}
/**
* This is the entry point for the application.
*
* @param args The command-line arguments.
*
* @throws Exception If there is an error decrypting the document.
*/
public static void main( String[] args ) throws Exception
{
ExtractImages extractor = new ExtractImages();
extractor.extractImages( args );
}
private void extractImages( String[] args ) throws Exception
{
if( args.length < 1 || args.length > 4 )
{
usage();
}
else
{
String pdfFile = null;
String password = "";
String prefix = null;
boolean addKey = false;
boolean useNonSeqParser = false;
for( int i=0; i<args.length; i++ )
{
if( args[i].equals( PASSWORD ) )
{
i++;
if( i >= args.length )
{
usage();
}
password = args[i];
}
else if( args[i].equals( PREFIX ) )
{
i++;
if( i >= args.length )
{
usage();
}
prefix = args[i];
}
else if( args[i].equals( ADDKEY ) )
{
addKey = true;
}
else if( args[i].equals( NONSEQ ) )
{
useNonSeqParser = true;
}
else
{
if( pdfFile == null )
{
pdfFile = args[i];
}
}
}
if(pdfFile == null)
{
usage();
}
else
{
if( prefix == null && pdfFile.length() >4 )
{
prefix = pdfFile.substring( 0, pdfFile.length() -4 );
}
PDDocument document = null;
try
{
if (useNonSeqParser)
{
document = PDDocument.loadNonSeq(new File(pdfFile), null, password);
}
else
{
document = PDDocument.load( pdfFile );
if( document.isEncrypted() )
{
StandardDecryptionMaterial spm = new StandardDecryptionMaterial(password);
document.openProtection(spm);
}
}
AccessPermission ap = document.getCurrentAccessPermission();
if( ! ap.canExtractContent() )
{
throw new IOException(
"Error: You do not have permission to extract images." );
}
List pages = document.getDocumentCatalog().getAllPages();
Iterator iter = pages.iterator();
while( iter.hasNext() )
{
PDPage page = (PDPage)iter.next();
PDResources resources = page.getResources();
// extract all XObjectImages which are part of the page resources
processResources(resources, prefix, addKey);
}
}
finally
{
if( document != null )
{
document.close();
}
}
}
}
}
private void processResources(PDResources resources, String prefix, boolean addKey) throws IOException
{
if (resources == null)
{
return;
}
Map<String, PDXObject> xobjects = resources.getXObjects();
if( xobjects != null )
{
Iterator<String> xobjectIter = xobjects.keySet().iterator();
while( xobjectIter.hasNext() )
{
String key = xobjectIter.next();
PDXObject xobject = xobjects.get( key );
// write the images
if (xobject instanceof PDXObjectImage)
{
PDXObjectImage image = (PDXObjectImage)xobject;
String name = null;
if (addKey)
{
name = getUniqueFileName( prefix + "_" + key, image.getSuffix() );
}
else
{
name = getUniqueFileName( prefix, image.getSuffix() );
}
System.out.println( "Writing image:" + name );
image.write2file( name );
}
// maybe there are more images embedded in a form object
else if (xobject instanceof PDXObjectForm)
{
PDXObjectForm xObjectForm = (PDXObjectForm)xobject;
PDResources formResources = xObjectForm.getResources();
processResources(formResources, prefix, addKey);
}
}
}
}
private String getUniqueFileName( String prefix, String suffix )
{
String uniqueName = null;
File f = null;
while( f == null || f.exists() )
{
uniqueName = prefix + "-" + imageCounter;
f = new File( uniqueName + "." + suffix );
imageCounter++;
}
return uniqueName;
}
/**
* This will print the usage requirements and exit.
*/
private static void usage()
{
System.err.println( "Usage: java org.apache.pdfbox.ExtractImages [OPTIONS] <PDF file>\n" +
" -password <password> Password to decrypt document\n" +
" -prefix <image-prefix> Image prefix(default to pdf name)\n" +
" -addkey add the internal image key to the file name\n" +
" -nonSeq Enables the new non-sequential parser\n" +
" <PDF file> The PDF document to use\n"
);
System.exit( 1 );
}
}
现在要裁剪图片，你可以使用：
/**
* Crop the main image according to this rectangle, and scale it to the
* correct size for a thumbnail.
*/
public InputStream cropAndScale(InputStream mainImageStream,
CropRectangle crop) {
try {
RenderedOp mainImage = loadImage(mainImageStream);
RenderedOp opaqueImage = makeImageOpaque(mainImage);
RenderedOp croppedImage = cropImage(opaqueImage, crop);
RenderedOp scaledImage = scaleImage(croppedImage);
byte[] jpegBytes = encodeAsJpeg(scaledImage);
return new ByteArrayInputStream(jpegBytes);
} catch (Exception e) {
throw new IllegalStateException("Failed to scale the image", e);
}
}