问题
I'm using flexicapture processor for recognizing my document. I've a case where i've a document with multiple pages i.e. a document have multiple images and each image is need to recognize.
I'm following below procedure to achieve my general task ,either one image in document or multiple image in a document;
- create a processor
- add document definition file or afl file
- run recognition as IDocument document = processor.RecognizeNextDocument(); But when it return a document, document, it has only one page,which is the first page of document, why is it so?
On the other case, if i use project instead processor,IProject, with below procedure
- create a project
- get batches from project project.getBatches(),
- add a document (that have multiple page) to batch
- recognize them The i've all pages information of document,IDocuments documents = batch.getDocuments(),
How i can achieve the same task wit processor? I want processor recognize all pages in a document and return a document with all pages in it. ?
if something is unclear, pls ask for more information. Please reply asap... Code :1 using flexicapture processor /** * */
/** * @author Nitin * */
import java.sql.BatchUpdateException;
import com.abbyy.FCEngine.*;
public class FlexicaputreVerificationUsingProcessor {
private static Object verificationWorkSet(Object object) {
// TODO Auto-generated method stub
return null;
}
private static void trace( String txt )
{
System.out.println( txt );
}
static private String samplesFolder;
static private String projectFolder;
static private String serialNumber;
static private String dllPath;
static {
samplesFolder = "C:\\ProgramData\\ABBYY\\SDK\\10\\FlexiCapture Engine\\Samples\\";
projectFolder = "C:\\Users\\Nitin\\FlexicaptureTest\\flexiverificationtest" ;
try {
java.io.FileInputStream file = new java.io.FileInputStream( samplesFolder + "SampleConfig\\SamplesConfig.txt" );
java.io.BufferedReader reader = new java.io.BufferedReader( new java.io.InputStreamReader( file ) );
serialNumber = reader.readLine();
dllPath = reader.readLine();
file.close();
} catch( java.io.IOException e ) {
System.out.println( e.getMessage() );
e.printStackTrace();
}
}
/**
* @param args
*/
public static void main(String[] args) {
// Load Engine
try {
trace("Loading engine");
IEngineLoader engineLoader= Engine.CreateEngineOutprocLoader();
IEngine engine = engineLoader.Load(serialNumber,dllPath);
try {
// Create and configure FlexiCaptureProcessor
trace("Creating and configureing FlexiCaptureProcessor");
IFlexiCaptureProcessor processor = engine.CreateFlexiCaptureProcessor();
processor.AddDocumentDefinitionFile( projectFolder + "\\Document_Definition_1.fcdot" );
trace("Adding images/pdf to processor");
final int fileCount = 1 ;
processor.AddImageFile(projectFolder + "\\don't upload to big .pdf");
engine.EnableRecognitionVariants( true );
trace("Creating Document collection");
IDocumentsCollection documentsCollection = engine.CreateDocumentsCollection();
trace( "Reconizing Images/pdfs..." );
int totalErrors = 0 ;
for ( int iterator = 0 ; iterator<fileCount; iterator++ ){
trace("Recongnizing image/pdf number: " +(iterator+1));
IDocument document = processor.RecognizeNextDocument();
trace("Getting last processing error for checksum");
IProcessingError lastProcessingError = processor.GetLastProcessingError() ;
if ( lastProcessingError !=null)
{
String errormsg = lastProcessingError.MessageText();
totalErrors++;
trace("Error occured while recognizeing document, Document number: "+(iterator+1)+ " with Error msg: "+errormsg);
//since we are not handling error (right now) so moving to next document for recognization
processor.ResumeProcessing(false);
}else {
trace("No error occured while recognization of document number : "+(iterator+1));
}
trace("Adding documents in Documents collection");
documentsCollection.Add(document);
}
if ( totalErrors == fileCount){
trace("Facing Error for all document while recongnization");
return ;
}
trace("Creaing Verification session");
try {
IVerificationSession verificationSession = engine.CreateVerificationSession(documentsCollection) ;
try {
//enabling context verification
verificationSession.getOptions().setVerifyFields(true);
//disabling group verification
verificationSession.getOptions().setVerifyBaseSymbols(false);
verificationSession.getOptions().setVerifyExtraSymbols(false);
try {
trace("Get NextWork Set");
IVerificationWorkSet verificationWorkSet = verificationSession.NextWorkSet();
if ( verificationWorkSet == null){
trace("first verificationWork set is null");
}else {
//process each work set in Verification session
trace("Processing Work Set");
while ( verificationWorkSet != null ){
try{
trace("Geting Verification group");
//get next group for verification
IVerificationGroup verificationGroup = verificationWorkSet.NextGroup();
if ( verificationGroup == null ){
trace("First verification group is null");
}else {
trace("processing each group of a workset");
//processing each group of a work set
while ( verificationGroup!= null){
int verificationObjectInAGroupCount = verificationGroup.getCount();
trace("Total number of verification object: " +verificationObjectInAGroupCount);
for ( int iterator = 0; iterator<verificationObjectInAGroupCount; iterator++){
trace ( "getting and Processing "+(iterator +1 ) + " verification object of A group");
//getting verification object
IVerificationObject verificationObject = verificationGroup.getElement(iterator);
if ( verificationObject == null){
trace("verification object is null");
}else {
if ( verificationObject.getType() == VerificationObjectTypeEnum.VOT_Group ) {
IGroupVerificationObject groupVerificationObject = verificationObject.AsGroupVerificationObject();
if ( groupVerificationObject == null){
System.out.println("group verification object is null ");
}
}else if ( verificationObject.getType() == VerificationObjectTypeEnum.VOT_Context) {
IContextVerificationObject contextVerificationObject = verificationObject.AsContextVerificationObject();
if ( contextVerificationObject == null){
trace("ContextVerification object is null");
}else {
IField field = contextVerificationObject.getField();
if ( field == null){
trace("field getting null");
}else {
System.out.println(" field full name: " +field.getFullName() + "\n Name: " +field.getName());
IFieldValue fieldValue = field.getValue();
if ( fieldValue == null){
trace("Field Value is Null");
}else {
trace ( "getting text from field value");
IText text = fieldValue.getAsText() ;
if ( text == null){
trace("text getting null in field value");
}else {
int wordCount = text.getRecognizedWordsCount() ;
trace("recognized word count: "+wordCount);
//getting words from text
for ( int wordIndex = 0 ; wordIndex<wordCount; wordIndex++ ){
trace ("processing word number :" +wordIndex);
IRecognizedWordInfo recognizedWordInfo = engine.CreateRecognizedWordInfo() ;
if ( recognizedWordInfo == null){
trace("Can't create recognizedWordInfo object using engine");
}else {
text.GetRecognizedWord(wordIndex, -1, recognizedWordInfo);
//getting characters from word
for (int characterIndex = 0 ; characterIndex<recognizedWordInfo.getText().length(); characterIndex++ ){
trace("processing character number : " +characterIndex);
IRecognizedCharacterInfo recognizedCharacterInfo = engine.CreateRecognizedCharacterInfo();
if ( recognizedCharacterInfo == null) {
trace("can't create recognizedCharacterInfo object");
}else {
recognizedWordInfo.GetRecognizedCharacter(characterIndex, -1, recognizedCharacterInfo);
System.out.println(" Character: " + recognizedCharacterInfo.getCharacter());
System.out.println(" Confidence level : " +recognizedCharacterInfo.getCharConfidence());
}
}
}
}
}
System.out.println(" Field Value : " +fieldValue.getAsString());
}
}
}
}
}
}
trace("Geting next Verification group");
verificationGroup = verificationWorkSet.NextGroup();
}
}
}catch (Exception e){
trace("Exception occured in getting next work group");
e.printStackTrace();
}
trace("Get next worksets");
//get next work set
verificationWorkSet = verificationSession.NextWorkSet();
}
}
}catch (Exception e){
e.printStackTrace();
}
}finally {
trace("closing Verification object");
verificationSession.Close();
}
} catch (Exception e) {
trace("Exception occured in creating verification sessions");
}
}catch (Exception e){
trace ("Exception occured in");
}
}catch (Exception e) {
// TODO: handle exception
e.printStackTrace();
}
finally {
trace("unloading Engine");
Engine.Unload();
}
}
}
Code : 2 using project
import java.io.File;
import java.io.IOException;
import java.sql.BatchUpdateException;
import com.abbyy.FCEngine.*;
public class VerificationStep {
//same as above
public static void main( String[] args )
{
// Load Engine
try {
trace("Loading engine");
IEngineLoader engineLoader= Engine.CreateEngineOutprocLoader();
IEngine engine = engineLoader.Load(serialNumber,dllPath);
try{
IProject project = engine.OpenProject( projectFolder + "\\flexitest.fcproj" );
try {
IBatch batch = null ;
trace( "Creating Batch..." );
IBatches batchs = project.getBatches();
if (batchs == null || batchs.getCount() == 0){
batch = project.getBatches().AddNew("TestBatch");
}
batch = batchs.getElement(0);
assert(batch == null);
try{
trace("opening batch");
batch.Open();
trace( "Adding pdfs..." );
batch.AddImage(projectFolder + "\\don't upload to big .pdf");
trace( "Reconizing pdfs..." );
batch.Recognize(null, RecognitionModeEnum.RM_ReRecognizeAll,null);
trace("Creating Verification object");
try {
IVerificationSession verificationSession = project.StartVerification(null);
try {
//enabling context verification
verificationSession.getOptions().setVerifyFields(true);
//disabling group verification
verificationSession.getOptions().setVerifyBaseSymbols(false);
verificationSession.getOptions().setVerifyExtraSymbols(false);
try {
trace("Get NextWork Set");
IVerificationWorkSet verificationWorkSet = verificationSession.NextWorkSet();
if ( verificationWorkSet == null){
trace("first verificationWork set is null");
}else {
//process each work set in Verification session
trace("Processing Work Set");
while ( verificationWorkSet != null ){
try{
trace("Geting Verification group");
//get next group for verification
IVerificationGroup verificationGroup = verificationWorkSet.NextGroup();
if ( verificationGroup == null ){
trace("First verification group is null");
}else {
trace("processing each group of a workset");
//processing each group of a work set
while ( verificationGroup!= null){
int verificationObjectInAGroupCount = verificationGroup.getCount();
trace("Total number of verification object: " +verificationObjectInAGroupCount);
for ( int iterator = 0; iterator<verificationObjectInAGroupCount; iterator++){
trace ( "getting and Processing "+(iterator +1 ) + " verification object of A group");
//getting verification object
IVerificationObject verificationObject = verificationGroup.getElement(iterator);
if ( verificationObject == null){
trace("verification object is null");
}else {
if ( verificationObject.getType() == VerificationObjectTypeEnum.VOT_Group ) {
IGroupVerificationObject groupVerificationObject = verificationObject.AsGroupVerificationObject();
if ( groupVerificationObject == null){
System.out.println("group verification object is null ");
}
}else if ( verificationObject.getType() == VerificationObjectTypeEnum.VOT_Context) {
IContextVerificationObject contextVerificationObject = verificationObject.AsContextVerificationObject();
if ( contextVerificationObject == null){
trace("ContextVerification object is null");
}else {
IField field = contextVerificationObject.getField();
if ( field == null){
trace("field getting null");
}else {
System.out.println(" field full name: " +field.getFullName() + "\n Name: " +field.getName());
IFieldValue fieldValue = field.getValue();
if ( fieldValue == null){
trace("Field Value is Null");
}else {
trace ( "getting text from field value");
IText text = fieldValue.getAsText() ;
if ( text == null){
trace("text getting null in field value");
}else {
int wordCount = text.getRecognizedWordsCount() ;
trace("recognized word count: "+wordCount);
//getting words from text
for ( int wordIndex = 0 ; wordIndex<wordCount; wordIndex++ ){
trace ("processing word number :" +wordIndex);
IRecognizedWordInfo recognizedWordInfo = engine.CreateRecognizedWordInfo() ;
if ( recognizedWordInfo == null){
trace("Can't create recognizedWordInfo object using engine");
}else {
text.GetRecognizedWord(wordIndex, -1, recognizedWordInfo);
//getting characters from word
for (int characterIndex = 0 ; characterIndex<recognizedWordInfo.getText().length(); characterIndex++ ){
trace("processing character number : " +characterIndex);
IRecognizedCharacterInfo recognizedCharacterInfo = engine.CreateRecognizedCharacterInfo();
if ( recognizedCharacterInfo == null) {
trace("can't create recognizedCharacterInfo object");
}else {
recognizedWordInfo.GetRecognizedCharacter(characterIndex, -1, recognizedCharacterInfo);
System.out.println(" Character: " + recognizedCharacterInfo.getCharacter());
System.out.println(" Confidence level : " +recognizedCharacterInfo.getCharConfidence());
}
}
}
}
}
System.out.println(" Field Value : " +fieldValue.getAsString());
}
}
}
}
}
}
verificationGroup = verificationWorkSet.NextGroup();
}
}
}catch (Exception e){
e.printStackTrace();
}
//get next work set
verificationWorkSet = verificationSession.NextWorkSet();
}
}
}catch (Exception e){
e.printStackTrace();
}
}finally {
verificationSession.Close();
}
}catch (Exception e){
e.printStackTrace();
}
trace ("Getting Documents");
IDocuments documents = batch.getDocuments();
trace ("Getting Fields and printing");
for ( int j = 0 ; j < documents.getCount(); j++){
trace ("Getting documnets:" +(j+1));
IDocument document = documents.getElement(j);
IDocumentDefinition definition = document.getDocumentDefinition();
assert( definition != null );
assert( document.getPages().getCount() == 1 );
trace( "DocumentType: " + document.getDocumentDefinition().getName() );
try {
trace("opening document");
document.Open(true);
IFields fields = document.getSections().Item( 0 ).getChildren();
for( int i = 0; i < fields.getCount(); i++ ) {
IField field = fields.getElement( i );
trace( field.getName() + ": " +
( field.getValue() != null ? field.getValue().getAsString() : "." ) );
}
}finally {
trace("closing document");
document.Close(true);
}
}
}finally {
trace("Closing Batch");
batch.Close();
}
}catch (Exception e){
System.out.println("Exception in creating Batch");
e.printStackTrace();
}
finally {
trace("closing project");
project.Close();
}
}catch (Exception e){
System.out.println("Exception occured while loading project");
e.printStackTrace();
}
}catch (Exception e) {
// TODO: handle exception
System.out.println("Exception occured while loading engine");
e.printStackTrace();
}
finally {
trace("unloading Engine");
Engine.Unload();
}
}
}
回答1:
Finally i got my solution, actually it recognize correctly, i'm handling them wrong way...
来源：https://stackoverflow.com/questions/24034598/flexicapture-processor-recognize-only-first-page-of-document