import os import cv2 import numpy as np from pathlib import Path import random from circle_feature import exact_features from color_aug_class import ColorStatsDatabase, CircleColorAugmentor from image_precess import estimate_stroke_width import traceback DEF_PROB_DICT = {"crop": 0.3, "rotation": 0.5, "shear": 0.3, "affine": 0.5, "stroke": 0.3, "color": 0.5, "blur": 0.3 } # DEF_PROB_DICT = {"crop": 1, # "rotation": 1, # "shear": 1, # "affine": 1, # "stroke": 1, # "color": 1, # "blur": 1 # } # ================= 核心增强类 (带调试记录) ================= class CircleAugmentation: def __init__( self, color_cache_file=os.path.join(os.path.dirname(__file__), "test_color_sta.json"), prob_dict=DEF_PROB_DICT, ): # 记录每一步的图像 self.steps = {} ref_db = ColorStatsDatabase(color_cache_file) self.color_augmentor = CircleColorAugmentor(ref_db, match_std=True) self.prob_dict = prob_dict def apply_crop(self, image): """步骤 1: 随机单方向边缘裁剪 (20% 概率)""" h, w = image.shape[:2] step_name = "1_Crop" if random.random() > self.prob_dict["crop"]: # 不发生裁剪,直接返回原图副本 self.steps[step_name] = image.copy() self.steps[f"{step_name}_info"] = "No Crop" return image # 决定裁剪方向:0:Top, 1:Bottom, 2:Left, 3:Right direction = random.randint(0, 3) max_pixels = int(min(h, w) * 0.2) crop_amount = random.randint(1, max_pixels) y1, y2, x1, x2 = 0, h, 0, w if direction == 0: # Top y1 = crop_amount info = f"Top-{crop_amount}px" elif direction == 1: # Bottom y2 = h - crop_amount info = f"Bottom-{crop_amount}px" elif direction == 2: # Left x1 = crop_amount info = f"Left-{crop_amount}px" else: # Right x2 = w - crop_amount info = f"Right-{crop_amount}px" cropped = image[y1:y2, x1:x2].copy() self.steps[step_name] = cropped self.steps[f"{step_name}_info"] = info return cropped def apply_rotation(self, image, degrees=20): step_name = "rotation" if random.random() > self.prob_dict["rotation"]: # 不发生裁剪,直接返回原图副本 self.steps[step_name] = image.copy() self.steps[f"{step_name}_info"] = "No " + step_name return image """步骤 2: 随机旋转""" h, w = image.shape[:2] center = (w // 2, h // 2) angle = np.random.uniform(-degrees, degrees) M = cv2.getRotationMatrix2D(center, angle, 1.0) rotated = cv2.warpAffine(image, M, (w, h), borderMode=cv2.BORDER_CONSTANT, borderValue=(255, 255, 255), flags=cv2.INTER_LINEAR) self.steps["2_Rotate"] = rotated self.steps["2_Rotate_info"] = f"rotate:{angle:.1f}" return rotated def apply_shear(self, image, degrees=10): """步骤 3: 随机剪切""" step_name = "shear" if random.random() > self.prob_dict["shear"]: # 不发生裁剪,直接返回原图副本 self.steps[step_name] = image.copy() self.steps[f"{step_name}_info"] = "No " + step_name return image h, w = image.shape[:2] shear_x = np.random.uniform(-np.tan(np.radians(degrees)), np.tan(np.radians(degrees))) shear_y = np.random.uniform(-np.tan(np.radians(degrees)), np.tan(np.radians(degrees))) M = np.float32([[1, shear_x, 0], [shear_y, 1, 0]]) sheared = cv2.warpAffine( image, M, (w, h), borderMode=cv2.BORDER_CONSTANT, borderValue=(255, 255, 255), flags=cv2.INTER_LINEAR ) self.steps["3_Shear"] = sheared self.steps["3_Shear_info"] = f"sheer-x:{shear_x:.2f}, y:{shear_y:.2f}" return sheared def apply_affine(self, image, translate=(0.05, 0.05), scale=(0.95, 1.05)): """步骤 4: 随机平移 + 缩放""" step_name = "affine" if random.random() > self.prob_dict["affine"]: # 不发生裁剪,直接返回原图副本 self.steps[step_name] = image.copy() self.steps[f"{step_name}_info"] = "No " + step_name return image h, w = image.shape[:2] tx = np.random.uniform(-translate[0], translate[0]) * w ty = np.random.uniform(-translate[1], translate[1]) * h sx = np.random.uniform(scale[0], scale[1]) sy = np.random.uniform(scale[0], scale[1]) M = np.float32([[sx, 0, tx], [0, sy, ty]]) affine = cv2.warpAffine(image, M, (w, h), borderMode=cv2.BORDER_CONSTANT, borderValue=(255, 255, 255)) self.steps["4_Affine"] = affine self.steps["4_Affine_info"] = f"affine aug" return affine def apply_stroke_aug(self, image): """步骤 5: 外观变换 (笔迹粗细)""" if random.random() > self.prob_dict["stroke"]: self.steps["5_Stroke"] = image.copy() self.steps["5_Stroke_info"] = "No stroke aug" return image # 模拟动态逻辑 (这里简化为随机变粗或变细,实际可接入 width 估算) kernel = np.ones((3, 3), np.uint8) width = estimate_stroke_width(image) if width > 6.5: op_type = -1 # iter = random.randint(1, min(2, int((width - 3)/2))) else: op_type = 1 # iter = random.randint(1, min(2, int((7.5 - width)/2))) iter = 1 if len(image.shape) == 3: channels = cv2.split(image) new_ch = [] for ch in channels: if op_type == -1: mod = cv2.dilate(ch, kernel, iterations=iter) #白色膨胀,笔画变细 else: mod = cv2.erode(ch, kernel, iterations=iter) #白色腐蚀,笔画变粗 new_ch.append(mod) result = cv2.merge(new_ch) self.steps["5_Stroke"] = result if op_type == -1: self.steps["5_Stroke_info"] = "small:" + f"w:{width:.1f}" else: self.steps["5_Stroke_info"] = "large:" + f"w:{width:.1f}" return result def apply_color(self, image, use_prob=0.5): """步骤 5: 外观变换 (笔迹粗细)""" if random.random() > use_prob: self.steps["6_colar"] = image.copy() self.steps["6_colar_info"] = "No color aug" return image image = self.color_augmentor.augment(image, b_debug=False) self.steps["6_colar"] = image self.steps["6_colar_info"] = "color aug" return image def apply_blur(self, image): """步骤 X: 外观变换 (图像模糊)""" # 1. 概率控制:只有 use_prob (默认 30%) 的概率发生模糊 if random.random() > self.prob_dict["blur"]: self.steps["7_Blur"] = image.copy() self.steps["7_Blur_info"] = "No blur" return image ksize = random.choice([3, 5, 7]) blurred_image = cv2.GaussianBlur(image, (ksize, ksize), 0) # 4. 记录调试信息 self.steps["7_Blur"] = blurred_image self.steps["7_Blur_info"] = f"Gauss K={ksize}" return blurred_image def aug_image(self, image): """执行全流程并记录每一步""" # 0. Original self.steps["0_Original"] = image.copy() self.steps["0_Original_info"] = "Input" # 1. Crop img = self.apply_crop(image) # 2. Rotate img = self.apply_rotation(img) # 3. Shear img = self.apply_shear(img) # 4. Affine img = self.apply_affine(img) # 5. Stroke Aug img = self.apply_stroke_aug(img) # 6. color img = self.apply_color(img) # 7. blur img = self.apply_blur(img) return img def aug_image_offical(self, img): """执行全流程并记录每一步""" # 0. Original self.steps["0_Original"] = img.copy() self.steps["0_Original_info"] = "Input" # 1. Crop # img = self.apply_crop(image) # 2. Rotate img = self.apply_rotation(img) # 3. Shear # img = self.apply_shear(img) # 4. Affine img = self.apply_affine(img) # 5. Stroke Aug # img = self.apply_stroke_aug(img) # # 6. color # img = self.apply_color(img) # # 7. blur # img = self.apply_blur(img) return img def process_full_pipeline(self, image): """执行全流程并记录每一步""" # 0. Original self.steps["0_Original"] = image.copy() self.steps["0_Original_info"] = "Input" # 1. Crop img = self.apply_crop(image) # 2. Rotate img = self.apply_rotation(img) # 3. Shear img = self.apply_shear(img) # 4. Affine img = self.apply_affine(img) # 5. Stroke Aug img = self.apply_stroke_aug(img) # 6. color img = self.apply_color(img) # 7. blur img = self.apply_blur(img) return self.steps # ================= 可视化工具 ================= def create_debug_image(steps, target_h=120): """将 steps 字典中的图像拼接成一行""" row_images = [] # 定义显示顺序 order = [ "0_Original", "1_Crop", "2_Rotate", "3_Shear", "4_Affine", "5_Stroke", "6_colar", "7_Blur" ] for key in order: if key not in steps: continue img = steps[key] info = steps.get(f"{key}_info", "") # 统一高度 h, w = img.shape[:2] if h != target_h: scale = target_h / h new_w = int(w * scale) img_resized = cv2.resize(img, (new_w, target_h)) else: img_resized = img.copy() # 添加底部文字标签 cv2.putText(img_resized, info, (5, target_h - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.4, (0, 255, 0), 1) # 添加顶部标题 (简单用颜色条区分,或者只在第一张写) if key == "0_Original": cv2.putText(img_resized, "Original", (5, 15), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 2) row_images.append(img_resized) if not row_images: return None return np.hstack(row_images) # ================= 主执行逻辑 ================= def debug_main(): INPUT_FOLDER = "/path/to/circle_id/images/images/" OUTPUT_FOLDER = "/path/to/circle_id/outputs/augment2" FILE_PATTERN = "*.png" # 或者 "*.png" 处理所有 NUM_SAMPLES = 100 # 调试几张图片 os.makedirs(OUTPUT_FOLDER, exist_ok=True) print(f"✅ 输出目录:{OUTPUT_FOLDER}") img_paths = list(Path(INPUT_FOLDER).glob(FILE_PATTERN))[:NUM_SAMPLES] print(f"🔍 找到 {len(img_paths)} 张图片,开始生成调试图...") aug = CircleAugmentation() for idx, path in enumerate(img_paths): # path = "/path/to/circle_id/images/images/10542.png" # path = "/path/to/circle_id/images/images/14406.png" # path = "/path/to/circle_id/images/images/21070.png" # path = "/path/to/circle_id/images/images/30164.png" # # path = "/path/to/circle_id/images/images/38334.png" # path = "/path/to/circle_id/images/images/39022.png" path = "/path/to/circle_id/images/images/39890.png" path_name = path.split("/")[-1] # path_name = path.name image = cv2.imread(str(path)) if image is None: continue all_rows = [] # 初始化增强器 (每次循环重新初始化以重置随机状态记录) # 执行流程 steps = aug.process_full_pipeline(image) # 生成拼接图 row_imgs = create_debug_image(steps, target_h=150) if row_imgs is not None: # 添加左侧文件名标签 h, w, _ = row_imgs.shape label_img = np.ones((h, 150, 3), dtype=np.uint8) * 255 cv2.putText(label_img, path_name, (10, h // 2), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 1) final_row = np.hstack([label_img, row_imgs]) all_rows.append(final_row) # 垂直拼接所有行 # 确保宽度一致 (取最小宽度) min_w = min([r.shape[1] for r in all_rows]) padded_rows = [] for r in all_rows: if r.shape[1] > min_w: r = r[:, :min_w, :] padded_rows.append(r) final_grid = np.vstack(padded_rows) image_name = str(path).split("/")[-1] output_path = os.path.join(OUTPUT_FOLDER, f"{idx}_{image_name}") try: feature = exact_features(steps["7_Blur"]) except Exception as e: print(steps["7_Blur"].shape) cv2.imwrite(output_path, final_grid) print(f"\n🎉 错误调试图已保存:{output_path}") print(str(path)) print(traceback.format_exc()) if __name__ == "__main__": debug_main() # src_path = "/path/to/circle_id/images/images/00151.png" # img = cv2.imread(src_path) # aug = CircleAugmentation() # img_aug = aug.aug_image(img) # cv2.imwrite("/path/to/circle_id/outputs/polar_order/temp/00151.png", img_aug) # feature = exact_features(img_aug)