图像数据预处理之图像增强方法汇总

图像数据预处理

图像增强方法汇总

使用cv2

水平翻转

def horizon_flip(img):
#图像水平翻转
    return cv2.flip(img, 1)

垂直翻转

def vertical_flip(img):
#图像垂直翻转
    return cv2.flip(img, 0)

仿射(角度)变化

def rotate(img, limit_up=10, limit_down=-10):
#在一定角度范围内，图像随机旋转
    rows, cols = img.shape[:2]
    center_coordinate = (int(cols / 2), int(rows / 2))
    angle = random.uniform(limit_down, limit_up)
    M = cv2.getRotationMatrix2D(center_coordinate, angle, 1)

    # 仿射变换
    out_size = (cols, rows)
    rotate_img = cv2.warpAffine(img, M, out_size, borderMode=cv2.BORDER_REPLICATE)

    return rotate_img

仿射平移变化

def shift(img, distance_down, distance_up):
#利用仿射变换实现图像平移，平移距离∈[down, up]
    rows, cols = img.shape[:2]
    y_shift = random.uniform(distance_down, distance_up)
    x_shift = random.uniform(distance_down, distance_up)

    # 生成平移矩阵
    M = np.float32([[1, 0, x_shift], [0, 1, y_shift]])
    # 平移
    img_shift = cv2.warpAffine(img, M, (cols, rows), borderMode=cv2.BORDER_REPLICATE)

    return img_shift

亮度对比度调整

def lighting_adjust(img, k_down, k_up, b_down, b_up):

    # 图像亮度、对比度调整
    # :param img:
    # :param k_down:对比度系数下限
    # :param k_up:对比度系数上限
    # :param b_down:亮度增值上限
    # :param b_up:亮度增值下限
    # :return:调整后的图像
    #
    # #对比度调整系数
    slope = random.uniform(k_down, k_up)
    # 亮度调整系数
    bias = random.uniform(b_down, b_up)
    # 图像亮度和对比度调整
    img = img * slope + bias
    # 灰度值截断，防止超出255
    img = np.clip(img, 0, 255)

    return cv2.cvtColor(img.astype(np.uint8),cv2.COLOR_BGR2RGB)

高斯噪声

def Gaussian_noise(img):
 #
 #    图像加高斯噪声
 #    :param img: 原图
 #    :param mean: 均值
 #    :param std: 标准差
 #    :return:
 #
 #    # 高斯噪声图像
    img = cv2.GaussianBlur(img, (5, 5), 1.1)
    return img

椒盐噪声

def sp_noiseImg(img_file1,prob): #同时加杂乱(RGB单噪声)RGB图噪声 prob:噪声占比
     image = np.array(img_file1,dtype=float)
     height = image.shape[0]
     width = image.shape[1]
     channels = image.shape[2]
     #prob = 0.05 #噪声占比 已经比较明显了 >0.1 严重影响画质
     NoiseImg = image.copy()
     NoiseNum = int(prob * image.shape[0] * image.shape[1])

     for i in range(NoiseNum):
         rows = np.random.randint(0, image.shape[0] - 1)
         cols = np.random.randint(0, image.shape[1] - 1)
         channel = np.random.randint(0, 3)
         if np.random.randint(0, 2) == 0:#随机加盐或者加椒
             NoiseImg[rows, cols, channel] = 0
         else:
             NoiseImg[rows, cols, channel] = 255
     return NoiseImg

锐化处理

def burl(image):
    kernel = np.array([[0, -1, 0], [-1, 5, -1], [0, -1, 0]], np.float32)  # 锐化
    dst = cv2.filter2D(image, -1, kernel=kernel)
    return dst