# Facial Expression Recognition — Part 2: Solution Pipeline on Android

Source: [https://docs.qualcomm.com/doc/80-63442-4/topic/facial-expression-recognition-part-2.html](https://docs.qualcomm.com/doc/80-63442-4/topic/facial-expression-recognition-part-2.html)

Testing the app on the mobile device

The [previous part of this
                pipeline](https://docs.qualcomm.com/doc/80-63442-4/topic/facial-expression-recognition-part-1.html) covered using the TensorFlow low-level API and supported layers from
            the Qualcomm® Neural Processing SDK for AI to train a facial expression recognition
            model. Then it covered how to convert the model to the deep learning container (DLC)
            format using tools in the SDK. The next step is to deploy the DLC on an Android device
            using APIs in the SDK.

The sample Android application described below was developed and installed on a device
            powered by Snapdragon® Mobile Platform. It was designed to detect faces captured using
            Android [Camera2 APIs](https://developer.android.com/reference/android/hardware/camera2/package-summary), then to apply a machine learning
            model for facial expression recognition (FER).

## Project prerequisites

- 1. Mobile display
- [2. Snapdragon 835 (or above) Mobile HDK development
                        board](https://www.qualcomm.com/developer/hardware)
- 3. USB Type C cable
- 4. External camera setup
- 5. Power cable

## Hardware setup

Set up the hardware as shown in the image:  
![](data:image/png;base64,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)

## Software setup

To install the Android application on the development board, switch on the power to
                the board. Next, connect the board to your development machine with the USB Type C
                cable. Then, enable USB debugging in the Developer options on the board as
                follows:

- 1. Open the Settings app through the display.
- 2. Select “About phone” in the list.
- 3. Scroll down and tap “Build number” seven times. (It may be under “Software
                    information.”)
- 4. Press the back arrow and find “Developer options” in the list.
- 5. Open Developer options, and then scroll down to find and enable USB
                    debugging.

The board should now be connected to the development machine.

## Application workflow

The application opens a front camera preview, collects all the frames, detects faces
                present in the frames, crops down to the faces and converts them to bitmaps. The
                model, in .dlc format, becomes the input for NeuralNetworkBuilder in the Qualcomm
                Neural Processing SDK. In the inference step, the bitmaps go to the model, which
                returns a label corresponding to the expression on captured faces.

## 1. Configuring the neural network

The neural network must be built on the target device to run inference on the model.
                Following is the code to load a network from the .dlc.

    @Override
    protected NeuralNetwork doInBackground(File... params) {
       NeuralNetwork network = null;
       try {
         final SNPE.NeuralNetworkBuilder builder = new SNPE.NeuralNetworkBuilder(mApplication)
          .setDebugEnabled(false)
        // Sets the runtime order to the network
        .setRuntimeOrder(DSP, GPU, CPU)
          .setModel(new File(""))
          .setCpuFallbackEnabled(true)
          .setUseUserSuppliedBuffers(false);
        // Build the network
         network = builder.build();
        } catch (IllegalStateException | IOException e) {
         Logger.e(TAG, e.getMessage(), e);
         }
         return network;
    }Copy to clipboard

## 2. Using Android Camera2 APIs for face detection

Each [CaptureResult](https://developer.android.com/reference/android/hardware/camera2/CaptureResult) is produced by a [CameraDevice](https://developer.android.com/reference/android/hardware/camera2/CameraDevice) after processing a [CaptureRequest](https://developer.android.com/reference/android/hardware/camera2/CaptureRequest). The following code shows
                the constant [CaptureResult.STATISTICS_FACE_DETECT_MODE](https://developer.android.com/reference/android/hardware/camera2/CaptureResult.html#STATISTICS_FACE_DETECT_MODE),
                which is the operating mode for face detection and gives the list of detected
                faces.

    private CameraCaptureSession.CaptureCallback mCaptureCallback
        = new CameraCaptureSession.CaptureCallback() {
       private void process(CaptureResult result) {
        Integer mode = result.get(CaptureResult.STATISTICS_FACE_DETECT_MODE );
        Face[] faces = result.get(CaptureResult.STATISTICS_FACES);Copy to clipboard

## 3. Localization of captured faces in custom view

As shown in the following code, the position of a detected face can be obtained
                through the bounds of the [Face](https://developer.android.com/reference/android/hardware/camera2/params/Face) class. A rectangle can be drawn on
                the custom view by left, top, right and bottom parameters of bounds. The [Canvas](https://developer.android.com/reference/android/graphics/Canvas?hl=en) class can be used to draw the
                rectangle on the face.

    final Face face = faces[i];
    int left = face.getBounds().left;
    int top = face.getBounds().top;
    int right = face.getBounds().right;
    int bottom = face.getBounds().bottom;
    Rect rect = new Rect((left), (top), (right), (bottom));
    mOverlayView.setRect(rect, mPreviewSize.getWidth(), mPreviewSize.getHeight());Copy to clipboard

## 4. Cropping face bounds and scaling the bitmap

A bitmap of fixed height and width can be obtained from [TextureView](https://developer.android.com/reference/android/view/TextureView).

    Bitmap mBitmap = mTextureView.getBitmap(BITMAP_WIDTH, BITMAP_HEIGHT);
    if (rect.left > 0 && rect.left < rect.right && rect.top < rect.bottom) {
       Bitmap cropped = Bitmap.createBitmap(mBitmap, rect.left, rect.top, rect.right - rect.left, rect.bottom – rect.top);
    //creating bitmap of size 48X48
       Bitmap resizedBitmap = Bitmap.createScaledBitmap(cropped, 48, 48, false);}Copy to clipboard

## 5. Using the model for inference

The resized bitmap is converted to grayscale before handoff as input to the model.
                Basic image processing depends on the kind of input shape required by the model.

The prediction API requires conversion of the processed image into a tensor. That
                returns facial expression recognition in the Map &lt;String, FloatTensor&gt; object, as
                shown below. The size of FloatTensor, which contains the index of facial expression,
                is 1.

    final Map outputs = inferenceOnBitmap(resizedBitmap);
    for (Map.Entry output : outputs.entrySet()) {
       final FloatTensor tensor = output.getValue();
       final float[] values = new float[tensor.getSize()];
       tensor.read(values, 0, values.length);
       int expID = (int)values[0];
       text = lookupMsCoco(expID, "");
    }
    //The HashMap of facial expressions versus index
    public String lookupMsCoco(int cocoIndex, String fallback) {
       if (mCocoMap == null) {
        mCocoMap = new ArrayMap<>();
        mCocoMap.put(0, "Angry");
        mCocoMap.put(1, "Disgust");
        mCocoMap.put(2, "Fear");
        mCocoMap.put(3, "Happy");
        mCocoMap.put(4, "Sad");
        mCocoMap.put(5, "Surprise");
        mCocoMap.put(6, "Neutral");
       }
       return mCocoMap.containsKey(cocoIndex) ? mCocoMap.get(cocoIndex) : fallback;
    }Copy to clipboard

Here is a sample screenshot from the application:  
![](data:image/png;base64,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)

**Parent Topic:** [Vision-based AI Use Cases](https://docs.qualcomm.com/doc/80-63442-4/topic/vision-based-ai-use-cases.html)

Last Published: Jun 24, 2024

[Previous Topic
Facial Expression Recognition — Part 1: Solution Pipeline on Ubuntu](https://docs.qualcomm.com/bundle/publicresource/80-63442-4/topics/facial-expression-recognition-part-1.md) [Next Topic
Performance Analysis Using Benchmarking Tools](https://docs.qualcomm.com/bundle/publicresource/80-63442-4/topics/performance-analysis-using-benchmarking-tools.md)