我正在 OpenCV android 2.4.11 的示例下工作，它使用相机检测面部。 我没有在找到的脸上画一个矩形，而是尝试在脸上放置一个遮罩（png 图像）。 但为了在脸上显示图像，png 图像带有黑色背景，其中有透明度。
FdActivity.java
public void onCameraViewStarted(int width, int height) {
mGray = new Mat();
mRgba = new Mat();
//Load my mask png
Bitmap image = BitmapFactory.decodeResource(getResources(), R.drawable.mask_1);
mask = new Mat();
Utils.bitmapToMat(image, mask);
}
public Mat onCameraFrame(CvCameraViewFrame inputFrame) {
mRgba = inputFrame.rgba();
mGray = inputFrame.gray();
if (mAbsoluteFaceSize == 0) {
int height = mGray.rows();
if (Math.round(height * mRelativeFaceSize) > 0) {
mAbsoluteFaceSize = Math.round(height * mRelativeFaceSize);
}
mNativeDetector.setMinFaceSize(mAbsoluteFaceSize);
}
MatOfRect faces = new MatOfRect();
if (mDetectorType == JAVA_DETECTOR) {
if (mJavaDetector != null)
mJavaDetector.detectMultiScale(mGray, faces, 1.1, 2, 2,
new Size(mAbsoluteFaceSize, mAbsoluteFaceSize), new Size());
}
else if (mDetectorType == NATIVE_DETECTOR) {
if (mNativeDetector != null)
mNativeDetector.detect(mGray, faces);
}
else {
Log.e(TAG, "Detection method is not selected!");
}
Rect[] facesArray = faces.toArray();
for (int i = 0; i < facesArray.length; i++) {
overlayImage(mRgba, mask, facesArray[i]);
}
return mRgba;
}
public Mat overlayImage(Mat background, Mat foregroundMask, Rect faceRect)
{
Mat mask = new Mat();
Imgproc.resize(this.mask, mask, faceRect.size());
Mat source = new Mat();
Imgproc.resize(foregroundMask, source, background.size());
mask.copyTo( background.submat( new Rect((int) faceRect.tl().x, (int) faceRect.tl().y, mask.cols(), mask.rows())) );
source.release();
mask.release();
return background;
}
注意：由于我没有设置Android开发环境，因此我将解释一般原理并给你一个Python实现的示例。将其移植到 Java 应该相当简单。请随意将您的代码作为单独的答案发布。
你需要做一些类似于addWeighted操作确实如此，那就是操作
然而，在你的情况下， α 需要是一个矩阵（即我们需要每个像素不同的混合系数）。
让我们使用一些示例图像来说明这一点。我们可以使用 Lena 图像作为样本人脸：
该图像作为透明叠加：
该图像作为不透明的叠加层：
为了获得alpha矩阵，我们可以使用阈值确定前景（覆盖）和背景（脸部）蒙版，或者使用输入图像中的 Alpha 通道（如果可用）。
在值范围为 0.0 .. 1.0 的浮点图像上执行此操作非常有用。然后我们可以将两个掩码之间的关系表示为
foreground_mask = 1.0 - background_mask
即两个掩码相加得到的结果都是掩码。
对于 RGBA 格式的叠加图像，我们得到以下前景和背景蒙版：
当我们在 RGB 格式的情况下使用阈值、侵蚀和模糊时，我们得到以下前景和背景蒙版：
现在我们可以计算两个加权部分：
foreground_part = overlay_image * foreground_mask
background_part = face_image * background_mask
对于 RGBA 叠加，前景和背景部分如下所示：
对于 RGB 叠加，前景和背景部分如下所示：
最后将它们相加，并将图像转换回 0-255 范围内的 8 位整数。
操作结果如下（分别为 RGBA 和 RGB 叠加）：
import numpy as np
import cv2
# ==============================================================================
def blend_non_transparent(face_img, overlay_img):
# Let's find a mask covering all the non-black (foreground) pixels
# NB: We need to do this on grayscale version of the image
gray_overlay = cv2.cvtColor(overlay_img, cv2.COLOR_BGR2GRAY)
overlay_mask = cv2.threshold(gray_overlay, 1, 255, cv2.THRESH_BINARY)[1]
# Let's shrink and blur it a little to make the transitions smoother...
overlay_mask = cv2.erode(overlay_mask, cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3)))
overlay_mask = cv2.blur(overlay_mask, (3, 3))
# And the inverse mask, that covers all the black (background) pixels
background_mask = 255 - overlay_mask
# Turn the masks into three channel, so we can use them as weights
overlay_mask = cv2.cvtColor(overlay_mask, cv2.COLOR_GRAY2BGR)
background_mask = cv2.cvtColor(background_mask, cv2.COLOR_GRAY2BGR)
# Create a masked out face image, and masked out overlay
# We convert the images to floating point in range 0.0 - 1.0
face_part = (face_img * (1 / 255.0)) * (background_mask * (1 / 255.0))
overlay_part = (overlay_img * (1 / 255.0)) * (overlay_mask * (1 / 255.0))
# And finally just add them together, and rescale it back to an 8bit integer image
return np.uint8(cv2.addWeighted(face_part, 255.0, overlay_part, 255.0, 0.0))
# ==============================================================================
# We load the images
face_img = cv2.imread("lena.png", -1)
overlay_img = cv2.imread("overlay.png", -1)
result_1 = blend_non_transparent(face_img, overlay_img)
cv2.imwrite("merged.png", result_1)
import numpy as np
import cv2
# ==============================================================================
def blend_transparent(face_img, overlay_t_img):
# Split out the transparency mask from the colour info
overlay_img = overlay_t_img[:,:,:3] # Grab the BRG planes
overlay_mask = overlay_t_img[:,:,3:] # And the alpha plane
# Again calculate the inverse mask
background_mask = 255 - overlay_mask
# Turn the masks into three channel, so we can use them as weights
overlay_mask = cv2.cvtColor(overlay_mask, cv2.COLOR_GRAY2BGR)
background_mask = cv2.cvtColor(background_mask, cv2.COLOR_GRAY2BGR)
# Create a masked out face image, and masked out overlay
# We convert the images to floating point in range 0.0 - 1.0
face_part = (face_img * (1 / 255.0)) * (background_mask * (1 / 255.0))
overlay_part = (overlay_img * (1 / 255.0)) * (overlay_mask * (1 / 255.0))
# And finally just add them together, and rescale it back to an 8bit integer image
return np.uint8(cv2.addWeighted(face_part, 255.0, overlay_part, 255.0, 0.0))
# ==============================================================================
# We load the images
face_img = cv2.imread("lena.png", -1)
overlay_t_img = cv2.imread("overlay_transparent.png", -1) # Load with transparency
result_2 = blend_transparent(face_img, overlay_t_img)
cv2.imwrite("merged_transparent.png", result_2)