[这不是关于如何保留透明度的常规问题。]
最有效的方式(内存和CPU)是让 libPNG 来完成,使用 png_set_background
:
If you don't need, or can't handle, the alpha channel you can call png_set_background() to remove it by compositing against a fixed color. Don't call png_set_strip_alpha() to do this - it will leave spurious pixel values in transparent parts of this image.
png_set_background(png_ptr, &background_color, PNG_BACKGROUND_GAMMA_SCREEN, 0, 1);
The background_color is an RGB or grayscale value according to the data format libpng will produce for you.
不幸的是,OpenCV对libPNG的包装器并未使用此功能,因此您需要自己补丁来支持一些基本功能(受限于无法向imread
传递其他选项的能力)。
另一个可能的方法是,只需编写自己的简单图像加载程序,以便针对特定目的使用libPNG。
如果您可以承担某些浪费,请将其加载为BGRA,并进行一些后期处理。但是,我会比Gabriel引用的代码更进一步,并在其中合并颜色转换。
void remove_transparency(cv::Mat const& source
, cv::Mat& destination
, uint8_t background_color)
{
CV_Assert(source.type() == CV_8UC4);
destination.create(source.rows, source.cols, CV_8UC1);
auto it_src(source.begin<cv::Vec4b>()), it_src_end(source.end<cv::Vec4b>());
auto it_dest(destination.begin<uint8_t>());
std::transform(it_src, it_src_end, it_dest
, [background_color](cv::Vec4b const& v) -> uchar
{
// Conversion constants taken from cvtColor docs...
float gray(v[0] * 0.114f + v[1] * 0.587f + v[2] * 0.299f);
float alpha(v[3] / 255.0f);
return cv::saturate_cast<uchar>(gray * alpha + background_color * (1 - alpha));
}
);
}
cv::parallel_for_
来进一步改进它。class ParallelRemoveTransparency
: public cv::ParallelLoopBody
{
public:
ParallelRemoveTransparency(cv::Mat const& source
, cv::Mat& destination
, uint8_t background_color)
: source_(source)
, destination_(destination)
, background_color_(background_color)
{
CV_Assert(source.size == destination.size);
}
virtual void operator()(const cv::Range& range) const
{
cv::Mat4b roi_src(source_.rowRange(range));
cv::Mat1b roi_dest(destination_.rowRange(range));
std::transform(roi_src.begin(), roi_src.end(), roi_dest.begin()
, [this](cv::Vec4b const& v) -> uint8_t {
float gray(v[0] * 0.114f + v[1] * 0.587f + v[2] * 0.299f);
float alpha(v[3] / 255.0f);
return cv::saturate_cast<uint8_t>(gray * alpha + background_color_ * (1 - alpha));
}
);
}
private:
cv::Mat const& source_;
cv::Mat& destination_;
uint8_t background_color_;
};
void remove_transparency(cv::Mat const& source
, cv::Mat& destination
, uint8_t background_color)
{
CV_Assert(source.type() == CV_8UC4);
destination.create(source.rows, source.cols, CV_8UC1);
ParallelRemoveTransparency parallel_impl(source, destination, background_color);
cv::parallel_for_(cv::Range(0, source.rows), parallel_impl);
}
import numpy as np
import cv2
def remove_transparency(source, background_color):
source_img = cv2.cvtColor(source[:,:,:3], cv2.COLOR_BGR2GRAY)
source_mask = source[:,:,3] * (1 / 255.0)
background_mask = 1.0 - source_mask
bg_part = (background_color * (1 / 255.0)) * (background_mask)
source_part = (source_img * (1 / 255.0)) * (source_mask)
return np.uint8(cv2.addWeighted(bg_part, 255.0, source_part, 255.0, 0.0))
img = cv2.imread('smile.png', -1)
result = remove_transparency(img, 255)
cv2.imshow('', result)
cv2.waitKey()
如果你使用imread
读取PNG文件时没有传递IMREAD_UNCHANGED
参数,那么你将得到一个三通道的BGR图像。如果有第四个alpha通道(0表示完全透明,255表示完全可见),那么它会被裁剪掉,正如文档所述。
你在原本是透明像素的地方得到了黑色像素,这是因为像素的BGR部分给出了黑色颜色(Vec3b(0, 0, 0)
)。
如果你还不相信,请尝试以BGR格式打开(使用imread
而不带IMREAD_UNCHANGED
参数),并显示(使用imshow
然后waitkey
)下面的两张图片:
虽然它们在此页面或Gimp中看起来相似,但第一个应该有黑色背景,而第二个应该有红色背景。
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgcodecs.hpp>
int main(int argc, char** argv ) {
cv::Mat img_4_channels;
img_4_channels = cv::imread(argv[1], cv::IMREAD_UNCHANGED); // gives 8UC4
// img_4_channels = cv::imread(argv[1]); // inappropriate: gives 8UC3
cv::Mat background = cv::Mat(img_4_channels.size(), CV_8UC3, cv::Vec3b(255, 255, 255)); // white background
overlayImage(background, img_4_channels, img_3_channels, cv::Point2i(0, 0));
cv::imshow("3 channels", img_3_channels);
}
这个解决方案更加轻量级(没有前景的坐标,也不需要分配背景图像)。
def read_transparent_png(filename, hexcode):
image_4channel = cv2.imread(filename, cv2.IMREAD_UNCHANGED)
alpha_channel = image_4channel[:, :, 3]
rgb_channels = image_4channel[:, :, :3]
white_background_image = np.zeros((image_4channel.shape[0], image_4channel.shape[1],3), dtype=np.uint8)
rgb = tuple(int(hexcode[i:i+2], 16) for i in (0, 2, 4))
RED, GREEN, BLUE = rgb[0], rgb[1], rgb[2]
white_background_image[::] = (BLUE, GREEN, RED)
alpha_factor = alpha_channel[:, :, np.newaxis].astype(np.float32) / 255.0
alpha_factor = np.concatenate(
(alpha_factor, alpha_factor, alpha_factor), axis=2)
base = rgb_channels.astype(np.float32) * alpha_factor
white = white_background_image.astype(np.float32) * (1 - alpha_factor)
final_image = base + white
return final_image.astype(np.uint8)
这里的hexcode
是您想要设置为透明PNG背景的颜色的十六进制代码。
PngDecoder
中没有支持这方面的内容。我猜需要在某个地方调用png_set_background
。 - Dan Mašek