Question

我正在按照教程从以下位置提取图像中的文本：

https://cloud.google.com/functions/docs/tutorials/ocr?authuser=1

但是我不想翻译文本，我想检测并保存文本。

本教程实现了3个功能：

gcloud beta functions deploy ocr-extract --trigger-bucket [YOUR_IMAGE_BUCKET_NAME] --entry-point processImage

gcloud beta functions deploy ocr-translate --trigger-topic [YOUR_TRANSLATE_TOPIC_NAME] --entry-point translateText

gcloud beta functions deploy ocr-save --trigger-topic [YOUR_RESULT_TOPIC_NAME] --entry-point saveResult

我只希望检测文本并保存文本，但是无法删除以下代码的翻译部分：

/**
 * Detects the text in an image using the Google Vision API.
 *
 * @param {string} bucketName Cloud Storage bucket name.
 * @param {string} filename Cloud Storage file name.
 * @returns {Promise}
 */
function detectText (bucketName, filename) {
  let text;

  console.log(`Looking for text in image ${filename}`);
  return vision.textDetection({ source: { imageUri: `gs://${bucketName}/${filename}` } })
    .then(([detections]) => {
      const annotation = detections.textAnnotations[0];
      text = annotation ? annotation.description : '';
      console.log(`Extracted text from image (${text.length} chars)`);
      return translate.detect(text);
    })
    .then(([detection]) => {
      if (Array.isArray(detection)) {
        detection = detection[0];
      }
      console.log(`Detected language "${detection.language}" for ${filename}`);

      // Submit a message to the bus for each language we're going to translate to
      const tasks = config.TO_LANG.map((lang) => {
        let topicName = config.TRANSLATE_TOPIC;
        if (detection.language === lang) {
          topicName = config.RESULT_TOPIC;
        }
        const messageData = {
          text: text,
          filename: filename,
          lang: lang,
          from: detection.language
        };

        return publishResult(topicName, messageData);
      });

      return Promise.all(tasks);
    });
}

之后，我只想将detectec文本保存到文件中，如下面的代码所示：

/**
 * Saves the data packet to a file in GCS. Triggered from a message on a Pub/Sub
 * topic.
 *
 * @param {object} event The Cloud Functions event.
 * @param {object} event.data The Cloud Pub/Sub Message object.
 * @param {string} event.data.data The "data" property of the Cloud Pub/Sub
 * Message. This property will be a base64-encoded string that you must decode.
     */
exports.saveResult = (event) => {
  const pubsubMessage = event.data;
  const jsonStr = Buffer.from(pubsubMessage.data, 'base64').toString();
  const payload = JSON.parse(jsonStr);

  return Promise.resolve()
    .then(() => {
      if (!payload.text) {
        throw new Error('Text not provided. Make sure you have a "text" property in your request');
      }
      if (!payload.filename) {
        throw new Error('Filename not provided. Make sure you have a "filename" property in your request');
      }
      if (!payload.lang) {
        throw new Error('Language not provided. Make sure you have a "lang" property in your request');
      }

      console.log(`Received request to save file ${payload.filename}`);

      const bucketName = config.RESULT_BUCKET;
      const filename = renameImageForSave(payload.filename, payload.lang);
      const file = storage.bucket(bucketName).file(filename);

      console.log(`Saving result to ${filename} in bucket ${bucketName}`);

      return file.save(payload.text);
    })
    .then(() => {
      console.log(`File saved.`);
    });
};

Answer 1

因此，那里的教程基于更加“复杂”的设置（也使用Pub Sub和Translate），并且您只想提取文本，因此，您应该能够：

'use strict';
const Storage = require('@google-cloud/storage');
const Vision = require('@google-cloud/vision');
const bucketName = 'YOUR_BUCKET';
const srcFilename = 'YOUR_IMAGE.jpg';
const projectId = 'YOUR_PROJECT_ID';
const storage = new Storage({
    projectId: projectId
});
const vision = new Vision.ImageAnnotatorClient({
    projectId: projectId
});
exports.processImage = (req, res) => {
    let text;
    vision.textDetection(`gs://${bucketName}/${srcFilename}`)
        .then(([detections]) => {
            const annotation = detections.textAnnotations[0];
            text = annotation ? annotation.description : '';
            console.log(`Extracted text: ${text}`);
            console.log(`Extracted text from image (${text.length} chars)`);
        }).catch(vis_err => {
            console.error("Vision error:" , vis_err);
        });
    res.status(200).send("OK");
}

我的依存关系，在我的package.json文件中：

  "dependencies": {
    "@google-cloud/vision": "0.21.0"
  },

如果需要，您以后可以扩展它以将文本保存到存储中。还有其他有关如何执行此操作的教程。

使用Vision API从图像中提取Google Cloud Functions文本

1 个答案: