#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ @Time : 2026/3/19 15:33 @File : image_precess.py @Description : """ import os from pathlib import Path import cv2 import numpy as np from matplotlib import pyplot as plt def denoise_image(binary_image: np.ndarray) -> np.ndarray: """形态学开运算去噪""" kernel = np.ones((2, 2), np.uint8) return cv2.morphologyEx(binary_image, cv2.MORPH_OPEN, kernel) def binarize_image(image: np.ndarray, method: str = 'adaptive') -> np.ndarray: """图像二值化""" if len(image.shape) == 3: gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) else: gray = image.copy() if method == 'adaptive': binary = cv2.adaptiveThreshold( gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV, 11, 2 ) elif method == 'otsu': _, binary = cv2.threshold( gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU ) else: _, binary = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY_INV) return binary def skeletonize_image(binary_image: np.ndarray) -> np.ndarray: """形态学骨架化 (迭代细化)""" size = np.size(binary_image) skel = np.zeros(binary_image.shape, np.uint8) element = cv2.getStructuringElement(cv2.MORPH_CROSS, (3, 3)) done = False temp_img = binary_image.copy() while not done: eroded = cv2.erode(temp_img, element) temp = cv2.dilate(eroded, element) temp = cv2.subtract(temp_img, temp) skel = cv2.bitwise_or(skel, temp) temp_img = eroded.copy() zeros = size - cv2.countNonZero(temp_img) if zeros == size: done = True return skel def preprocess_writer_image( image: np.ndarray, use_binarization: bool = True, use_skeleton: bool = True ) -> np.ndarray: """ 完整的图像预处理流程 Args: image: 输入图像 (RGB 或灰度) use_binarization: 是否二值化 use_skeleton: 是否骨架化 debug_path: 调试输出路径 Returns: 处理后的图像 (单通道或三通道) """ # 二值化 if use_binarization: processed = binarize_image(image, method='otsu') else: processed = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) if len(image.shape) == 3 else image.copy() # 去噪 processed = denoise_image(processed) # 骨架化 if use_skeleton: processed = skeletonize_image(processed) return processed def estimate_stroke_width_simple(binary_image, skeleton_image, k=1.5): """ 【极简版】通过面积比估算平均笔画宽度 公式:Width ≈ Area_Binary / Area_Skeleton """ # 1. 统计前景像素数量 (面积) # 假设输入是 0(背景) 和 255(前景) binary_area = cv2.countNonZero(binary_image) skeleton_area = cv2.countNonZero(skeleton_image) # 2. 防止除以零 if skeleton_area == 0: return 0.0 # 3. 计算宽度 avg_width = binary_area / skeleton_area * k return avg_width def estimate_stroke_width(image_orig, k=1.5): """ 【极简版】通过面积比估算平均笔画宽度 公式:Width ≈ Area_Binary / Area_Skeleton """ binary = binarize_image(image_orig, method='otsu') # B. 骨架化 skel = skeletonize_image(binary) # C. 计算宽度 width = estimate_stroke_width_simple(binary, skel, k) return width def resize_image(image, target_size=100): """ 预处理单张图片:保持长宽比 resize,边缘像素填充到目标大小 """ if image is None: raise ValueError("警告:无法读取图片") h, w = image.shape[:2] # 计算缩放比例(保持长宽比) scale = min(target_size / h, target_size / w) new_h = int(h * scale) new_w = int(w * scale) # Resize 图片 image_resized = cv2.resize(image, (new_w, new_h), interpolation=cv2.INTER_AREA) # 计算需要填充的像素量(居中填充) pad_top = (target_size - new_h) // 2 pad_bottom = target_size - new_h - pad_top pad_left = (target_size - new_w) // 2 pad_right = target_size - new_w - pad_left # 使用255填充 image_padded = cv2.copyMakeBorder( image_resized, pad_top, pad_bottom, pad_left, pad_right, borderType=cv2.BORDER_CONSTANT, value=(255, 255, 255), ) return image_padded def sta_polor(): # 配置路径 input_folder = "/path/to/circle_id/images/images/" output_folder = "/path/to/circle_id/outputs/width_estimate2" # 1. 创建输出目录 os.makedirs(output_folder, exist_ok=True) print(f"✅ 输出目录已确认:{output_folder}") # 2. 获取图片列表 (这里处理全部图片,如果想限制数量可以加 [:100]) # img_paths = list(Path(input_folder).glob("v2_*.png")) all_paths = list(Path(input_folder).glob("*.png")) img_paths = [p for p in all_paths if not p.name.startswith('v2_')] # img_paths = img_paths[:100] # 调试时可取消注释 print(f"🔍 找到 {len(img_paths)} 张图片,开始处理...") # --- 新增:用于统计的列表 --- all_widths = [] valid_count = 0 invalid_count = 0 count = 0 for path in img_paths: # 读取图片 (BGR) image_orig = cv2.imread(str(path)) if image_orig is None: print(f"⚠️ 无法读取图片:{path}") continue # --- 处理流程 --- binary = binarize_image(image_orig, method='adaptive') skel = skeletonize_image(binary) width = estimate_stroke_width_simple(binary, skel) # --- 数据收集 --- if width > 0: all_widths.append(width) valid_count += 1 else: invalid_count += 1 # print(f"⚠️ 无效宽度 (骨架为空): {path.name}") # --- 可视化准备 (保持原有逻辑) --- h, w = image_orig.shape[:2] image_display = image_orig.copy() text = f"W: {width:.2f}" font = cv2.FONT_HERSHEY_SIMPLEX font_scale = 0.6 thickness = 2 # cv2.putText(image_display, text, (5, 45), font, font_scale, (0, 255, 0), thickness) # cv2.putText(image_display, "Original", (15, 25), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2) # # binary_bgr = cv2.cvtColor(binary, cv2.COLOR_GRAY2BGR) # cv2.putText(binary_bgr, "Binary", (15, 25), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2) # # skel_bgr = cv2.cvtColor(skel, cv2.COLOR_GRAY2BGR) # cv2.putText(skel_bgr, "Skeleton", (15, 25), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2) # # combined_image = np.hstack([image_display, binary_bgr, skel_bgr]) # # # --- 保存结果 --- # output_path = os.path.join(output_folder, path.name) # cv2.imwrite(output_path, combined_image) count += 1 if count % 50 == 0: print(f"已处理 {count}/{len(img_paths)} 张...") print(f"\n🎉 图片处理完成!共处理 {count} 张,有效样本 {valid_count} 张,无效 {invalid_count} 张。") # ================= 统计与绘图 ================= if len(all_widths) > 0: # 1. 计算统计指标 widths_arr = np.array(all_widths) mean_w = np.mean(widths_arr) median_w = np.median(widths_arr) std_w = np.std(widths_arr) min_w = np.min(widths_arr) max_w = np.max(widths_arr) print("\n📊 笔画宽度统计报告:") print(f" 平均宽度 (Mean): {mean_w:.2f} px") print(f" 中位数 (Median): {median_w:.2f} px") print(f" 标准差 (Std): {std_w:.2f} px") print(f" 最小值 (Min): {min_w:.2f} px") print(f" 最大值 (Max): {max_w:.2f} px") # 2. 绘制直方图 plt.style.use('seaborn-v0_8-whitegrid') # 使用好看的风格 fig, ax = plt.subplots(figsize=(10, 6)) # 绘制直方图 n, bins, patches = ax.hist(all_widths, bins=50, color='#4CAF50', alpha=0.7, edgecolor='black', linewidth=0.5) # 添加统计线 ax.axvline(mean_w, color='red', linestyle='dashed', linewidth=2, label=f'Mean: {mean_w:.2f}') ax.axvline(median_w, color='blue', linestyle='solid', linewidth=2, label=f'Median: {median_w:.2f}') # 添加标题和标签 ax.set_title(f'Stroke Width Distribution (N={valid_count})', fontsize=14, fontweight='bold') ax.set_xlabel('Stroke Width (pixels)', fontsize=12) ax.set_ylabel('Frequency (Count)', fontsize=12) ax.legend() # 添加文本框显示详细统计 textstr = f'Mean: {mean_w:.2f}\nMedian: {median_w:.2f}\nStd: {std_w:.2f}\nMin: {min_w:.2f}\nMax: {max_w:.2f}' props = dict(boxstyle='round', facecolor='wheat', alpha=0.5) ax.text(0.95, 0.95, textstr, transform=ax.transAxes, fontsize=10, verticalalignment='top', horizontalalignment='right', bbox=props) # 保存图表 hist_plot_path = os.path.join(output_folder, "stroke_width_distribution_train.png") plt.savefig(hist_plot_path, dpi=150, bbox_inches='tight') print(f"\n📈 直方图已保存至:{hist_plot_path}") # 如果在本地有图形界面,可以显示;服务器后台运行则不会弹窗 # plt.show() plt.close() else: print("\n⚠️ 没有有效的宽度数据,无法绘制直方图。请检查二值化或骨架化逻辑。") print(f"\n💡 提示:所有结果已保存至 {output_folder}") # ================= 使用示例 ================= if __name__ == "__main__": path = "/path/to/circle_id/images/images/39890.png" img = cv2.imread(path) img_new = resize_image(img) write_path = "/path/to/circle_id/outputs/augment2/" + path.split("/")[-1] cv2.imwrite(write_path, img_new)