目标识别数据集扩充方法

背景引入

在训练图像识别的深度神经网络时，使用大量更多的训练数据，可能会使网络得到更好的性能，例如提高网络的分类准确率，防止过拟合等。人为扩展训练数据时对数据的操作最好能反映真实世界的变化。人为扩充数据集之后如果分类准确率有明显的提升，说明我们对数据所做的拓展操作是良性的，能够“反映真实世界的变化”，就会被用到整个数据集的扩展。反之，则说明不能用此操作对数据集进行拓展。

具体方法

原图

图像强度变换

亮度变化

lightness

darkness

图像整体加上一个随机偏差，或整体进行尺度的放缩

亮度增强
亮度减弱

brightness = 1 + np.random.randint(1, 9) / 10
brightness_img = img.point(lambda p: p * brightness)

对比度变化

contrast

扩展图像灰度级动态范围，对两极的像素进行压缩，对中间范围的像素进行扩展

range_contrast=(-50, 50)
contrast = np.random.randint(*range_contrast)
contrast_img = img.point(lambda p: p * (contrast / 127 + 1) - contrast)

图像滤波

锐化

sharpen

增强图像边缘信息

identity = np.array([[0, 0, 0],[0, 1, 0],[0, 0, 0]])
sharpen = np.array([[ 0, -1,  0],[-1,  4, -1],[ 0, -1,  0]]) / 4
max_center = 4
sharp = sharpen * np.random.random() * max_center
kernel = identity + sharp
sharpen_img = cv2.filter2D(img, -1, kernel)

高斯模糊

blur

图像平滑

kernel_size = (7, 7)
blur_img = cv2.GaussianBlur(img,kernel_size,0)

透视变换

镜像翻转

flip

使图像沿长轴进行翻转

flip_img = cv2.flip(cv2.cvtColor(np.asarray(img),cv2.COLOR_RGB2BGR), 1)

第一个位置的参数 pos = 1 - pos，其他信息不变，可以采用脚本自动生成

with open(name + "_flip.txt", "w") as outfile:with open(name + ".txt", "r") as infile:for line in infile.readlines():words = line.split(" ")horizontal_coord = float(words[1])outfile.write(words[0] + " " + str(format(1-horizontal_coord, ".6f")) + " " + words[2] + " " + words[3] + " " + words[4])

图像裁剪

crop

裁剪原图80%大小的中心图像，并进行随机移动

kernel_size = list(map(lambda x: int(x*0.8), size))
shift_min, shift_max = -50, 50
shift_size = [np.random.randint(shift_min, shift_max), np.random.randint(shift_min, shift_max)]crop_img = img[(size[0]-kernel_size[0])//2+shift_size[0]:(size[0]-kernel_size[0])//2+kernel_size[0]+shift_size[0],(size[1]-kernel_size[1])//2+shift_size[1]:(size[1]-kernel_size[1])//2+kernel_size[1]+shift_size[1]
]

图像拉伸

deform

拉伸成长宽为原始宽的正方形图像

deform_img = img.resize((int(w), int(w)))

镜头畸变

distortion

对图像进行透视变化，模拟鱼眼镜头的镜头畸变

通过播放径向系数k1，k2，k3和切向系数p1，p2实现

d_coef= np.array((0.15, 0.15, 0.1, 0.1, 0.05))
# get the height and the width of the image
h, w = img.shape[:2]
# compute its diagonal
f = (h ** 2 + w ** 2) ** 0.5
# set the image projective to carrtesian dimension
K = np.array([[f, 0, w / 2],[0, f, h / 2],[0, 0,   1  ]])
d_coef = d_coef * np.random.random(5) # value
d_coef = d_coef * (2 * (np.random.random(5) < 0.5) - 1) # sign
# Generate new camera matrix from parameters
M, _ = cv2.getOptimalNewCameraMatrix(K, d_coef, (w, h), 0)
# Generate look-up tables for remapping the camera image
remap = cv2.initUndistortRectifyMap(K, d_coef, None, M, (w, h), 5)
# Remap the original image to a new image
distortion_img = cv2.remap(img, *remap, cv2.INTER_LINEAR)

注入噪声

椒盐噪声

noise

在图像中随机添加白/黑像素

for i in range(5000):x = np.random.randint(0,rows)y = np.random.randint(0,cols)noise_img[x,y,:] = 255noise_img.flags.writeable = True

渐晕

vignetting

对图像添加一个圆范围内的噪声模拟光晕

ratio_min_dist=0.2
range_vignette=np.array((0.2, 0.8))
random_sign=Falseh, w = img.shape[:2]
min_dist = np.array([h, w]) / 2 * np.random.random() * ratio_min_dist# create matrix of distance from the center on the two axis
x, y = np.meshgrid(np.linspace(-w/2, w/2, w), np.linspace(-h/2, h/2, h))
x, y = np.abs(x), np.abs(y)
# create the vignette mask on the two axis
x = (x - min_dist[0]) / (np.max(x) - min_dist[0])
x = np.clip(x, 0, 1)
y = (y - min_dist[1]) / (np.max(y) - min_dist[1])
y = np.clip(y, 0, 1)
# then get a random intensity of the vignette
vignette = (x + y) / 2 * np.random.uniform(*range_vignette)
vignette = np.tile(vignette[..., None], [1, 1, 3])
sign = 2 * (np.random.random() < 0.5) * (random_sign) - 1
vignetting_img = img * (1 + sign * vignette)

其他

随机抠除

cutout

随机抠出四个位置，并用黑色/彩色矩形填充

channel_wise = False
max_crop = 4
replacement=0size = np.array(img.shape[:2])
mini, maxi = min_size_ratio * size, max_size_ratio * size
cutout_img = img
for _ in range(max_crop):# random sizeh = np.random.randint(mini[0], maxi[0])w = np.random.randint(mini[1], maxi[1])# random placeshift_h = np.random.randint(0, size[0] - h)shift_w = np.random.randint(0, size[1] - w)if channel_wise:c = np.random.randint(0, img.shape[-1])cutout_img[shift_h:shift_h+h, shift_w:shift_w+w, c] = replacementelse:cutout_img[shift_h:shift_h+h, shift_w:shift_w+w] = replacement