如何使用 Google Cloud Vision API 确认图像（包含手写和打印文本）是不是包含手写文本？
Posted
技术标签:
【中文标题】如何使用 Google Cloud Vision API 确认图像（包含手写和打印文本）是不是包含手写文本？【英文标题】：How to confirm whether an image (containing both handwritten and printed texts) contains handwritten text using Google Cloud Vision API?如何使用 Google Cloud Vision API 确认图像（包含手写和打印文本）是否包含手写文本？ 【发布时间】：2020-02-09 16:35:26 【问题描述】：我正在使用 Cloud Vision API - DOCUMENT_TEXT_DETECTION 功能从图像中检测手写文本。尽管它为我提取了手写数据，但是当涉及到同时具有打印文本和手写文本的图像时，它没有响应标识符，该标识符表示该位是手写的并且该位是打印的。直截了当地问，我想确认一张图片是否有手写文字。注意 - 图像可能仅包含手写文本或打印和手写文本的组合。
如果有人可以详细说明我需要传递给云视觉 api 以实现结果的所有其他属性，将不胜感激？或者有没有办法让 Cloud Vision API 标记出我的图像是否包含手写数据。
示例代码
public class Detect
public static void main(String args[])
String filePath = "C:\\Development_Avecto\\images.jpg";
try
detectDocumentText(filePath, System.out);
catch (IOException e)
e.printStackTrace();
catch (Exception e)
e.printStackTrace();
public static void detectDocumentText(String filePath, PrintStream out) throws Exception, IOException
List<AnnotateImageRequest> requests = new ArrayList<>();
ByteString imgBytes = ByteString.readFrom(new FileInputStream(filePath));
Image img = Image.newBuilder().setContent(imgBytes).build();
Feature feat = Feature.newBuilder().setType(Type.DOCUMENT_TEXT_DETECTION).build();
AnnotateImageRequest request = AnnotateImageRequest.newBuilder().addFeatures(feat).setImage(img).build();
requests.add(request);
try (ImageAnnotatorClient client = ImageAnnotatorClient.create())
BatchAnnotateImagesResponse response = client.batchAnnotateImages(requests);
List<AnnotateImageResponse> responses = response.getResponsesList();
client.close();
for (AnnotateImageResponse res : responses)
if (res.hasError())
out.printf("Error: %s\n", res.getError().getMessage());
return;
TextAnnotation annotation = res.getFullTextAnnotation();
for (Page page : annotation.getPagesList())
String pageText = "";
for (Block block : page.getBlocksList())
String blockText = "";
for (Paragraph para : block.getParagraphsList())
String paraText = "";
for (Word word : para.getWordsList())
String wordText = "";
for (Symbol symbol : word.getSymbolsList())
wordText = wordText + symbol.getText();
out.format("Symbol text: %s (confidence: %f)\n",
symbol.getText(),symbol.getConfidence());
out.format("Word text: %s (confidence: %f)\n\n",wordText, word.getConfidence());
paraText = String.format("%s %s", paraText,wordText);
// Output Example using Paragraph:
out.println("\nParagraph: \n" + paraText);
out.format("Paragraph Confidence: %f\n",para.getConfidence());
blockText = blockText + paraText;
pageText = pageText + blockText;
out.println("\nComplete annotation:");
out.println(annotation.getText());
图片 -
【问题讨论】：
【参考方案1】：这可能会有所帮助，这是工作示例。
public async Task<string> GetText(string imgPath,string language,string type)
TextResult = JsonResult = "";
var credential = CreateCredential();
var service = CreateService(credential);
service.HttpClient.Timeout = new TimeSpan(1,1,1);
byte[] file = File.ReadAllBytes(imgPath);
BatchAnnotateImagesRequest batchRequest = new BatchAnnotateImagesRequest();
batchRequest.Requests= new List<AnnotateImageRequest>();
batchRequest.Requests.Add(new AnnotateImageRequest()
Features = new List<Feature>() new Feature() Type = type, MaxResults =
1 , ,
ImageContext = new ImageContext() LanguageHints = new List<string>()
language ,
Image = new Image() Content = Convert.ToBase64String(file)
);
var annotate = service.Images.Annotate(batchRequest);
BatchAnnotateImagesResponse batchAnnotateImagesResponse = annotate.Execute();
if (batchAnnotateImagesResponse.Responses.Any())
AnnotateImageResponse annotateImageResponse =
batchAnnotateImagesResponse.Responses[0];
if (annotateImageResponse.Error != null)
if (annotateImageResponse.Error.Message != null)
Error = annotateImageResponse.Error.Message;
else
switch (type)
case "TEXT_DETECTION":
if (annotateImageResponse.TextAnnotations != null &&
annotateImageResponse.TextAnnotations.Any())
TextResult =
annotateImageResponse.TextAnnotations[0].Description.Replace("\n", "\r\n");
break;
case "DOCUMENT_TEXT_DETECTION":
if (annotateImageResponse.TextAnnotations != null &&
annotateImageResponse.TextAnnotations.Any())
TextResult =
annotateImageResponse.TextAnnotations[0].Description.Replace("\n", "\r\n");
break;
case "FACE_DETECTION":
if (annotateImageResponse.FaceAnnotations != null &&
annotateImageResponse.FaceAnnotations.Any())
TextResult =
JsonConvert.SerializeObject(annotateImageResponse.FaceAnnotations[0]);
break;
case "LOGO_DETECTION":
if (annotateImageResponse.LogoAnnotations != null &&
annotateImageResponse.LogoAnnotations.Any())
TextResult =
JsonConvert.SerializeObject(annotateImageResponse.LogoAnnotations[0]);
break;
case "LABEL_DETECTION":
if (annotateImageResponse.LabelAnnotations != null &&
annotateImageResponse.LabelAnnotations.Any())
TextResult =
JsonConvert.SerializeObject(annotateImageResponse.LabelAnnotations[0]);
break;
case "LANDMARK_DETECTION":
if (annotateImageResponse.LandmarkAnnotations != null &&
annotateImageResponse.LandmarkAnnotations.Any())
TextResult =
JsonConvert.SerializeObject(annotateImageResponse.LandmarkAnnotations[0]);
break;
case "SAFE_SEARCH_DETECTION":
if (annotateImageResponse.SafeSearchAnnotation != null)
TextResult =
JsonConvert.SerializeObject(annotateImageResponse.SafeSearchAnnotation);
break;
case "IMAGE_PROPERTIES":
if (annotateImageResponse.ImagePropertiesAnnotation != null)
TextResult =
JsonConvert.SerializeObject(annotateImageResponse.ImagePropertiesAnnotation);
break;
return TextResult;
【讨论】：
以上是关于如何使用 Google Cloud Vision API 确认图像（包含手写和打印文本）是不是包含手写文本？的主要内容，如果未能解决你的问题，请参考以下文章
Google Cloud Vision - 如何使用 Node.js 发送请求属性
如何使用 Google Cloud Vision API 读取一列文本
如何修复 Google Cloud Vision 的分段错误？
如何使用 Google Cloud Vision API 确认图像（包含手写和打印文本）是不是包含手写文本？