Android & Firebase ML Kit in Java / Kotlin

Create your first Android app in Android Studio by building an interface with an image view and two buttons for gallery and camera, then display the selected or captured image.

Add an if block to verify the gallery image selection using the result code before displaying it in image view; the next lecture covers capturing an image with the camera.

Learn to request camera and external storage permissions, declare them in the manifest, and implement an open camera flow using an activity result launcher to capture and display the image.

Convert gallery or camera images to bitmap in Android, apply rotation correction, and prepare the bitmap for machine learning models such as facial recognition.

Learn to build an Android image picker in Java by selecting from gallery or capturing with camera, using intents and activity result launchers to display bitmap in an image view.

Create an Android Studio project in Kotlin to build a GUI with two buttons for picking or capturing images via gallery or camera, then display the image.

Learn to implement image selection from the gallery in Android apps using the activity result launcher, an image pick intent, and displaying the chosen image in an image view.

Learn how to capture images in Android by adding camera and external storage permissions, declaring them in the manifest, and requesting them at runtime for devices running M or newer.

Learn how to capture images in Android by handling permissions, launching the camera with an open camera method, using an image capture intent, and displaying the result in image view.

Convert images from gallery or camera to bitmap format in Android using URI to bitmap and rotate bitmap to portrait, preparing inputs for machine learning models.

Learn to build an Android image picker app: create a project, design a UI with image view and two buttons, handle gallery and camera intents, and display selected images.

Clone the starter Android project from GitHub, run it in an emulator, and build an image labeling app that lets users pick or capture a photo, then display labeling results.

Explore the Android user interface with ConstraintLayout and CardView that display the selected image and labeling results, plus gallery and camera flows.

Learn how to integrate ML Kit image labeling in Android apps, using the base model or a custom TensorFlow Lite model, and compare bundled versus unbundled deployment approaches.

Add google maven repositories to the Gradle files, add the bundled image labeling dependency, sync Gradle, and convert bitmaps to InputImage format for labeling.

Initialize the image labeler with get client and options, then process the input image, handle success and failure, display label names with confidence in a text view, clearing prior results.

Test the image labeling app by selecting gallery images, observe predictions with confidence scores, and confirm dog and beach labels reflect the pictured content.

Format the output by showing the confidence with two decimal places and set a 0.7 confidence threshold for the image labeler to filter predictions, then test with images.

Learn to build an Android image labeling app with Firebase ML Kit, from capturing or selecting an image to labeling it and displaying the results.

Build an image labeling app with the ML Kit image labeling model by selecting images from the gallery or capturing them with the camera, then display the labeling results.

Explore how the app requests camera and external storage permissions, displays images in a responsive ui, and uses an activity result launcher to pick or capture photos for image labeling.

Explore how to implement image labeling with ML Kit in an android app, using the base classifier or custom models, and compare bundled versus unbundled deployment.

Learn to add the Android Firebase ML Kit library, configure bundled dependencies in app-level gradle, and convert bitmaps to input images for image labeling with the ML Kit model.

Initialize an image labeler and pass the selected image to the labeling model to obtain results, then display each label name with its confidence score.

Test image labeling in the Android and Firebase ML Kit app by selecting images from the gallery, observing predictions such as dog, pet, beach, and sky with high confidence.

Format the confidence value to two decimal places and apply a confidence threshold to show only high‑confidence predictions using image labeler options.

Learn to implement image labeling in an android app by choosing or capturing images. Initialize the image labeler, convert images to input format, obtain labels, and display results on screen.

Create a new Android Studio project, connect it to Firebase using the Firebase Assistant, add ML Kit dependencies to your app, and verify the build succeeds.

Create an Android GUI where users pick an image, view it, and see text detected by a locally downloaded ML Kit model, with manifest lines enabling automatic download on install.

Learn to create and use the Firebase ML Kit text recognizer in Java to extract text from images chosen from the gallery, process the image, and display results.

Learn to build an Android app using Firebase ML Kit for text recognition in Java, extracting text blocks, lines, and words, managing dependencies, and displaying bounding boxes.

Create a Kotlin text recognition app with Firebase ML Kit to detect and display text from images or documents, integrating the Firebase console and image picker.

Resolve the google-services.json missing error by connecting your Android Studio project to the correct Firebase console account, downloading google-services.json from project settings, and placing it in the app folder.

Explore how Kotlin developers follow Java lectures, convert Firebase ML Kit code to Kotlin, and work with text recognition and landmark detection.

Create an Android app that uses Firebase ML Kit language identification to detect the language of user input, wiring Firebase, dependencies, and a simple UI with success and failure callbacks.

Combine Firebase translation API with the file-based language ID API to auto-detect source text and translate it into a chosen target language in an Android app.

Create an android text translation app by setting up a firebase ml kit project, adding dependencies, and building a landscape layout with input, output, and a translate button.

Translate English to German using Firebase ML Kit in an Android app by creating an English-German translator, downloading the model on Wi-Fi, and translating text on a button click.

Test an Android translation app using Firebase ML Kit, run the app, enter text, and evaluate translation accuracy. Manage and download language models, switch languages, and delete downloaded models.

Develop an android barcode scanner using Firebase ML Kit by selecting an image to decode barcodes or qr codes and display the extracted data.

Learn to run a barcode scanning Android application that reads an e-mail address, subject, and body, and generates a QR code using ML Kit.

Set up an Android face detection app by connecting to Firebase, adding ML Kit dependencies, and configuring the manifest; implement a UI with image view and image selection.

Learn to detect faces in an image and draw yellow stroked rectangles around them by converting a bitmap to mutable, creating a canvas, and rendering on an image view.

Detect landmarks with Android Firebase ML Kit to obtain positions such as the left ear, eyes, and mouth, then draw rectangles on a canvas to visualize them.

Use the android firebase ml kit face detector to obtain each face's smiling probability, apply a 0.5 threshold, and draw a 'smiling' label with a bounding rectangle.

Set up a Kotlin Android project and use Firebase ML Kit to detect faces and landmarks in a gallery image, then draw rectangles around detected faces.

Learn to build an on-device face detector in Android with Kotlin and Firebase ML Kit, configure Firebase, add dependencies, set detector options, and draw bounding boxes around faces.

Learn to detect faces with Firebase ML Kit in Kotlin and draw rectangles on a mutable bitmap using a canvas and paint, including selecting an image and displaying results.

Explore landmark detection with Android Firebase ML Kit, drawing precise rectangles around facial landmarks like the left ear using canvas and paint, and updating the bitmap for real-time visualization.

Explore how to detect smiles with Android Firebase ML Kit, compute smiling probability, apply a 60 percent threshold, and draw rectangles and text like 'smiling' or 'serious' on faces.