【Python 项目】照片马赛克 - 3

完整代码

import sys, os, random, argparse
from PIL import Image
import imghdr
import numpy as np

def getAverageRGB(image):
	"""
	return the average color value as (r, g, b) for each input image
	"""
	# 用 numpy 将每个 Image 对象转换为数据数组。返回的 numpy 数组形为(w, h, d)
	im = np.array(image)
	# 保存 shape 元组，然后计算平均 RGB值，将这个数组变形为更方便的形状(w*h, d)
	w,h,d = im.shape
	# 用 numpy.average()计算出使用平均值
	return tuple(np.average(im.reshape(w*h, d), axis=0))

def splitImage(image, size):
	"""
	given the image and dimensions (rows, cols), return an m*n list of images
	"""
	W, H = image.size[0], image.size[1] # 得到目标图像的维度
	m, n = size # 得到尺寸
	w, h = int(W/n), int(H/m) # 用基本除法计算目标图像中每一小块的尺寸
	# image list
	imgs = []
	# generate a list of dimensions
	for j in range(m):
		for i in range(n):
			# append cropped image
			imgs.append(image.crop((i*w, j*h, (i+1)*w, (j+1)*h)))
	return imgs


def getImages(imageDir):
	"""
	用 os.listdir()将 imageDir 目录中的文件放入一个列表
	"""
	files = os.listdir(imageDir)
	images = []
	for file in files:
		# os.path.abspath()和 os.path.join()来获取图像的完整文件名
		filePath = os.path.abspath(os.path.join(imageDir, file))
		try:
			# 用 open()打开图像文件。在随后的几行中，将文件句柄传入 Image.open()，将得到的图像 im 存入一个数组
			fp = open(filePath, "rb")
			im = Image.open(fp)
			images.append(im)
			# 调用 Image.load()，强制加载 im 中的图像数据
			im.load()
			# 关闭文件句柄，释放系统资源
			fp.close()
		except:
			# skip
			print("Invalid image: %s" % (filePath,))
	return images


def getImageFilenames(imageDir):
	files = os.listdir(imageDir)
	filenames = []
	for file in files:
		filePath = os.path.abspath(os.path.join(imageDir, file))
		try:
			imgType = imghdr.what(filePath)
			if imgType:
				filenames.append(filePath)
		except:
			print("Invalid image: %s" % (filePath,))
	return filenames


def getBestMatchIndex(input_avg, avgs):
	"""
	return index of the best image match based on average RGB value distance
	"""

	# input image average
	avg = input_avg

	# get the closest RGB value to input, based on RGB distance
	index = 0 
	# 将最接近的匹配下标初始化为 0，最小距离初始化为无穷大
	min_index = 0 
	min_dist = float("inf")
	for val in avgs: # 遍历平均值列表中的值
		# 用标准公式计算距离
		dist = ((val[0] - avg[0])*(val[0] - avg[0]) + 
				(val[1] - avg[1])*(val[1] - avg[1]) + 
				(val[2] - avg[2])*(val[2] - avg[2]))
		if dist < min_dist: #如果计算的距离小于保存的最小距离 min_dist，它就被替换为新的最小距离
			min_dist = dist
			min_index = index
		index += 1 

	return min_index



def createImageGrid(images, dims):
	"""
	given a list of images and a grid size (m, n), create a grid of images
	"""
	m, n = dims # 取得网格的尺寸，然后用 assert 检查，提供给 createImageGrid()的图像数量是否符合网格的大小
	
	# sanity check
	assert m*n == len(images)
	
	# 计算小块图像的最大宽度和高度
	# don't assume they're all equal
	width = max([img.size[0] for img in images])
	height = max([img.size[1] for img in images])

	# 创建一个空的 Image，大小符合网格中的所有图像
	grid_img = Image.new('RGB', (n*width, m*height))
	
	# paste the tile images into the image grid
	for index in range(len(images)):
		row = int(index/n)
		col = index - n*row
		grid_img.paste(images[index], (col*width, row*height)) # 循环遍历选定的图像，利用 Image.paste()方法，将它们粘贴到相应的网格中
	
	return grid_img



def createPhotomosaic(target_image, input_images, grid_size, reuse_images=True):
	"""
	creates a photomosaic given target and input images
	"""
	
	print('splitting input image...')
	# split the target image into tiles
	target_images = splitImage(target_image, grid_size)
	
	print('finding image matches...')
	# for each tile, pick one matching input image
	output_images = []
	# for user feedback
	count = 0 
	batch_size = int(len(target_images)/10)
	# calculate the average of the input image
	avgs = []
	for img in input_images:
		avgs.append(getAverageRGB(img))
	
	for img in target_images:
		# compute the average RGB value of the image
		avg = getAverageRGB(img)
		# find the matching index of closest RGB value
		# from a list of average RGB values
		match_index = getBestMatchIndex(avg, avgs)
		output_images.append(input_images[match_index])
		# user feedback
		if count > 0 and batch_size > 10 and count % batch_size is 0:
			print('processed %d of %d...' %(count, len(target_images)))
		count += 1 
		# remove the selected image from input if flag set
		if not reuse_images:
			input_images.remove(match)

	print('creating mosaic...')
	# create photomosaic image from tiles
	mosaic_image = createImageGrid(output_images, grid_size)
	
	# display the mosaic
	return mosaic_image


def main():
	# parse arguments
	parser = argparse.ArgumentParser(description='Creates a photomosaic frominput images')

	# add arguments
	parser.add_argument('--target-image', dest='target_image', required=True)
	parser.add_argument('--input-folder', dest='input_folder', required=True)
	parser.add_argument('--grid-size', nargs=2, dest='grid_size', required=True)
	parser.add_argument('--output-file', dest='outfile', required=False)

	args = parser.parse_args()

	target_image = Image.open(args.target_image)

	print('reading input folder...')
	input_images = getImages(args.input_folder)

	if input_images == []:
		print('No input images found in %s. Exiting.' % (args.input_folder, ))
		exit()

	random.shuffle(input_images)

	grid_size = (int(args.grid_size[0]), int(args.grid_size[1]))

	output_filename = 'mosaic.png'
	if args.outfile:
		output_filename = args.outfile

	reuse_images =True
	resize_input = True

	print('starting photomosaic creation...')

	if not reuse_images:
		if grid_size[0]*grid_size[1] > len(input_images):
			print('grid size less than number of images')
			exit()

	if resize_input:
		print('resizing images...')
		# for given grid size, compute the maximum width and height of tiles
		dims = (int(target_image.size[0]/grid_size[1]),
				int(target_image.size[1]/grid_size[0]))
		print("max tile dims: %s" % (dims,))
		# resize
		for img in input_images:
			img.thumbnail(dims)

	mosaic_image = createPhotomosaic(target_image, input_images, grid_size, reuse_images)
	mosaic_image.save(output_filename, 'PNG')
	print("saved output to %s" % (output_filename,))
	print('done.')

if __name__ == '__main__':
	main()

运行程序

在本文件所在目录打开终端，输入：

python photomosaic.py --target-image cherai.jpg --input-folder test-data/set6/ --grid-size 128 128

其中 photomosaic.py是本文件名，cherai.jpg是输入图像的名称，**test-data/set6/**是输入图像所在的文件夹，128 128是网格尺寸，可根据需要自行更改。