Google Cloud Functions Text Extraction from image using Vision API

Question

I am following the tutorial to extract text from images at:

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

But I do not wish to translate the text, I wish to detect and save the text.

The tutorial implements 3 functions:

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

I just wish to detect text and save the text but I could not remove the translation portion of the code below:

/**
 * 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);
    });
}

After that, I just wish to save the detectec text to a file, as the code below shows:

/**
 * 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.`);
    });
};

I'd follow these instead: https://github.com/googleapis/nodejs-vision/tree/master/samples I can help if you're having issues with those samples. — Torry Yang, Jun 26 '18 at 21:37
Thanks but I do not wish to install the libraries locally, I wish to run the translation as a function in google cloud... I tried to use the code in the link that you sent but since I am not js expert I was not able to do it. — Cristiana SP, Jul 02 '18 at 14:38
the tutorial and the samples use the same libraries and can both run on google cloud. would you prefer to do this with Go, Java, .NET, PHP, Python or Ruby? — Torry Yang, Jul 02 '18 at 17:12
Are you still trying to use this code or you moved to Python? @CristianaS.Parada — Mangu, Aug 21 '18 at 07:42

score 3 · Accepted Answer · answered Aug 23 '18 at 08:58

So, the tutorials there are based in a much more 'complex' setup (using Pub Sub and Translate also), and you only want to extract the text, so, with this, you should be able:

'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");
}

My dependencies, in my package.json file:

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

You can later on extend this to save this text to Storage, if you wish to. There are other tutorials on how to do so.

Google Cloud Functions Text Extraction from image using Vision API

1 Answers1