import cv2 import numpy as np import os import random import matplotlib.pyplot as plt import pickle import json from tqdm import tqdm # ================= 辅助函数 (二值化与骨架化) ================= def binarize_image(image: np.ndarray, method: str = 'adaptive', k=1) -> np.ndarray: """ k=2,默认 k=0,含有更多边缘 """ if len(image.shape) == 3: gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) else: gray = image.copy() if method == 'adaptive': # 优化参数以保留更多细节 return cv2.adaptiveThreshold( gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV, 15, k ) elif method == 'otsu': _, binary = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU) return binary else: _, binary = cv2.threshold(gray, 100, 255, cv2.THRESH_BINARY_INV) return binary def create_hard_mask(img): """生成硬二值Mask (0或255),用于确定变换区域""" if len(img.shape) == 3: gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) else: gray = img blur = cv2.GaussianBlur(gray, (5, 5), 0) ret, mask = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU) kernel = np.ones((3, 3), np.uint8) mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel, iterations=1) mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, kernel, iterations=2) if cv2.countNonZero(mask) / mask.size < 0.01: _, mask = cv2.threshold(blur, 200, 255, cv2.THRESH_BINARY_INV) mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, kernel, iterations=2) # kernel = np.ones((3, 3), np.uint8) # mask = cv2.erode(mask, kernel, iterations=2) return mask class ColorStatsDatabase: """ 负责预计算、保存和加载参考图像库的统计信息。 针对白底黑字场景,仅计算'前景区域'的均值和方差。 """ def __init__(self, cache_file='test_color_sta.json'): # 缓存文件保存在参考文件夹的父目录或当前目录,避免污染图片文件夹 self.cache_file = cache_file self.stats_data = {} self.file_list = [] if os.path.exists(self.cache_file): self.load() else: raise ValueError("输入正确的资源文件路径") def compute_and_save(self, folder_path): self.folder_path = folder_path """遍历文件夹,计算统计量并保存到磁盘""" print(f"正在扫描并计算参考库统计量: {self.folder_path} ...") valid_ext = ('.jpg', '.jpeg', '.png') files = [f for f in os.listdir(self.folder_path) if f.lower().endswith(valid_ext) and f.startswith('v2_')] if not files: raise ValueError(f"文件夹中未找到图像: {self.folder_path}") self.stats_data = {} for filename in tqdm(files, desc="计算统计量"): filepath = os.path.join(self.folder_path, filename) img = cv2.imread(filepath) if img is None: continue mask = create_hard_mask(img) mask_bool = mask > 0 if np.sum(mask_bool) < 10: continue # 跳过无前景的图 means = [] stds = [] # 分别计算 B, G, R 通道的前景统计量 for i in range(3): channel = img[:, :, i] pixels = channel[mask_bool].astype(np.float64) means.append(float(np.mean(pixels))) stds.append(float(np.std(pixels))) self.stats_data[filename] = { 'mean': means, 'std': stds } with open(self.cache_file, 'w') as f: json.dump(self.stats_data, f, indent=2) print(f"统计量已保存至: {self.cache_file}") print(f"共处理有效图像: {len(self.stats_data)} 张") self.file_list = list(self.stats_data.keys()) def load(self): """从磁盘加载统计量""" if not os.path.exists(self.cache_file): print(f"缓存文件不存在: {self.cache_file},将重新计算...") self.compute_and_save() else: print(f"正在加载缓存统计量: {self.cache_file}") with open(self.cache_file, 'r') as f: self.stats_data = json.load(f) self.file_list = list(self.stats_data.keys()) print(f"加载完成,共 {len(self.stats_data)} 张图像统计量。") def get_random_stats(self): """随机返回一组统计量 (filename, mean, std)""" if not self.file_list: raise ValueError("数据库为空") fname = random.choice(self.file_list) data = self.stats_data[fname] return fname, data['mean'], data['std'] class CircleColorAugmentor: """ 颜色增强类:利用预计算的统计量对源图像进行硬变换(无边缘融合)。 """ def __init__(self, ref_stats_db: ColorStatsDatabase, match_std=True): self.ref_db = ref_stats_db self.match_std = match_std def augment(self, src_img, b_debug=False): """ 执行一次增强: 1. 读取源图 2. 随机选择一组参考统计量 3. 生成源图硬Mask 4. 计算源图前景统计量 5. 应用线性变换并直接替换前景像素 """ # src_img = cv2.imread(src_img_path) # channels = cv2.split(src_img) # kernel = np.ones((3, 3), np.uint8) # new_ch = [] # for ch in channels: # mod = cv2.erode(ch, kernel, iterations=2) # new_ch.append(mod) # src_img = cv2.merge(new_ch) # 1. 获取随机参考统计量 (从内存缓存读取,极速) ref_fname, ref_means, ref_stds = self.ref_db.get_random_stats() # 2. 生成源图的硬 Mask (必须实时生成) hard_mask = create_hard_mask(src_img) mask_bool = hard_mask > 0 if np.sum(mask_bool) < 10: # 没检测到前景,直接返回原图和空mask if b_debug is True: return src_img, src_img.copy(), np.zeros_like(hard_mask), "No_Foreground" else: return src_img # 3. 计算源图当前前景的统计量 src_means = [] src_stds = [] for i in range(3): channel = src_img[:, :, i] pixels = channel[mask_bool].astype(np.float64) src_means.append(np.mean(pixels)) src_stds.append(np.std(pixels)) # 4. 应用变换 (直接替换,无融合) result_img = src_img.copy().astype(np.float64) for i in range(3): s_chan = src_img[:, :, i].astype(np.float64) m_s, s_s = src_means[i], src_stds[i] m_r, s_r = ref_means[i], ref_stds[i] # 提取前景像素 src_vals = s_chan[mask_bool] # 计算新值 if s_s < 1e-5: new_vals = np.full_like(src_vals, m_r) else: if self.match_std: # 匹配均值和方差 new_vals = (src_vals - m_s) * (s_r / s_s) + m_r else: # 仅匹配均值 new_vals = src_vals - m_s + m_r # 截断 new_vals = np.clip(new_vals, 0, 255) # 【关键】直接赋值给结果图像的 Mask 区域,背景保持不变 result_img[:, :, i][mask_bool] = new_vals result_img = np.clip(result_img, 0, 255).astype(np.uint8) # channels = cv2.split(result_img) # new_ch = [] # for ch in channels: # mod = cv2.dilate(ch, kernel, iterations=2) # new_ch.append(mod) # result_img = cv2.merge(new_ch) # result_img = cv2.GaussianBlur(result_img, (5, 5), 0) if b_debug is True: return src_img, result_img, hard_mask, ref_fname else: return result_img def visualize_results(src_img, tgt_img, hard_mask, ref_path, save_path): """生成对比图:源图 | 结果图 | 硬Mask | 参考信息""" src_rgb = cv2.cvtColor(src_img, cv2.COLOR_BGR2RGB) tgt_rgb = cv2.cvtColor(tgt_img, cv2.COLOR_BGR2RGB) # 硬Mask 可视化 mask_vis = hard_mask.astype(np.uint8) mask_rgb = cv2.cvtColor(mask_vis, cv2.COLOR_GRAY2RGB) fig, axes = plt.subplots(1, 4, figsize=(20, 5)) axes[0].imshow(src_rgb) axes[0].set_title("Source Image", fontsize=14, fontweight='bold') axes[0].axis('off') axes[1].imshow(tgt_rgb) axes[1].set_title(f"Target (Hard Transform)", fontsize=14, fontweight='bold') axes[1].axis('off') axes[2].imshow(mask_rgb) axes[2].set_title("Foreground Mask (Binary)", fontsize=14, fontweight='bold') axes[2].axis('off') # 第四列显示参考信息 ref_rgb = cv2.imread(ref_path) axes[3].imshow(ref_rgb) axes[3].set_title(f"Reference") axes[3].axis('off') plt.tight_layout() plt.savefig(save_path, dpi=150, bbox_inches='tight') plt.close(fig) def debug(): # ================= 配置区域 ================= path_src_folder = "/path/to/circle_id/images/ours_images" path_ref_folder = "/path/to/circle_id/images/images/" path_out_folder = "/path/to/circle_id/outputs/color_aug_hard_class_new" cache_file = os.path.join(os.path.dirname(__file__), "test_color_sta.json") ref_db = ColorStatsDatabase(cache_file) # test_color_sta.compute_and_save('/path/to/circle_id/images') MATCH_STANDARD_DEVIATION = False # 是否匹配方差 NUM_SAMPLES = 100 # 生成测试图数量 # =========================================== os.makedirs(path_out_folder, exist_ok=True) # 2. 初始化增强器 augmentor = CircleColorAugmentor(ref_db, match_std=MATCH_STANDARD_DEVIATION) # 3. 获取源图像列表 valid_ext = ('.jpg', '.jpeg', '.png') src_files = [f for f in os.listdir(path_src_folder) if f.lower().endswith(valid_ext)] if not src_files: print("源文件夹为空") return print(f"\n开始生成 {NUM_SAMPLES} 张增强图像 (硬变换模式)...\n") for idx in range(NUM_SAMPLES): src_fname = random.choice(src_files) src_path = os.path.join(path_src_folder, src_fname) try: src_img, tgt_img, hard_mask, ref_used = augmentor.augment(src_path, b_debug=True) if ref_used == "No_Foreground": print(f"[{idx + 1}/{NUM_SAMPLES}] 跳过 (未检测到前景): {src_fname}") continue # 保存结果 out_name = f"aug_{idx:03d}_{os.path.splitext(src_fname)[0]}_ref_{os.path.splitext(ref_used)[0]}.jpg" save_path = os.path.join(path_out_folder, out_name) ref_used = path_ref_folder + ref_used visualize_results(src_img, tgt_img, hard_mask, ref_used, save_path) print(f"[{idx + 1}/{NUM_SAMPLES}] 完成: {out_name}") except Exception as e: print(f"[{idx + 1}/{NUM_SAMPLES}] 失败: {e}") import traceback traceback.print_exc() print("\n所有任务完成!结果已保存。") def main(): cache_file = os.path.join(os.path.dirname(__file__), "test_color_sta.json") ref_db = ColorStatsDatabase(cache_file) augmentor = CircleColorAugmentor(ref_db, match_std=True) src_path = "/path/to/circle_id/images/ours_images/W103_17_circle_010.png" tgt_img = augmentor.augment(src_path, b_debug=False) cv2.imwrite("/path/to/circle_id/outputs/tgt.png", tgt_img) if __name__ == "__main__": # main() debug()