「深度学习一遍过」必修4:图像数据增强解决你的有限数据集

Posted 荣仔!最靓的仔!

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了「深度学习一遍过」必修4:图像数据增强解决你的有限数据集相关的知识,希望对你有一定的参考价值。

本专栏用于记录关于深度学习的笔记,不光方便自己复习与查阅,同时也希望能给您解决一些关于深度学习的相关问题,并提供一些微不足道的人工神经网络模型设计思路。
专栏地址:「深度学习一遍过」必修篇

目录

1 方法

2 具体实现

2.1 缩放

2.1.1 放大缩小

2.2 翻转

2.2.1 水平翻转

2.2.2 垂直翻转

2.2.3 旋转

2.3 明亮度

2.3.1 变暗

 2.3.2 变亮

2.3.3 平移

2.4 增加噪声

2.4.1 增加椒盐噪声

2.4.2 增加高斯噪声

3 完整代码

4 效果展示 


1 方法

  • 尺寸放大缩小
  • 旋转(任意角度,如45°,90°,180°,270°)
  • 翻转(水平翻转,垂直翻转)
  • 明亮度改变(变亮,变暗)
  • 像素平移(往一个方向平移像素,空出部分自动填补黑色)
  • 添加噪声(椒盐噪声,高斯噪声) 

:不可用 “复制粘贴” 思想进行图像增强,因为此方法对计算机来说得到的图像是一样的,不会起到数据增强的效果。

2 具体实现

2.1 缩放

2.1.1 放大缩小

cv2.resize(image, None, fx=scale, fy=scale, interpolation=cv2.INTER_LINEAR)

2.2 翻转

2.2.1 水平翻转

cv2.flip(image, 1, dst=None)  # 水平镜像

2.2.2 垂直翻转

cv2.flip(image, 0, dst=None)  # 垂直镜像

2.2.3 旋转

R可控制图片放大缩小 

cv2.warpAffine(image, M, (w, h))

2.3 明亮度

2.3.1 变暗

image_copy[xj, xi, 0] = int(image[xj, xi, 0] * percetage)
image_copy[xj, xi, 1] = int(image[xj, xi, 1] * percetage)
image_copy[xj, xi, 2] = int(image[xj, xi, 2] * percetage)

 2.3.2 变亮

image_copy[xj, xi, 0] = np.clip(int(image[xj, xi, 0] * percetage), a_max=255, a_min=0)
image_copy[xj, xi, 1] = np.clip(int(image[xj, xi, 1] * percetage), a_max=255, a_min=0)
image_copy[xj, xi, 2] = np.clip(int(image[xj, xi, 2] * percetage), a_max=255, a_min=0)

2.3.3 平移

cv2.warpAffine(img, mat_translation, (width, height)) 

2.4 增加噪声

2.4.1 增加椒盐噪声

randR = np.random.randint(0, src.shape[0] - 1)
randG = np.random.randint(0, src.shape[1] - 1)
randB = np.random.randint(0, 3)
if np.random.randint(0, 1) == 0:
    SP_NoiseImg[randR, randG, randB] = 0
else:
    SP_NoiseImg[randR, randG, randB] = 255

2.4.2 增加高斯噪声

temp_x = np.random.randint(0, h)
temp_y = np.random.randint(0, w)
G_Noiseimg[temp_x][temp_y][np.random.randint(3)] = np.random.randn(1)[0]

3 完整代码

import os
import cv2
import numpy as np

'''
缩放
'''
# 放大缩小
def Scale(image, scale):
    return cv2.resize(image, None, fx=scale, fy=scale, interpolation=cv2.INTER_LINEAR)

'''
翻转
'''
# 水平翻转
def Horizontal(image):
    return cv2.flip(image, 1, dst=None)  # 水平镜像

# 垂直翻转
def Vertical(image):
    return cv2.flip(image, 0, dst=None)  # 垂直镜像

# 旋转
def Rotate(image, angle=15, scale=0.9):
    w = image.shape[1]
    h = image.shape[0]
    M = cv2.getRotationMatrix2D((w / 2, h / 2), angle, scale)     # rotate matrix
    image = cv2.warpAffine(image, M, (w, h))       # rotate
    return image

'''  
明亮度 
'''
# 变暗
def Darker(image, percetage=0.9):
    image_copy = image.copy()
    w = image.shape[1]
    h = image.shape[0]
    # get darker
    for xi in range(0, w):
        for xj in range(0, h):
            image_copy[xj, xi, 0] = int(image[xj, xi, 0] * percetage)
            image_copy[xj, xi, 1] = int(image[xj, xi, 1] * percetage)
            image_copy[xj, xi, 2] = int(image[xj, xi, 2] * percetage)
    return image_copy


# 明亮
def Brighter(image, percetage=1.1):
    image_copy = image.copy()
    w = image.shape[1]
    h = image.shape[0]
    # get brighter
    for xi in range(0, w):
        for xj in range(0, h):
            image_copy[xj, xi, 0] = np.clip(int(image[xj, xi, 0] * percetage), a_max=255, a_min=0)
            image_copy[xj, xi, 1] = np.clip(int(image[xj, xi, 1] * percetage), a_max=255, a_min=0)
            image_copy[xj, xi, 2] = np.clip(int(image[xj, xi, 2] * percetage), a_max=255, a_min=0)
    return image_copy

# 平移
def Move(img, x, y):
    img_info = img.shape
    height = img_info[0]
    width = img_info[1]
    mat_translation = np.float32([[1, 0, x], [0, 1, y]])  # 变换矩阵:设置平移变换所需的计算矩阵:2行3列
    # [[1,0,20],[0,1,50]]   表示平移变换:其中x表示水平方向上的平移距离,y表示竖直方向上的平移距离。
    dst = cv2.warpAffine(img, mat_translation, (width, height))  # 变换函数
    return dst

'''
增加噪声
'''
# 椒盐噪声
def SaltAndPepper(src, percetage=0.05):
    SP_NoiseImg = src.copy()
    SP_NoiseNum = int(percetage * src.shape[0] * src.shape[1])
    for i in range(SP_NoiseNum):
        randR = np.random.randint(0, src.shape[0] - 1)
        randG = np.random.randint(0, src.shape[1] - 1)
        randB = np.random.randint(0, 3)
        if np.random.randint(0, 1) == 0:
            SP_NoiseImg[randR, randG, randB] = 0
        else:
            SP_NoiseImg[randR, randG, randB] = 255
    return SP_NoiseImg

# 高斯噪声
def GaussianNoise(image, percetage=0.05):
    G_Noiseimg = image.copy()
    w = image.shape[1]
    h = image.shape[0]
    G_NoiseNum = int(percetage * image.shape[0] * image.shape[1])
    for i in range(G_NoiseNum):
        temp_x = np.random.randint(0, h)
        temp_y = np.random.randint(0, w)
        G_Noiseimg[temp_x][temp_y][np.random.randint(3)] = np.random.randn(1)[0]
    return G_Noiseimg

def Blur(img):
    blur = cv2.GaussianBlur(img, (7, 7), 1.5)       # cv2.GaussianBlur(图像,卷积核,标准差)
    return blur


def TestOnePic():
    test_jpg_loc = r"data/daisy/1.jpg"
    test_jpg = cv2.imread(test_jpg_loc)
    cv2.imshow("Show Img", test_jpg)
    img1 = Blur(test_jpg)
    cv2.imshow("Img 1", img1)
    img2 = GaussianNoise(test_jpg,0.01)
    cv2.imshow("Img 2", img2)
    cv2.waitKey(0)


def TestOneDir():
    root_path = "data/daisy"
    save_path = root_path
    for a, b, c in os.walk(root_path):
        for file_i in c:
            file_i_path = os.path.join(a, file_i)
            print(file_i_path)
            img_i = cv2.imread(file_i_path)

            img_scale = Scale(img_i,1.5)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_scale.jpg"), img_scale)

            img_horizontal = Horizontal(img_i)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_horizontal.jpg"), img_horizontal)

            img_vertical = Vertical(img_i)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_vertical.jpg"), img_vertical)

            img_rotate = Rotate(img_i,90)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_rotate90.jpg"), img_rotate)

            img_rotate = Rotate(img_i, 180)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_rotate180.jpg"), img_rotate)

            img_rotate = Rotate(img_i, 270)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_rotate270.jpg"), img_rotate)

            img_move = Move(img_i,15,15)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_move.jpg"), img_move)

            img_darker = Darker(img_i)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_darker.jpg"), img_darker)

            img_brighter = Brighter(img_i)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_brighter.jpg"), img_brighter)

            img_blur = Blur(img_i)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_blur.jpg"), img_blur)

            img_salt = SaltAndPepper(img_i,0.05)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_salt.jpg"), img_salt)


def AllData(rootpath):
    root_path = "data/"
    save_loc = root_path
    for a, b, c in os.walk(root_path):
        for file_i in c:
            file_i_path = os.path.join(a, file_i)
            print(file_i_path)
            split = os.path.split(file_i_path)
            dir_loc = os.path.split(split[0])[1]
            save_path = os.path.join(save_loc, dir_loc)

            img_i = cv2.imread(file_i_path)
            img_scale = Scale(img_i,1.5)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_scale.jpg"), img_scale)

            img_horizontal = Horizontal(img_i)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_horizontal.jpg"), img_horizontal)

            img_vertical = Vertical(img_i)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_vertical.jpg"), img_vertical)

            img_rotate = Rotate(img_i, 90)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_rotate90.jpg"), img_rotate)

            img_rotate = Rotate(img_i, 180)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_rotate180.jpg"), img_rotate)

            img_rotate = Rotate(img_i, 270)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_rotate270.jpg"), img_rotate)

            img_move = Move(img_i, 15, 15)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_move.jpg"), img_move)

            img_darker = Darker(img_i)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_darker.jpg"), img_darker)

            img_brighter = Brighter(img_i)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_brighter.jpg"), img_brighter)

            img_blur = Blur(img_i)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_blur.jpg"), img_blur)

            img_salt = SaltAndPepper(img_i, 0.05)
            cv2.imwrite(os.path.join(save_path, file_i[:-4] + "_salt.jpg"), img_salt)


if __name__ == "__main__":
    TestOneDir()
    TestOnePic()
    root_path = "data/"
    AllData(root_path)

4 效果展示 

欢迎大家交流评论,一起学习

希望本文能帮助您解决您在这方面遇到的问题

感谢阅读
END

版权声明:本文为CSDN博主「荣仔!最靓的仔!」的原创文章,遵循 CC 4.0 BY-SA 版权协议。
         转载请在醒目位置附上原文出处链接及本声明。

以上是关于「深度学习一遍过」必修4:图像数据增强解决你的有限数据集的主要内容,如果未能解决你的问题,请参考以下文章

「深度学习一遍过」必修17:基于Pytorch细粒度分类实战

「深度学习一遍过」必修10:pytorch 框架的使用

「深度学习一遍过」必修26:机器学习与深度学习基础知识汇总

「深度学习一遍过」必修26:机器学习与深度学习基础知识汇总

「深度学习一遍过」必修26:机器学习与深度学习基础知识汇总

「深度学习一遍过」必修9:解读卷积神经网络 AlexNet