标签归档:png

使用PIL将RGBA PNG转换为RGB

问题:使用PIL将RGBA PNG转换为RGB

我正在使用PIL将使用Django上传的透明PNG图像转换为JPG文件。输出看起来坏了。

源文件

Image.open(object.logo.path).save('/tmp/output.jpg', 'JPEG')

要么

Image.open(object.logo.path).convert('RGB').save('/tmp/output.png')

结果

两种方式的结果图像如下所示:

有没有办法解决这个问题?我想要白色背景曾经是透明背景。


多亏了出色的答案,我提出了以下函数集合:

import Image
import numpy as np


def alpha_to_color(image, color=(255, 255, 255)):
    """Set all fully transparent pixels of an RGBA image to the specified color.
    This is a very simple solution that might leave over some ugly edges, due
    to semi-transparent areas. You should use alpha_composite_with color instead.

    Source: http://stackoverflow.com/a/9166671/284318

    Keyword Arguments:
    image -- PIL RGBA Image object
    color -- Tuple r, g, b (default 255, 255, 255)

    """ 
    x = np.array(image)
    r, g, b, a = np.rollaxis(x, axis=-1)
    r[a == 0] = color[0]
    g[a == 0] = color[1]
    b[a == 0] = color[2] 
    x = np.dstack([r, g, b, a])
    return Image.fromarray(x, 'RGBA')


def alpha_composite(front, back):
    """Alpha composite two RGBA images.

    Source: http://stackoverflow.com/a/9166671/284318

    Keyword Arguments:
    front -- PIL RGBA Image object
    back -- PIL RGBA Image object

    """
    front = np.asarray(front)
    back = np.asarray(back)
    result = np.empty(front.shape, dtype='float')
    alpha = np.index_exp[:, :, 3:]
    rgb = np.index_exp[:, :, :3]
    falpha = front[alpha] / 255.0
    balpha = back[alpha] / 255.0
    result[alpha] = falpha + balpha * (1 - falpha)
    old_setting = np.seterr(invalid='ignore')
    result[rgb] = (front[rgb] * falpha + back[rgb] * balpha * (1 - falpha)) / result[alpha]
    np.seterr(**old_setting)
    result[alpha] *= 255
    np.clip(result, 0, 255)
    # astype('uint8') maps np.nan and np.inf to 0
    result = result.astype('uint8')
    result = Image.fromarray(result, 'RGBA')
    return result


def alpha_composite_with_color(image, color=(255, 255, 255)):
    """Alpha composite an RGBA image with a single color image of the
    specified color and the same size as the original image.

    Keyword Arguments:
    image -- PIL RGBA Image object
    color -- Tuple r, g, b (default 255, 255, 255)

    """
    back = Image.new('RGBA', size=image.size, color=color + (255,))
    return alpha_composite(image, back)


def pure_pil_alpha_to_color_v1(image, color=(255, 255, 255)):
    """Alpha composite an RGBA Image with a specified color.

    NOTE: This version is much slower than the
    alpha_composite_with_color solution. Use it only if
    numpy is not available.

    Source: http://stackoverflow.com/a/9168169/284318

    Keyword Arguments:
    image -- PIL RGBA Image object
    color -- Tuple r, g, b (default 255, 255, 255)

    """ 
    def blend_value(back, front, a):
        return (front * a + back * (255 - a)) / 255

    def blend_rgba(back, front):
        result = [blend_value(back[i], front[i], front[3]) for i in (0, 1, 2)]
        return tuple(result + [255])

    im = image.copy()  # don't edit the reference directly
    p = im.load()  # load pixel array
    for y in range(im.size[1]):
        for x in range(im.size[0]):
            p[x, y] = blend_rgba(color + (255,), p[x, y])

    return im

def pure_pil_alpha_to_color_v2(image, color=(255, 255, 255)):
    """Alpha composite an RGBA Image with a specified color.

    Simpler, faster version than the solutions above.

    Source: http://stackoverflow.com/a/9459208/284318

    Keyword Arguments:
    image -- PIL RGBA Image object
    color -- Tuple r, g, b (default 255, 255, 255)

    """
    image.load()  # needed for split()
    background = Image.new('RGB', image.size, color)
    background.paste(image, mask=image.split()[3])  # 3 is the alpha channel
    return background

性能

简单的非合成alpha_to_color功能是最快的解决方案,但由于它不能处理半透明区域,因此留下了丑陋的边界。

纯粹的PIL和numpy合成解决方案都可以提供出色的结果,但alpha_composite_with_color其速度(8.93毫秒)比pure_pil_alpha_to_color(79.6毫秒)要快得多。如果您的系统上有numpy可用,那就是这种方式。 (更新:新的纯PIL版本是所有提到的解决方案中最快的。)

$ python -m timeit "import Image; from apps.front import utils; i = Image.open(u'logo.png'); i2 = utils.alpha_to_color(i)"
10 loops, best of 3: 4.67 msec per loop
$ python -m timeit "import Image; from apps.front import utils; i = Image.open(u'logo.png'); i2 = utils.alpha_composite_with_color(i)"
10 loops, best of 3: 8.93 msec per loop
$ python -m timeit "import Image; from apps.front import utils; i = Image.open(u'logo.png'); i2 = utils.pure_pil_alpha_to_color(i)"
10 loops, best of 3: 79.6 msec per loop
$ python -m timeit "import Image; from apps.front import utils; i = Image.open(u'logo.png'); i2 = utils.pure_pil_alpha_to_color_v2(i)"
10 loops, best of 3: 1.1 msec per loop

I’m using PIL to convert a transparent PNG image uploaded with Django to a JPG file. The output looks broken.

Source file

Code

Image.open(object.logo.path).save('/tmp/output.jpg', 'JPEG')

or

Image.open(object.logo.path).convert('RGB').save('/tmp/output.png')

Result

Both ways, the resulting image looks like this:

Is there a way to fix this? I’d like to have white background where the transparent background used to be.


Solution

Thanks to the great answers, I’ve come up with the following function collection:

import Image
import numpy as np


def alpha_to_color(image, color=(255, 255, 255)):
    """Set all fully transparent pixels of an RGBA image to the specified color.
    This is a very simple solution that might leave over some ugly edges, due
    to semi-transparent areas. You should use alpha_composite_with color instead.

    Source: http://stackoverflow.com/a/9166671/284318

    Keyword Arguments:
    image -- PIL RGBA Image object
    color -- Tuple r, g, b (default 255, 255, 255)

    """ 
    x = np.array(image)
    r, g, b, a = np.rollaxis(x, axis=-1)
    r[a == 0] = color[0]
    g[a == 0] = color[1]
    b[a == 0] = color[2] 
    x = np.dstack([r, g, b, a])
    return Image.fromarray(x, 'RGBA')


def alpha_composite(front, back):
    """Alpha composite two RGBA images.

    Source: http://stackoverflow.com/a/9166671/284318

    Keyword Arguments:
    front -- PIL RGBA Image object
    back -- PIL RGBA Image object

    """
    front = np.asarray(front)
    back = np.asarray(back)
    result = np.empty(front.shape, dtype='float')
    alpha = np.index_exp[:, :, 3:]
    rgb = np.index_exp[:, :, :3]
    falpha = front[alpha] / 255.0
    balpha = back[alpha] / 255.0
    result[alpha] = falpha + balpha * (1 - falpha)
    old_setting = np.seterr(invalid='ignore')
    result[rgb] = (front[rgb] * falpha + back[rgb] * balpha * (1 - falpha)) / result[alpha]
    np.seterr(**old_setting)
    result[alpha] *= 255
    np.clip(result, 0, 255)
    # astype('uint8') maps np.nan and np.inf to 0
    result = result.astype('uint8')
    result = Image.fromarray(result, 'RGBA')
    return result


def alpha_composite_with_color(image, color=(255, 255, 255)):
    """Alpha composite an RGBA image with a single color image of the
    specified color and the same size as the original image.

    Keyword Arguments:
    image -- PIL RGBA Image object
    color -- Tuple r, g, b (default 255, 255, 255)

    """
    back = Image.new('RGBA', size=image.size, color=color + (255,))
    return alpha_composite(image, back)


def pure_pil_alpha_to_color_v1(image, color=(255, 255, 255)):
    """Alpha composite an RGBA Image with a specified color.

    NOTE: This version is much slower than the
    alpha_composite_with_color solution. Use it only if
    numpy is not available.

    Source: http://stackoverflow.com/a/9168169/284318

    Keyword Arguments:
    image -- PIL RGBA Image object
    color -- Tuple r, g, b (default 255, 255, 255)

    """ 
    def blend_value(back, front, a):
        return (front * a + back * (255 - a)) / 255

    def blend_rgba(back, front):
        result = [blend_value(back[i], front[i], front[3]) for i in (0, 1, 2)]
        return tuple(result + [255])

    im = image.copy()  # don't edit the reference directly
    p = im.load()  # load pixel array
    for y in range(im.size[1]):
        for x in range(im.size[0]):
            p[x, y] = blend_rgba(color + (255,), p[x, y])

    return im

def pure_pil_alpha_to_color_v2(image, color=(255, 255, 255)):
    """Alpha composite an RGBA Image with a specified color.

    Simpler, faster version than the solutions above.

    Source: http://stackoverflow.com/a/9459208/284318

    Keyword Arguments:
    image -- PIL RGBA Image object
    color -- Tuple r, g, b (default 255, 255, 255)

    """
    image.load()  # needed for split()
    background = Image.new('RGB', image.size, color)
    background.paste(image, mask=image.split()[3])  # 3 is the alpha channel
    return background

Performance

The simple non-compositing alpha_to_color function is the fastest solution, but leaves behind ugly borders because it does not handle semi transparent areas.

Both the pure PIL and the numpy compositing solutions give great results, but alpha_composite_with_color is much faster (8.93 msec) than pure_pil_alpha_to_color (79.6 msec). If numpy is available on your system, that’s the way to go. (Update: The new pure PIL version is the fastest of all mentioned solutions.)

$ python -m timeit "import Image; from apps.front import utils; i = Image.open(u'logo.png'); i2 = utils.alpha_to_color(i)"
10 loops, best of 3: 4.67 msec per loop
$ python -m timeit "import Image; from apps.front import utils; i = Image.open(u'logo.png'); i2 = utils.alpha_composite_with_color(i)"
10 loops, best of 3: 8.93 msec per loop
$ python -m timeit "import Image; from apps.front import utils; i = Image.open(u'logo.png'); i2 = utils.pure_pil_alpha_to_color(i)"
10 loops, best of 3: 79.6 msec per loop
$ python -m timeit "import Image; from apps.front import utils; i = Image.open(u'logo.png'); i2 = utils.pure_pil_alpha_to_color_v2(i)"
10 loops, best of 3: 1.1 msec per loop

回答 0

这是一个简单得多的版本-不确定性能如何。很大程度上基于我在构建RGBA -> JPG + BG对单缩略图的支持时发现的一些django代码段。

from PIL import Image

png = Image.open(object.logo.path)
png.load() # required for png.split()

background = Image.new("RGB", png.size, (255, 255, 255))
background.paste(png, mask=png.split()[3]) # 3 is the alpha channel

background.save('foo.jpg', 'JPEG', quality=80)

结果@ 80%

结果@ 50%

Here’s a version that’s much simpler – not sure how performant it is. Heavily based on some django snippet I found while building RGBA -> JPG + BG support for sorl thumbnails.

from PIL import Image

png = Image.open(object.logo.path)
png.load() # required for png.split()

background = Image.new("RGB", png.size, (255, 255, 255))
background.paste(png, mask=png.split()[3]) # 3 is the alpha channel

background.save('foo.jpg', 'JPEG', quality=80)

Result @80%

Result @ 50%


回答 1

通过使用Image.alpha_composite,Yuji’Tomita’Tomita的解决方案变得更简单。tuple index out of range如果png没有alpha通道,则此代码可以避免错误。

from PIL import Image

png = Image.open(img_path).convert('RGBA')
background = Image.new('RGBA', png.size, (255,255,255))

alpha_composite = Image.alpha_composite(background, png)
alpha_composite.save('foo.jpg', 'JPEG', quality=80)

By using Image.alpha_composite, the solution by Yuji ‘Tomita’ Tomita become simpler. This code can avoid a tuple index out of range error if png has no alpha channel.

from PIL import Image

png = Image.open(img_path).convert('RGBA')
background = Image.new('RGBA', png.size, (255,255,255))

alpha_composite = Image.alpha_composite(background, png)
alpha_composite.save('foo.jpg', 'JPEG', quality=80)

回答 2

透明部分大部分具有RGBA值(0,0,0,0)。由于JPG没有透明度,因此jpeg值设置为(0,0,0),为黑色。

在圆形图标周围,存在具有非零RGB值的像素,其中A =0。因此,它们在PNG中看起来是透明的,但在JPG中是有趣的。

您可以使用numpy将A == 0的所有像素设置为R = G = B = 255,如下所示:

import Image
import numpy as np

FNAME = 'logo.png'
img = Image.open(FNAME).convert('RGBA')
x = np.array(img)
r, g, b, a = np.rollaxis(x, axis = -1)
r[a == 0] = 255
g[a == 0] = 255
b[a == 0] = 255
x = np.dstack([r, g, b, a])
img = Image.fromarray(x, 'RGBA')
img.save('/tmp/out.jpg')


请注意,徽标还具有一些半透明像素,用于平滑单词和图标周围的边缘。保存为jpeg会忽略半透明性,从而使生成的jpeg看起来参差不齐。

使用imagemagick的convert命令可以得到更好的质量结果:

convert logo.png -background white -flatten /tmp/out.jpg


为了使用numpy进行质量更好的混合,您可以使用alpha合成

import Image
import numpy as np

def alpha_composite(src, dst):
    '''
    Return the alpha composite of src and dst.

    Parameters:
    src -- PIL RGBA Image object
    dst -- PIL RGBA Image object

    The algorithm comes from http://en.wikipedia.org/wiki/Alpha_compositing
    '''
    # http://stackoverflow.com/a/3375291/190597
    # http://stackoverflow.com/a/9166671/190597
    src = np.asarray(src)
    dst = np.asarray(dst)
    out = np.empty(src.shape, dtype = 'float')
    alpha = np.index_exp[:, :, 3:]
    rgb = np.index_exp[:, :, :3]
    src_a = src[alpha]/255.0
    dst_a = dst[alpha]/255.0
    out[alpha] = src_a+dst_a*(1-src_a)
    old_setting = np.seterr(invalid = 'ignore')
    out[rgb] = (src[rgb]*src_a + dst[rgb]*dst_a*(1-src_a))/out[alpha]
    np.seterr(**old_setting)    
    out[alpha] *= 255
    np.clip(out,0,255)
    # astype('uint8') maps np.nan (and np.inf) to 0
    out = out.astype('uint8')
    out = Image.fromarray(out, 'RGBA')
    return out            

FNAME = 'logo.png'
img = Image.open(FNAME).convert('RGBA')
white = Image.new('RGBA', size = img.size, color = (255, 255, 255, 255))
img = alpha_composite(img, white)
img.save('/tmp/out.jpg')

The transparent parts mostly have RGBA value (0,0,0,0). Since the JPG has no transparency, the jpeg value is set to (0,0,0), which is black.

Around the circular icon, there are pixels with nonzero RGB values where A = 0. So they look transparent in the PNG, but funny-colored in the JPG.

You can set all pixels where A == 0 to have R = G = B = 255 using numpy like this:

import Image
import numpy as np

FNAME = 'logo.png'
img = Image.open(FNAME).convert('RGBA')
x = np.array(img)
r, g, b, a = np.rollaxis(x, axis = -1)
r[a == 0] = 255
g[a == 0] = 255
b[a == 0] = 255
x = np.dstack([r, g, b, a])
img = Image.fromarray(x, 'RGBA')
img.save('/tmp/out.jpg')


Note that the logo also has some semi-transparent pixels used to smooth the edges around the words and icon. Saving to jpeg ignores the semi-transparency, making the resultant jpeg look quite jagged.

A better quality result could be made using imagemagick’s convert command:

convert logo.png -background white -flatten /tmp/out.jpg


To make a nicer quality blend using numpy, you could use alpha compositing:

import Image
import numpy as np

def alpha_composite(src, dst):
    '''
    Return the alpha composite of src and dst.

    Parameters:
    src -- PIL RGBA Image object
    dst -- PIL RGBA Image object

    The algorithm comes from http://en.wikipedia.org/wiki/Alpha_compositing
    '''
    # http://stackoverflow.com/a/3375291/190597
    # http://stackoverflow.com/a/9166671/190597
    src = np.asarray(src)
    dst = np.asarray(dst)
    out = np.empty(src.shape, dtype = 'float')
    alpha = np.index_exp[:, :, 3:]
    rgb = np.index_exp[:, :, :3]
    src_a = src[alpha]/255.0
    dst_a = dst[alpha]/255.0
    out[alpha] = src_a+dst_a*(1-src_a)
    old_setting = np.seterr(invalid = 'ignore')
    out[rgb] = (src[rgb]*src_a + dst[rgb]*dst_a*(1-src_a))/out[alpha]
    np.seterr(**old_setting)    
    out[alpha] *= 255
    np.clip(out,0,255)
    # astype('uint8') maps np.nan (and np.inf) to 0
    out = out.astype('uint8')
    out = Image.fromarray(out, 'RGBA')
    return out            

FNAME = 'logo.png'
img = Image.open(FNAME).convert('RGBA')
white = Image.new('RGBA', size = img.size, color = (255, 255, 255, 255))
img = alpha_composite(img, white)
img.save('/tmp/out.jpg')


回答 3

这是纯PIL解决方案。

def blend_value(under, over, a):
    return (over*a + under*(255-a)) / 255

def blend_rgba(under, over):
    return tuple([blend_value(under[i], over[i], over[3]) for i in (0,1,2)] + [255])

white = (255, 255, 255, 255)

im = Image.open(object.logo.path)
p = im.load()
for y in range(im.size[1]):
    for x in range(im.size[0]):
        p[x,y] = blend_rgba(white, p[x,y])
im.save('/tmp/output.png')

Here’s a solution in pure PIL.

def blend_value(under, over, a):
    return (over*a + under*(255-a)) / 255

def blend_rgba(under, over):
    return tuple([blend_value(under[i], over[i], over[3]) for i in (0,1,2)] + [255])

white = (255, 255, 255, 255)

im = Image.open(object.logo.path)
p = im.load()
for y in range(im.size[1]):
    for x in range(im.size[0]):
        p[x,y] = blend_rgba(white, p[x,y])
im.save('/tmp/output.png')

回答 4

没坏 它完全按照您的指示进行。这些像素是黑色的,具有完全的透明度。您将需要遍历所有像素,并将完全透明的像素转换为白色。

It’s not broken. It’s doing exactly what you told it to; those pixels are black with full transparency. You will need to iterate across all pixels and convert ones with full transparency to white.


回答 5

import numpy as np
import PIL

def convert_image(image_file):
    image = Image.open(image_file) # this could be a 4D array PNG (RGBA)
    original_width, original_height = image.size

    np_image = np.array(image)
    new_image = np.zeros((np_image.shape[0], np_image.shape[1], 3)) 
    # create 3D array

    for each_channel in range(3):
        new_image[:,:,each_channel] = np_image[:,:,each_channel]  
        # only copy first 3 channels.

    # flushing
    np_image = []
    return new_image
import numpy as np
import PIL

def convert_image(image_file):
    image = Image.open(image_file) # this could be a 4D array PNG (RGBA)
    original_width, original_height = image.size

    np_image = np.array(image)
    new_image = np.zeros((np_image.shape[0], np_image.shape[1], 3)) 
    # create 3D array

    for each_channel in range(3):
        new_image[:,:,each_channel] = np_image[:,:,each_channel]  
        # only copy first 3 channels.

    # flushing
    np_image = []
    return new_image

回答 6

导入图片

def fig2img(fig):“”“ @brief将Matplotlib图形转换为RGBA格式的PIL图像并返回@param图matplotlib图形@返回Python图像库(PIL)图像”“”#将图形像素图放入一个numpy数组buf = fig2data(fig)w,h,d = buf.shape return Image.frombytes(“ RGBA”,(w,h),buf.tostring())

def fig2data(fig):“”“ @brief将Matplotlib图形转换为具有RGBA通道的4D numpy数组,然后将其返回@p​​aram图matplotlib图形@返回RGBA值的numpy 3D数组”“”#绘制渲染器图。 canvas.draw()

# Get the RGBA buffer from the figure
w,h = fig.canvas.get_width_height()
buf = np.fromstring ( fig.canvas.tostring_argb(), dtype=np.uint8 )
buf.shape = ( w, h, 4 )

# canvas.tostring_argb give pixmap in ARGB mode. Roll the ALPHA channel to have it in RGBA mode
buf = np.roll ( buf, 3, axis = 2 )
return buf

def rgba2rgb(img,c =(0,0,0),path =’foo.jpg’,is_already_saved = False,if_load = True):如果不是is_already_saved:background = Image.new(“ RGB”,img.size, c)background.paste(img,mask = img.split()[3])#3是Alpha通道

    background.save(path, 'JPEG', quality=100)   
    is_already_saved = True
if if_load:
    if is_already_saved:
        im = Image.open(path)
        return np.array(im)
    else:
        raise ValueError('No image to load.')

import Image

def fig2img ( fig ): “”” @brief Convert a Matplotlib figure to a PIL Image in RGBA format and return it @param fig a matplotlib figure @return a Python Imaging Library ( PIL ) image “”” # put the figure pixmap into a numpy array buf = fig2data ( fig ) w, h, d = buf.shape return Image.frombytes( “RGBA”, ( w ,h ), buf.tostring( ) )

def fig2data ( fig ): “”” @brief Convert a Matplotlib figure to a 4D numpy array with RGBA channels and return it @param fig a matplotlib figure @return a numpy 3D array of RGBA values “”” # draw the renderer fig.canvas.draw ( )

# Get the RGBA buffer from the figure
w,h = fig.canvas.get_width_height()
buf = np.fromstring ( fig.canvas.tostring_argb(), dtype=np.uint8 )
buf.shape = ( w, h, 4 )

# canvas.tostring_argb give pixmap in ARGB mode. Roll the ALPHA channel to have it in RGBA mode
buf = np.roll ( buf, 3, axis = 2 )
return buf

def rgba2rgb(img, c=(0, 0, 0), path=’foo.jpg’, is_already_saved=False, if_load=True): if not is_already_saved: background = Image.new(“RGB”, img.size, c) background.paste(img, mask=img.split()[3]) # 3 is the alpha channel

    background.save(path, 'JPEG', quality=100)   
    is_already_saved = True
if if_load:
    if is_already_saved:
        im = Image.open(path)
        return np.array(im)
    else:
        raise ValueError('No image to load.')