use of com.google.cloud.videointelligence.v1p2beta1.TextAnnotation in project java-video-intelligence by googleapis.
the class TextDetection method detectText.
// [START video_detect_text_beta]
/**
* Detect text in a video.
*
* @param filePath the path to the video file to analyze.
*/
public static VideoAnnotationResults detectText(String filePath) throws IOException, StatusRuntimeException, TimeoutException, ExecutionException, InterruptedException {
try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
// Read file
Path path = Paths.get(filePath);
byte[] data = Files.readAllBytes(path);
// Create the request
AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputContent(ByteString.copyFrom(data)).addFeatures(Feature.TEXT_DETECTION).build();
// asynchronously perform object tracking on videos
OperationFuture<AnnotateVideoResponse, AnnotateVideoProgress> future = client.annotateVideoAsync(request);
System.out.println("Waiting for operation to complete...");
// The first result is retrieved because a single video was processed.
AnnotateVideoResponse response = future.get(600, TimeUnit.SECONDS);
VideoAnnotationResults results = response.getAnnotationResults(0);
// Get only the first annotation for demo purposes.
TextAnnotation annotation = results.getTextAnnotations(0);
System.out.println("Text: " + annotation.getText());
// Get the first text segment.
TextSegment textSegment = annotation.getSegments(0);
System.out.println("Confidence: " + textSegment.getConfidence());
// For the text segment display it's time offset
VideoSegment videoSegment = textSegment.getSegment();
Duration startTimeOffset = videoSegment.getStartTimeOffset();
Duration endTimeOffset = videoSegment.getEndTimeOffset();
// Display the offset times in seconds, 1e9 is part of the formula to convert nanos to seconds
System.out.println(String.format("Start time: %.2f", startTimeOffset.getSeconds() + startTimeOffset.getNanos() / 1e9));
System.out.println(String.format("End time: %.2f", endTimeOffset.getSeconds() + endTimeOffset.getNanos() / 1e9));
// Show the first result for the first frame in the segment.
TextFrame textFrame = textSegment.getFrames(0);
Duration timeOffset = textFrame.getTimeOffset();
System.out.println(String.format("Time offset for the first frame: %.2f", timeOffset.getSeconds() + timeOffset.getNanos() / 1e9));
// Display the rotated bounding box for where the text is on the frame.
System.out.println("Rotated Bounding Box Vertices:");
List<NormalizedVertex> vertices = textFrame.getRotatedBoundingBox().getVerticesList();
for (NormalizedVertex normalizedVertex : vertices) {
System.out.println(String.format("\tVertex.x: %.2f, Vertex.y: %.2f", normalizedVertex.getX(), normalizedVertex.getY()));
}
return results;
}
}
use of com.google.cloud.videointelligence.v1p2beta1.TextAnnotation in project java-video-intelligence by googleapis.
the class TextDetection method detectTextGcs.
// [END video_detect_text]
// [START video_detect_text_gcs]
/**
* Detect Text in a video.
*
* @param gcsUri the path to the video file to analyze.
*/
public static VideoAnnotationResults detectTextGcs(String gcsUri) throws Exception {
try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
// Create the request
AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputUri(gcsUri).addFeatures(Feature.TEXT_DETECTION).build();
// asynchronously perform object tracking on videos
OperationFuture<AnnotateVideoResponse, AnnotateVideoProgress> future = client.annotateVideoAsync(request);
System.out.println("Waiting for operation to complete...");
// The first result is retrieved because a single video was processed.
AnnotateVideoResponse response = future.get(300, TimeUnit.SECONDS);
VideoAnnotationResults results = response.getAnnotationResults(0);
// Get only the first annotation for demo purposes.
TextAnnotation annotation = results.getTextAnnotations(0);
System.out.println("Text: " + annotation.getText());
// Get the first text segment.
TextSegment textSegment = annotation.getSegments(0);
System.out.println("Confidence: " + textSegment.getConfidence());
// For the text segment display it's time offset
VideoSegment videoSegment = textSegment.getSegment();
Duration startTimeOffset = videoSegment.getStartTimeOffset();
Duration endTimeOffset = videoSegment.getEndTimeOffset();
// Display the offset times in seconds, 1e9 is part of the formula to convert nanos to seconds
System.out.println(String.format("Start time: %.2f", startTimeOffset.getSeconds() + startTimeOffset.getNanos() / 1e9));
System.out.println(String.format("End time: %.2f", endTimeOffset.getSeconds() + endTimeOffset.getNanos() / 1e9));
// Show the first result for the first frame in the segment.
TextFrame textFrame = textSegment.getFrames(0);
Duration timeOffset = textFrame.getTimeOffset();
System.out.println(String.format("Time offset for the first frame: %.2f", timeOffset.getSeconds() + timeOffset.getNanos() / 1e9));
// Display the rotated bounding box for where the text is on the frame.
System.out.println("Rotated Bounding Box Vertices:");
List<NormalizedVertex> vertices = textFrame.getRotatedBoundingBox().getVerticesList();
for (NormalizedVertex normalizedVertex : vertices) {
System.out.println(String.format("\tVertex.x: %.2f, Vertex.y: %.2f", normalizedVertex.getX(), normalizedVertex.getY()));
}
return results;
}
}
use of com.google.cloud.videointelligence.v1p2beta1.TextAnnotation in project java-video-intelligence by googleapis.
the class TextDetection method detectText.
// [START video_detect_text]
/**
* Detect text in a video.
*
* @param filePath the path to the video file to analyze.
*/
public static VideoAnnotationResults detectText(String filePath) throws Exception {
try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
// Read file
Path path = Paths.get(filePath);
byte[] data = Files.readAllBytes(path);
// Create the request
AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputContent(ByteString.copyFrom(data)).addFeatures(Feature.TEXT_DETECTION).build();
// asynchronously perform object tracking on videos
OperationFuture<AnnotateVideoResponse, AnnotateVideoProgress> future = client.annotateVideoAsync(request);
System.out.println("Waiting for operation to complete...");
// The first result is retrieved because a single video was processed.
AnnotateVideoResponse response = future.get(300, TimeUnit.SECONDS);
VideoAnnotationResults results = response.getAnnotationResults(0);
// Get only the first annotation for demo purposes.
TextAnnotation annotation = results.getTextAnnotations(0);
System.out.println("Text: " + annotation.getText());
// Get the first text segment.
TextSegment textSegment = annotation.getSegments(0);
System.out.println("Confidence: " + textSegment.getConfidence());
// For the text segment display it's time offset
VideoSegment videoSegment = textSegment.getSegment();
Duration startTimeOffset = videoSegment.getStartTimeOffset();
Duration endTimeOffset = videoSegment.getEndTimeOffset();
// Display the offset times in seconds, 1e9 is part of the formula to convert nanos to seconds
System.out.println(String.format("Start time: %.2f", startTimeOffset.getSeconds() + startTimeOffset.getNanos() / 1e9));
System.out.println(String.format("End time: %.2f", endTimeOffset.getSeconds() + endTimeOffset.getNanos() / 1e9));
// Show the first result for the first frame in the segment.
TextFrame textFrame = textSegment.getFrames(0);
Duration timeOffset = textFrame.getTimeOffset();
System.out.println(String.format("Time offset for the first frame: %.2f", timeOffset.getSeconds() + timeOffset.getNanos() / 1e9));
// Display the rotated bounding box for where the text is on the frame.
System.out.println("Rotated Bounding Box Vertices:");
List<NormalizedVertex> vertices = textFrame.getRotatedBoundingBox().getVerticesList();
for (NormalizedVertex normalizedVertex : vertices) {
System.out.println(String.format("\tVertex.x: %.2f, Vertex.y: %.2f", normalizedVertex.getX(), normalizedVertex.getY()));
}
return results;
}
}
use of com.google.cloud.videointelligence.v1p2beta1.TextAnnotation in project java-video-intelligence by googleapis.
the class DetectIT method testTextDetectionGcs.
@Test
public void testTextDetectionGcs() throws Exception {
VideoAnnotationResults result = TextDetection.detectTextGcs(SPEECH_GCS_LOCATION);
boolean textExists = false;
for (TextAnnotation textAnnotation : result.getTextAnnotationsList()) {
for (String possibleText : POSSIBLE_TEXTS) {
if (textAnnotation.getText().toUpperCase().contains(possibleText.toUpperCase())) {
textExists = true;
break;
}
}
}
assertThat(textExists).isTrue();
}
use of com.google.cloud.videointelligence.v1p2beta1.TextAnnotation in project kie-wb-common by kiegroup.
the class DMNMarshaller method ddExtAugmentStunner.
private void ddExtAugmentStunner(Optional<org.kie.workbench.common.dmn.backend.definition.v1_1.dd.DMNDiagram> dmnDDDiagram, Node currentNode) {
if (!dmnDDDiagram.isPresent()) {
return;
}
Stream<DMNShape> drgShapeStream = dmnDDDiagram.get().getAny().stream().filter(DMNShape.class::isInstance).map(DMNShape.class::cast);
View content = (View) currentNode.getContent();
if (content.getDefinition() instanceof Decision) {
Decision d = (Decision) content.getDefinition();
internalAugment(drgShapeStream, d.getId(), content.getBounds().getUpperLeft(), d.getDimensionsSet(), content.getBounds().getLowerRight(), d.getBackgroundSet(), d::setFontSet);
} else if (content.getDefinition() instanceof InputData) {
InputData d = (InputData) content.getDefinition();
internalAugment(drgShapeStream, d.getId(), content.getBounds().getUpperLeft(), d.getDimensionsSet(), content.getBounds().getLowerRight(), d.getBackgroundSet(), d::setFontSet);
} else if (content.getDefinition() instanceof BusinessKnowledgeModel) {
BusinessKnowledgeModel d = (BusinessKnowledgeModel) content.getDefinition();
internalAugment(drgShapeStream, d.getId(), content.getBounds().getUpperLeft(), d.getDimensionsSet(), content.getBounds().getLowerRight(), d.getBackgroundSet(), d::setFontSet);
} else if (content.getDefinition() instanceof KnowledgeSource) {
KnowledgeSource d = (KnowledgeSource) content.getDefinition();
internalAugment(drgShapeStream, d.getId(), content.getBounds().getUpperLeft(), d.getDimensionsSet(), content.getBounds().getLowerRight(), d.getBackgroundSet(), d::setFontSet);
} else if (content.getDefinition() instanceof TextAnnotation) {
TextAnnotation d = (TextAnnotation) content.getDefinition();
internalAugment(drgShapeStream, d.getId(), content.getBounds().getUpperLeft(), d.getDimensionsSet(), content.getBounds().getLowerRight(), d.getBackgroundSet(), d::setFontSet);
}
}
Aggregations