本文主要是介绍python深度学习训练样本图像增强，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
深度学习样本标完后图片增强标签内容不变02_train图片增强后-CSDN博客
begin部分两部分都打开则可以实现随机从A图取一部分放至B图中增强图像
功能的优化
import numpy as np
import cv2
import copy
import random
import argparse
import globdef random_gray(em):if em >= 128:B = np.random.randint(0, 30)G = np.random.randint(0, 30)R = np.random.randint(0, 30)else:B = np.random.randint(196, 226)G = np.random.randint(196, 226)R = np.random.randint(196, 226)return (B, G, R)def get_hull(axis_list):hull = cv2.convexHull(axis_list, clockwise=True, returnPoints=True)return hulldef generate_curve(img, control_points, color, thickness):# 使用贝塞尔曲线拟合头发弯曲线条curve_points = []num_points = 100 # 调整生成的曲线上的点的数量for t in np.linspace(0, 1, num_points):curve_point = np.power(1 - t, 3) * control_points[0] + 3 * np.power(1 - t, 2) * t * control_points[1] + 3 * (1 - t) * np.power(t, 2) * control_points[2] + np.power(t, 3) * control_points[3]curve_points.append(curve_point)curve_points = np.array(curve_points, dtype=np.int32)# 绘制头发弯曲线条cv2.polylines(img, [curve_points], isClosed=False, color=color, thickness=thickness)return imgdef rotation(img, angle):rows = img.shape[0]cols = img.shape[1]M = cv2.getRotationMatrix2D((cols / 2, rows / 2), angle=angle, scale=1) # 向左旋转angle度并缩放为原来的scale倍img = cv2.warpAffine(img, M, (cols, rows), cv2.INTER_NEAREST) # 第三个参数是输出图像的尺寸中心return imgdef random_jitter(input, dx, dy):H = np.float32([[1, 0, dx], [0, 1, dy]]) # 定义平移矩阵rows, cols = input.shape[:2] # 获取图像高宽(行列数)res = cv2.warpAffine(input, H, (cols, rows), cv2.INTER_NEAREST)return resdef black_edge_crop(img, H, W):return cv2.resize(img[30:H - 30, 30:W - 30, :], dsize=(W, H))def random_h(img):img = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)region_mask1 = np.where(img[:, :, 0] < 175, 1, 0)region_mask2 = np.where(img[:, :, 0] > 5, 1, 0)region_mask = np.bitwise_and(region_mask1, region_mask2)hue_t = np.ones_like(img[:, :, 0]) * np.random.randint(-5, 6) * region_maskimg[:, :, 0] = img[:, :, 0] + hue_treturn cv2.cvtColor(img, cv2.COLOR_HSV2BGR)def brightness_adjustment(img):blank = np.zeros_like(img)c = (1 + np.random.randint(low=-1, high=2, size=None, dtype='l') / 10.)img = cv2.addWeighted(img, c, blank, 1 - c, 0)return imgdef change_channel(img, sd):b, g, r = cv2.split(img)if sd == 0:out = cv2.merge([b, r, g])elif sd == 1:out = cv2.merge([b, g, r])elif sd == 2:out = cv2.merge([r, g, b])elif sd == 3:out = cv2.merge([r, b, g])elif sd == 4:out = cv2.merge([g, b, r])elif sd == 5:out = cv2.merge([g, r, b])return outdef random_flip(input, flag):if flag == 1:return np.fliplr(input)elif flag == 2:return np.flipud(input)elif flag == 3:return np.flipud(np.fliplr(input))else:return inputdef gen_diffs(ex, mask, diff_src, num_diff, H, W):big_cnt = 0for b in range(num_diff):# 随机确定左上角的点和长宽if np.random.randint(0, 30) == 0 and big_cnt == 0:x_l, y_l, w, h = np.random.randint(low=99, high=W - 300, size=None, dtype='l'), \np.random.randint(low=99, high=H - 300, size=None, dtype='l'), \np.random.randint(low=100, high=300, size=None, dtype='l'), \np.random.randint(low=100, high=300, size=None, dtype='l')big_cnt = 1big_flag = 1else:x_l, y_l, w, h = np.random.randint(low=49, high=W - 50, size=None, dtype='l'), \np.random.randint(low=49, high=H - 50, size=None, dtype='l'), \np.random.randint(low=10, high=50, size=None, dtype='l'), \np.random.randint(low=10, high=50, size=None, dtype='l')big_flag = 0# 在此方形区域内生成差异， 同时将空mask图片中的对应区域变为1（白色）作为标签points = [[x_l + w // 2, y_l + h // 2]]for i in range(x_l, x_l + w):for j in range(y_l, y_l + h):if big_flag == 1:if np.random.randint(0, 5000) == 1:points.append([i, j])else:if np.random.randint(0, 100) == 1:points.append([i, j])random.shuffle(points)pts = np.asarray([points], dtype=np.int32)hull = get_hull(pts).transpose(1, 0, 2)mask = cv2.fillPoly(mask.copy(), hull, color=1)ex = cv2.fillPoly(ex.copy(), hull, color=(0, 0, 0))kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3))mask = cv2.dilate(mask.copy(), kernel, 1)mask_filled = np.stack((mask, mask, mask), axis=2)mask_filled = cv2.GaussianBlur(mask_filled, (3, 3), 0, 0)ex = (255 * ((ex / 255) * (1 - mask_filled) + (diff_src / 255) * mask_filled)).astype(np.uint8)return ex, maskdef one_curve(ex, mask, H, W):x1 = np.random.randint(20, W - 20)y1 = np.random.randint(20, H - 20)x2 = max(min(x1 + np.random.randint(-20, 20), W - 1), 0)y2 = max(min(y1 + np.random.randint(-20, 20), H - 1), 0)x3 = max(min(x2 + np.random.randint(-40, 40), W - 1), 0)y3 = max(min(y2 + np.random.randint(-40, 40), H - 1), 0)x4 = max(min(x3 + np.random.randint(-80, 80), W - 1), 0)y4 = max(min(y3 + np.random.randint(-80, 80), H - 1), 0)control_points = np.array([[x1, y1], [x2, y2], [x3, y3], [x4, y4]], dtype=np.int32)thickness = np.random.randint(1, 3)mask_for_curve = np.zeros_like(mask)mask_for_curve = generate_curve(mask_for_curve, control_points, 1, thickness)mask = generate_curve(mask, control_points, 1, thickness)ex_mean = ex[mask_for_curve == 1].sum() / np.sum(mask_for_curve == 1)ex = generate_curve(ex.copy(), control_points, random_gray(ex_mean / 3), thickness)return ex, maskdef noisy(noise_typ, image):if noise_typ == "gauss":row, col, ch = image.shapemean = 0var = 0.001sigma = var ** 0.5gauss = np.random.normal(mean, sigma, (row, col, ch))gauss = gauss.reshape(row, col, ch)noisy = (image / 255 + gauss) if np.random.randint(0, 2) == 1 else (image / 255 - gauss)noisy = cv2.normalize(noisy, None, alpha=0, beta=1, norm_type=cv2.NORM_MINMAX)noisy = np.uint8(noisy * 255)return noisyelif noise_typ == "s&p":row, col, ch = image.shapes_vs_p = 0.5amount = 0.004out = np.copy(image)# Salt modenum_salt = np.ceil(amount * image.size * s_vs_p)coords = [np.random.randint(0, i - 1, int(num_salt))for i in image.shape[:2]]out[:, :, 0:1][tuple(coords)] = 255out[:, :, 1:2][tuple(coords)] = 255out[:, :, 2:3][tuple(coords)] = 255# Pepper modenum_pepper = np.ceil(amount * image.size * (1. - s_vs_p))coords = [np.random.randint(0, i - 1, int(num_pepper))for i in image.shape[:2]]out[:, :, 0:1][tuple(coords)] = 0out[:, :, 1:2][tuple(coords)] = 0out[:, :, 2:3][tuple(coords)] = 0return outdef add_noise(image):# random numberr = np.random.rand(1)# gaussian noiseif r < 0.9:row, col, ch = image.shapemean = 0var = np.random.rand(1) * 0.3 * 256sigma = var ** 0.5gauss = sigma * np.random.randn(row, col) + meangauss = np.repeat(gauss[:, :, np.newaxis], ch, axis=2)noisy = image + gaussnoisy = np.clip(noisy, 0, 255)else:# motion blursizes = [3, 5, 7, 9, 11, 15]size = sizes[int(np.random.randint(len(sizes), size=1))]kernel_motion_blur = np.zeros((size, size))if np.random.rand(1) < 0.5:kernel_motion_blur[int((size - 1) / 2), :] = np.ones(size)else:kernel_motion_blur[:, int((size - 1) / 2)] = np.ones(size)kernel_motion_blur = kernel_motion_blur / sizenoisy = cv2.filter2D(image, -1, kernel_motion_blur)return noisydef virtual_light(img):# 获取图像行和列rows, cols = img.shape[:2]# 设置中心点和光照半径centerX = np.random.randint(50, cols - 50)centerY = np.random.randint(50, rows - 50)radius = min(centerX, centerY)# radius = np.random.randint(50, cols // 4)# 设置光照强度strength = 0 + np.random.randint(-20, 20)x = 1 if np.random.randint(0, 2) == 1 else -1# 新建目标图像distance = (centerY - np.arange(rows)[:, np.newaxis] - 0.5) ** 2 + \(centerX - np.arange(cols)[np.newaxis, :] - 0.5) ** 2# 计算结果矩阵result = strength * (1 - np.sqrt(distance) / radius)result[distance >= radius ** 2] = 0result = np.clip(result * x, -255, 255).astype("int32")# 添加结果dst = np.clip(img + result[..., np.newaxis], 0, 255).astype("uint8")return dstdef random_resize(img, right, up, fg):H, W = img.shape[0], img.shape[1]if fg == 0:if len(img.shape) == 3:img_croped = img[20:H - 20, 20:W - 20, :]else:img_croped = img[20:H - 20, 20:W - 20]img_resized = cv2.resize(img_croped, dsize=(W, H), interpolation=cv2.INTER_NEAREST)elif fg == 1:img_resized = imgelse:img_paded = cv2.copyMakeBorder(img, int(up), int(up), int(right), int(right),cv2.BORDER_CONSTANT, value=0)img_resized = cv2.resize(img_paded, dsize=(W, H), interpolation=cv2.INTER_NEAREST)return img_resized.copy()def add_time_noise(image):mu = np.random.randint(0, 30) / 10.sigma = np.random.randint(0, 30) / 10.noise = np.random.normal(mu, sigma, image.shape)noisy_image = (image + noise) if np.random.randint(0, 2) == 0 else (image - noise)noisy_image = np.clip(noisy_image, 0, 255).astype(np.uint8)return noisy_imagedef rgb_norm(image):r, g, b = cv2.split(image)eps = 1e-7r = (r - np.mean(r)) / (np.std(r) + eps)g = (g - np.mean(g)) / (np.std(g) + eps)b = (b - np.mean(b)) / (np.std(b) + eps)return cv2.merge((r, g, b))def make_datasets(args):H, W = args.HWfor a in range(L):## begin# 随机从A图中截取部分copy至B图中# num_diff = np.random.randint(low=12, high=20, size=None, dtype='l') # 生成差异的数量# mask = np.zeros((H, W)) # 生成固定大小的空白图片（全黑）## begin src = cv2.imread(imgs[a])src = cv2.resize(src, dsize=(H, W)) # 随机选择背景图片resize到640x480src_show = copy.deepcopy(src)if args.rot:angle = np.random.randint(low=-10, high=11) / 4src = rotation(img=src, angle=angle)if args.jit:dx, dy = np.random.randint(low=-5, high=6, size=2)src = random_jitter(src, dx, dy)if args.crop:src = black_edge_crop(src, H, W)if args.hue:src = random_h(src)if args.bright:src = brightness_adjustment(src)if args.channel_change:sd = np.random.randint(low=0, high=6)src = change_channel(src, sd=sd)if args.flip:sd = np.random.randint(low=0, high=6)src = random_flip(src, sd)## begin# 随机从A图中截取部分copy至B图中# diff_img = cv2.imread(imgs[np.random.randint(0, len(imgs))])# diff_src = cv2.resize(diff_img, dsize=(H, W))# src, _ = gen_diffs(src, mask, diff_src, num_diff, H, W)## beginif args.curve:src, mask = one_curve(src, mask, H, W)if args.noise:if np.random.randint(0, 3) == 0:src = noisy(noise_typ='gauss', image=src)elif np.random.randint(0, 3) == 1:src = noisy(noise_typ='s&p', image=src)else:src = add_noise(src)if args.blur:k = np.random.randint(1, 3) * 2 + 1src = cv2.GaussianBlur(src, (k, k), 0)if args.light:src = virtual_light(src)fg = np.random.randint(0, 2)right = np.random.randint(10, 15)up = np.random.randint(10, 15)src = random_resize(src, right, up, fg)if args.time_noise:src = add_time_noise(src)if args.show_result:cv2.imshow('left is source, right is augumented', np.hstack((src_show, src)))cv2.waitKey(500)if args.save_result:cv2.imwrite(imgs[a].replace('.png', '_augumented.png'), src)if __name__ == '__main__':parser = argparse.ArgumentParser()parser.add_argument('--HW', default=[640, 640], help='height, width of image')parser.add_argument('--imgs_path', default="D:\\BUFFER\\Pycharm\\Images\\", help='path of background images')parser.add_argument('--jit', default=False, help='translation augument') # 是否进行抖动增强parser.add_argument('--rot', default=False, help='rotation augument') # 是否进行旋转增强parser.add_argument('--channel_change', default=False, help='channel augument') # 是否进行通道变化增强parser.add_argument('--crop', default=True, help='random crop') # 是否进行随机裁剪增强parser.add_argument('--hue', default=False, help='color augument') # 是否进行色调随机增强parser.add_argument('--bright', default=False, help='brightness augument') # 是否进行亮度随机增强parser.add_argument('--flip', default=False, help='random flip') # 是否进行随机翻转parser.add_argument('--light', default=False, help='virtual light') # 是否模拟光照增强parser.add_argument('--noise', default=False, help='random noise') # 是否添加随机噪声parser.add_argument('--blur', default=False, help='guass blur') # 是否添加随机模糊parser.add_argument('--curve', default=False, help='add something thin and long') # 是否训练丝状异物parser.add_argument('--time_noise', default=False, help='motion blur') # 是否模拟时间噪声parser.add_argument('--show_result', default=True, help='show result') # 是否显示结果parser.add_argument('--save_result', default= True, help='save result') # 是否保存结果args = parser.parse_args()imgs = glob.glob(args.imgs_path + '\*.png')L = len(imgs)make_datasets(args) # 结果为图像列表这篇关于python深度学习训练样本图像增强的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
