图像分割预处理,利用keras同时对图像和标签进行数据增强

问题描述:进行分割操作时,为了扩充数据量,要对图像进行数据增强,而相应的标签(mask)也要做与图像对应的数据增强以保持一致的变换.
文件夹设定:
data文件夹下有images,masks和aug三个文件夹,分别代表图像,标签以及增强后的图像&标签.

程序

载入模块

#将image和mask同时做图像增强
import keras
from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img
import os
import numpy as np 

原图像和标签预处理(归一化,设置通道等)

def adjustData(img,mask,flag_multi_class,num_class):
    if(flag_multi_class):
        img = img / 255
        mask = mask[:,:,:,0] if(len(mask.shape) == 4) else mask[:,:,0]
        new_mask = np.zeros(mask.shape + (num_class,))
        for i in range(num_class):
            #for one pixel in the image, find the class in mask and convert it into one-hot vector
            #index = np.where(mask == i)
            #index_mask = (index[0],index[1],index[2],np.zeros(len(index[0]),dtype = np.int64) + i) if (len(mask.shape) == 4) else (index[0],index[1],np.zeros(len(index[0]),dtype = np.int64) + i)
            #new_mask[index_mask] = 1
            new_mask[mask == i,i] = 1
        new_mask = np.reshape(new_mask,(new_mask.shape[0],new_mask.shape[1]*new_mask.shape[2],new_mask.shape[3])) if flag_multi_class else np.reshape(new_mask,(new_mask.shape[0]*new_mask.shape[1],new_mask.shape[2]))
        mask = new_mask
    elif(np.max(img) > 1):
        img = img / 255
        mask = mask /255
        mask[mask > 0.5] = 1
        mask[mask <= 0.5] = 0
    return (img,mask)

设置增强效果(图像输出大小,灰度显示,图像输出路径等)

def trainGenerator(batch_size,train_path,image_folder,mask_folder,aug_dict,image_color_mode = "grayscale",
                    mask_color_mode = "grayscale",image_save_prefix  = "image",mask_save_prefix  = "mask",
                    flag_multi_class = False,num_class = 2,save_to_dir = None,target_size = (256,256),seed = 1):
    '''
    can generate image and mask at the same time
    use the same seed for image_datagen and mask_datagen to ensure the transformation for image and mask is the same
    if you want to visualize the results of generator, set save_to_dir = "your path"
    '''
    image_datagen = ImageDataGenerator(**aug_dict)
    mask_datagen = ImageDataGenerator(**aug_dict)
    image_generator = image_datagen.flow_from_directory(
        train_path,
        classes = [image_folder],
        class_mode = None,
        color_mode = image_color_mode,
        target_size = target_size,
        batch_size = batch_size,
        save_to_dir = save_to_dir,
        save_prefix  = image_save_prefix,
        seed = seed)
    mask_generator = mask_datagen.flow_from_directory(
        train_path,
        classes = [mask_folder],
        class_mode = None,
        color_mode = mask_color_mode,
        target_size = target_size,
        batch_size = batch_size,
        save_to_dir = save_to_dir,
        save_prefix  = mask_save_prefix,
        seed = seed)
    train_generator = zip(image_generator, mask_generator)
    for (img,mask) in train_generator:
        img,mask = adjustData(img,mask,flag_multi_class,num_class)
        yield (img,mask)

设置增强参数(旋转,平移等)

data_gen_args = dict(rotation_range=0.2,
                    width_shift_range=0.05,
                    height_shift_range=0.05,
                    shear_range=0.05,
                    zoom_range=0.05,
                    horizontal_flip=True,
                    fill_mode='nearest')

调用函数(输出路径save_to_dir可以自己调整,默认为None)

myGene = trainGenerator(2,'data','images','masks',data_gen_args,save_to_dir = 'data/aug')

执行函数(num_batch代表同一幅图像增强多少次,可视情况调整)

num_batch = 3
for i,batch in enumerate(myGene):
    if(i >= num_batch):
        break

end

增强后的效果:

图片1

标签1

图片2

标签2

总程序

#将image和mask同时做图像增强
#使用方法:将images和masks(label)各放入一个文件夹中,更改程序中的文件夹路径即可
import keras
from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img
import os
import numpy as np 
import os
#import glob
#import skimage.io as io
#import skimage.transform as trans

def adjustData(img,mask,flag_multi_class,num_class):
    if(flag_multi_class):
        img = img / 255
        mask = mask[:,:,:,0] if(len(mask.shape) == 4) else mask[:,:,0]
        new_mask = np.zeros(mask.shape + (num_class,))
        for i in range(num_class):
            #for one pixel in the image, find the class in mask and convert it into one-hot vector
            #index = np.where(mask == i)
            #index_mask = (index[0],index[1],index[2],np.zeros(len(index[0]),dtype = np.int64) + i) if (len(mask.shape) == 4) else (index[0],index[1],np.zeros(len(index[0]),dtype = np.int64) + i)
            #new_mask[index_mask] = 1
            new_mask[mask == i,i] = 1
        new_mask = np.reshape(new_mask,(new_mask.shape[0],new_mask.shape[1]*new_mask.shape[2],new_mask.shape[3])) if flag_multi_class else np.reshape(new_mask,(new_mask.shape[0]*new_mask.shape[1],new_mask.shape[2]))
        mask = new_mask
    elif(np.max(img) > 1):
        img = img / 255
        mask = mask /255
        mask[mask > 0.5] = 1
        mask[mask <= 0.5] = 0
    return (img,mask)def adjustData(img,mask,flag_multi_class,num_class):
    if(flag_multi_class):
        img = img / 255
        mask = mask[:,:,:,0] if(len(mask.shape) == 4) else mask[:,:,0]
        new_mask = np.zeros(mask.shape + (num_class,))
        for i in range(num_class):
            #for one pixel in the image, find the class in mask and convert it into one-hot vector
            #index = np.where(mask == i)
            #index_mask = (index[0],index[1],index[2],np.zeros(len(index[0]),dtype = np.int64) + i) if (len(mask.shape) == 4) else (index[0],index[1],np.zeros(len(index[0]),dtype = np.int64) + i)
            #new_mask[index_mask] = 1
            new_mask[mask == i,i] = 1
        new_mask = np.reshape(new_mask,(new_mask.shape[0],new_mask.shape[1]*new_mask.shape[2],new_mask.shape[3])) if flag_multi_class else np.reshape(new_mask,(new_mask.shape[0]*new_mask.shape[1],new_mask.shape[2]))
        mask = new_mask
    elif(np.max(img) > 1):
        img = img / 255
        mask = mask /255
        mask[mask > 0.5] = 1
        mask[mask <= 0.5] = 0
    return (img,mask)

def trainGenerator(batch_size,train_path,image_folder,mask_folder,aug_dict,image_color_mode = "grayscale",
                    mask_color_mode = "grayscale",image_save_prefix  = "image",mask_save_prefix  = "mask",
                    flag_multi_class = False,num_class = 2,save_to_dir = None,target_size = (256,256),seed = 1):
    '''
    can generate image and mask at the same time
    use the same seed for image_datagen and mask_datagen to ensure the transformation for image and mask is the same
    if you want to visualize the results of generator, set save_to_dir = "your path"
    '''
    image_datagen = ImageDataGenerator(**aug_dict)
    mask_datagen = ImageDataGenerator(**aug_dict)
    image_generator = image_datagen.flow_from_directory(
        train_path,
        classes = [image_folder],
        class_mode = None,
        color_mode = image_color_mode,
        target_size = target_size,
        batch_size = batch_size,
        save_to_dir = save_to_dir,
        save_prefix  = image_save_prefix,
        seed = seed)
    mask_generator = mask_datagen.flow_from_directory(
        train_path,
        classes = [mask_folder],
        class_mode = None,
        color_mode = mask_color_mode,
        target_size = target_size,
        batch_size = batch_size,
        save_to_dir = save_to_dir,
        save_prefix  = mask_save_prefix,
        seed = seed)
    train_generator = zip(image_generator, mask_generator)
    for (img,mask) in train_generator:
        img,mask = adjustData(img,mask,flag_multi_class,num_class)
        yield (img,mask)

data_gen_args = dict(rotation_range=0.2,
                    width_shift_range=0.05,
                    height_shift_range=0.05,
                    shear_range=0.05,
                    zoom_range=0.05,
                    horizontal_flip=True,
                    fill_mode='nearest')

#save_to_dir代表增强后的图像的存储路径,可设置为None,代表存储于原图像文件夹下
myGene = trainGenerator(2,'data','images','masks',data_gen_args,save_to_dir = 'data/aug')

#num_batch代表增强次数
num_batch = 3
for i,batch in enumerate(myGene):
    if(i >= num_batch):
        break