Python PIL库处理图片常用操作，图像识别数据增强的方法
在博客AlexNet原理及tensorflow实现训练神经网络的时候，做了数据增强，对图片的处理采用的是PIL(Python Image Library), PIL是Python常用的图像处理库.
下面对PIL中常用到的操作进行整理：
1. 改变图片的大小
from PIL import Image, ImageFont, ImageDraw
def image_resize(image, save, size=(100, 100)):
"""
:param image: 原图片
:param save: 保存地址
:param size: 大小
:return:
"""
image = Image.open(image) # 读取图片
image.convert("RGB")
re_sized = image.resize(size, Image.BILINEAR) # 双线性法
re_sized.save(save) # 保存图片
return re_sized2. 对图片进行旋转：
from PIL import Image, ImageFont, ImageDraw
import matplotlib.pyplot as plt
def image_rotate(image_path, save_path, angle):
"""
对图像进行一定角度的旋转
:param image_path: 图像路径
:param save_path: 保存路径
:param angle: 旋转角度
:return:
"""
image = Image.open(image_path)
image_rotated = image.rotate(angle, Image.BICUBIC)
image_rotated.save(save_path)
return image_rotated
3. 对图片进行左右反转：
from PIL import Image, ImageFont, ImageDraw
import matplotlib.pyplot as plt
def image_flip(image_path, save_path):
"""
图图象进行左右反转
:param image_path:
:param save_path:
:return:
"""
image = Image.open(image_path)
image_transpose = image.transpose(Image.FLIP_LEFT_RIGHT) # Image.FLIP_TOP_BOTTOM 上下反转
image_transpose.save(save_path)
return image_transpose
4. 对图像进行裁剪：
from PIL import Image, ImageFont, ImageDraw
import matplotlib.pyplot as plt
def image_crop(image_path, save_path, crop_region):
"""
对图像进行裁剪
:param image_path:
:param save_path:
:param crop_region: 裁剪的区域 crop_window=(x_min, y_min, x_max, y_max)
:return:
"""
image = Image.open(image_path)
image_crop = image.crop(crop_region) # (width_min, height_min, width_max, height_max) 图像的原点是在左上角
image_crop.save(save_path)
return image_crop
5. 在图片上添加文字
from PIL import Image, ImageFont, ImageDraw
import matplotlib.pyplot as plt
def image_title(image_path, save_path, font_pos, font_size, text):
"""
对图像添加文字
:param image_path:
:param save_path:
:param font_pos: 文字位置(x, y)
:param font_size: 文字大小
:param text: 文字内容
:return:
"""
image = Image.open(image_path)
font = ImageFont.truetype(font=r"C:\Windows\Fonts\Times New Roman\times.ttf", size=font_size)
draw = ImageDraw.Draw(image)
draw.text(xy=font_pos, text=text, fill=(255, 0, 0), font=font)
image.save(save_path)
return image
除以上之外，数据增强的方法还有对图像颜色进行抖动，和对图像进行高斯噪声处理
1. 颜色抖动：
from PIL import Image, ImageFont, ImageDraw, ImageEnhance
import matplotlib.pyplot as plt
import numpy as np
def image_color(image_path, save_path):
"""
对图像进行颜色抖动
:param image_path:
:param save_path:
:return:
"""
image = Image.open(image_path)
print(type(image))
random_factor = np.random.randint(low=0, high=31) / 10.0 # 随机的扰动因子
color_image = ImageEnhance.Color(image).enhance(random_factor) # 调整图像的饱和度
random_factor = np.random.randint(low=10, high=21) / 10.0
bright_image = ImageEnhance.Brightness(color_image).enhance(random_factor) # 调整图像的亮度
random_factor = np.random.randint(low=10, high=21) / 10.0
contrast_image = ImageEnhance.Contrast(bright_image).enhance(random_factor) # 调整图像的对比度
random_factor = np.random.randint(low=0, high=31) / 10.0
sharp_image = ImageEnhance.Sharpness(contrast_image).enhance(random_factor) # 调整图像的锐度
sharp_image.save(save_path)
return sharp_image
2.高斯噪声处理：
from PIL import Image, ImageFont, ImageDraw, ImageEnhance
import matplotlib.pyplot as plt
import numpy as np
import random
def image_gauss(image_path, save_path, mean, stddev):
"""
对图像进行颜色抖动
:param image_path:
:param save_path:
:return:
"""
def gaussNoisy(pixel_array, mean, stddev):
"""
对图像的单个通道进行高斯噪声处理
:param pixel_array:
:param mean: 均值
:param stddev: 方差
:return:
"""
for x in pixel_array:
x += random.gauss(mean, stddev)
return pixel_array
# 对图像进行数据转换
image = Image.open(image_path)
image.convert("RGB")
img = np.asarray(image) # 将PIL中的数据格式转化为array
img.flags.writeable = True # 将数组改为读写模式
width, height = img.shape[: 2]
img_r = img[:, :, 0].flatten()
img_g = img[:, :, 1].flatten()
img_b = img[:, :, 2].flatten()
img_r_new = gaussNoisy(pixel_array=img_r, mean=mean, stddev=stddev)
img_g_new = gaussNoisy(pixel_array=img_g, mean=mean, stddev=stddev)
img_b_new = gaussNoisy(pixel_array=img_b, mean=mean, stddev=stddev)
img[:, :, 0] = img_r_new.reshape([width, height])
img[:, :, 1] = img_g_new.reshape([width, height])
img[:, :, 2] = img_b_new.reshape([width, height])
image_new = Image.fromarray(np.uint8(img)) # 将array中的数据格式转化为PIL中的数据格式
image_new.save(save_path)
return image_new
