Recognize Text in Images Securely with Cloud Vision using Firebase Auth and Functions on Apple platforms

In order to call a Google Cloud API from your app, you need to create an intermediate REST API that handles authorization and protects secret values such as API keys. You then need to write code in your mobile app to authenticate to and communicate with this intermediate service.

One way to create this REST API is by using Firebase Authentication and Functions, which gives you a managed, serverless gateway to Google Cloud APIs that handles authentication and can be called from your mobile app with pre-built SDKs.

This guide demonstrates how to use this technique to call the Cloud Vision API from your app. This method will allow all authenticated users to access Cloud Vision billed services through your Cloud project, so consider whether this auth mechanism is sufficient for your use case before proceeding.

Before you begin

Configure your project

If you have not already added Firebase to your app, do so by following the steps in the getting started guide.

Use Swift Package Manager to install and manage Firebase dependencies.

  1. In Xcode, with your app project open, navigate to File > Add Packages.
  2. When prompted, add the Firebase Apple platforms SDK repository:
  4. Choose the Firebase ML library.
  5. Add the -ObjC flag to the Other Linker Flags section of your target's build settings.
  6. When finished, Xcode will automatically begin resolving and downloading your dependencies in the background.

Next, perform some in-app setup:

  1. In your app, import Firebase:


    import FirebaseMLModelDownloader


    @import FirebaseMLModelDownloader;

A few more configuration steps, and we're ready to go:

  1. If you have not already enabled Cloud-based APIs for your project, do so now:

    1. Open the Firebase ML APIs page of the Firebase console.
    2. If you have not already upgraded your project to the Blaze pricing plan, click Upgrade to do so. (You will be prompted to upgrade only if your project isn't on the Blaze plan.)

      Only Blaze-level projects can use Cloud-based APIs.

    3. If Cloud-based APIs aren't already enabled, click Enable Cloud-based APIs.
  2. Configure your existing Firebase API keys to disallow access to the Cloud Vision API:
    1. Open the Credentials page of the Cloud console.
    2. For each API key in the list, open the editing view, and in the Key Restrictions section, add all of the available APIs except the Cloud Vision API to the list.

Deploy the callable function

Next, deploy the Cloud Function you will use to bridge your app and the Cloud Vision API. The functions-samples repository contains an example you can use.

By default, accessing the Cloud Vision API through this function will allow only authenticated users of your app access to the Cloud Vision API. You can modify the function for different requirements.

To deploy the function:

  1. Clone or download the functions-samples repo and change to the Node-1st-gen/vision-annotate-image directory:
    git clone
    cd Node-1st-gen/vision-annotate-image
  2. Install dependencies:
    cd functions
    npm install
    cd ..
  3. If you don't have the Firebase CLI, install it.
  4. Initialize a Firebase project in the vision-annotate-image directory. When prompted, select your project in the list.
    firebase init
  5. Deploy the function:
    firebase deploy --only functions:annotateImage

Add Firebase Auth to your app

The callable function deployed above will reject any request from non-authenticated users of your app. If you have not already done so, you will need to add Firebase Auth to your app.

Add necessary dependencies to your app

Use Swift Package Manager to install the Cloud Functions for Firebase library.

Now you are ready to start recognizing text in images.

1. Prepare the input image

In order to call Cloud Vision, the image must be formatted as a base64-encoded string. To process a UIImage:


guard let imageData = uiImage.jpegData(compressionQuality: 1.0) else { return }
let base64encodedImage = imageData.base64EncodedString()


NSData *imageData = UIImageJPEGRepresentation(uiImage, 1.0f);
NSString *base64encodedImage =
  [imageData base64EncodedStringWithOptions:NSDataBase64Encoding76CharacterLineLength];

2. Invoke the callable function to recognize text

To recognize landmarks in an image, invoke the callable function passing a JSON Cloud Vision request.

  1. First, initialize an instance of Cloud Functions:


    lazy var functions = Functions.functions()


    @property(strong, nonatomic) FIRFunctions *functions;
  2. Create the request. The Cloud Vision API supports two Types of text detection: TEXT_DETECTION and DOCUMENT_TEXT_DETECTION. See the Cloud Vision OCR Docs for the difference between the two use cases.


    let requestData = [
      "image": ["content": base64encodedImage],
      "features": ["type": "TEXT_DETECTION"],
      "imageContext": ["languageHints": ["en"]]


    NSDictionary *requestData = @{
      @"image": @{@"content": base64encodedImage},
      @"features": @{@"type": @"TEXT_DETECTION"},
      @"imageContext": @{@"languageHints": @[@"en"]}
  3. Finally, invoke the function:


    do {
      let result = try await functions.httpsCallable("annotateImage").call(requestData)
    } catch {
      if let error = error as NSError? {
        if error.domain == FunctionsErrorDomain {
          let code = FunctionsErrorCode(rawValue: error.code)
          let message = error.localizedDescription
          let details = error.userInfo[FunctionsErrorDetailsKey]
        // ...


    [[_functions HTTPSCallableWithName:@"annotateImage"]
                                  completion:^(FIRHTTPSCallableResult * _Nullable result, NSError * _Nullable error) {
            if (error) {
              if ([error.domain isEqualToString:@"com.firebase.functions"]) {
                FIRFunctionsErrorCode code = error.code;
                NSString *message = error.localizedDescription;
                NSObject *details = error.userInfo[@"details"];
              // ...
            // Function completed succesfully
            // Get information about labeled objects

3. Extract text from blocks of recognized text

If the text recognition operation succeeds, a JSON response of BatchAnnotateImagesResponse will be returned in the task's result. The text annotations can be found in the fullTextAnnotation object.

You can get the recognized text as a string in the text field. For example:


let annotation = result.flatMap { $ as? [String: Any] }
    .flatMap { $0["fullTextAnnotation"] }
    .flatMap { $0 as? [String: Any] }
guard let annotation = annotation else { return }

if let text = annotation["text"] as? String {
  print("Complete annotation: \(text)")


NSDictionary *annotation =[@"fullTextAnnotation"];
if (!annotation) { return; }
NSLog(@"\nComplete annotation:");
NSLog(@"\n%@", annotation[@"text"]);

You can also get information specific to regions of the image. For each block, paragraph, word, and symbol, you can get the text recognized in the region and the bounding coordinates of the region. For example:


guard let pages = annotation["pages"] as? [[String: Any]] else { return }
for page in pages {
  var pageText = ""
  guard let blocks = page["blocks"] as? [[String: Any]] else { continue }
  for block in blocks {
    var blockText = ""
    guard let paragraphs = block["paragraphs"] as? [[String: Any]] else { continue }
    for paragraph in paragraphs {
      var paragraphText = ""
      guard let words = paragraph["words"] as? [[String: Any]] else { continue }
      for word in words {
        var wordText = ""
        guard let symbols = word["symbols"] as? [[String: Any]] else { continue }
        for symbol in symbols {
          let text = symbol["text"] as? String ?? ""
          let confidence = symbol["confidence"] as? Float ?? 0.0
          wordText += text
          print("Symbol text: \(text) (confidence: \(confidence)%n")
        let confidence = word["confidence"] as? Float ?? 0.0
        print("Word text: \(wordText) (confidence: \(confidence)%n%n")
        let boundingBox = word["boundingBox"] as? [Float] ?? [0.0, 0.0, 0.0, 0.0]
        print("Word bounding box: \(boundingBox.description)%n")
        paragraphText += wordText
      print("%nParagraph: %n\(paragraphText)%n")
      let boundingBox = paragraph["boundingBox"] as? [Float] ?? [0.0, 0.0, 0.0, 0.0]
      print("Paragraph bounding box: \(boundingBox)%n")
      let confidence = paragraph["confidence"] as? Float ?? 0.0
      print("Paragraph Confidence: \(confidence)%n")
      blockText += paragraphText
    pageText += blockText


for (NSDictionary *page in annotation[@"pages"]) {
  NSMutableString *pageText = [NSMutableString new];
  for (NSDictionary *block in page[@"blocks"]) {
    NSMutableString *blockText = [NSMutableString new];
    for (NSDictionary *paragraph in block[@"paragraphs"]) {
      NSMutableString *paragraphText = [NSMutableString new];
      for (NSDictionary *word in paragraph[@"words"]) {
        NSMutableString *wordText = [NSMutableString new];
        for (NSDictionary *symbol in word[@"symbols"]) {
          NSString *text = symbol[@"text"];
          [wordText appendString:text];
          NSLog(@"Symbol text: %@ (confidence: %@\n", text, symbol[@"confidence"]);
        NSLog(@"Word text: %@ (confidence: %@\n\n", wordText, word[@"confidence"]);
        NSLog(@"Word bounding box: %@\n", word[@"boundingBox"]);
        [paragraphText appendString:wordText];
      NSLog(@"\nParagraph: \n%@\n", paragraphText);
      NSLog(@"Paragraph bounding box: %@\n", paragraph[@"boundingBox"]);
      NSLog(@"Paragraph Confidence: %@\n", paragraph[@"confidence"]);
      [blockText appendString:paragraphText];
    [pageText appendString:blockText];