{"id":28345970,"url":"https://github.com/iammm0/newton-ring-analyzer","last_synced_at":"2025-07-30T16:33:22.072Z","repository":{"id":293687381,"uuid":"984809003","full_name":"iammm0/newton-ring-analyzer","owner":"iammm0","description":"本项目基于 PyTorch +OpenCV 实现牛顿环图像中圆环结构的自动识别与参数提取，支持单图、多图、深度模型和传统图像处理方法组合使用。","archived":false,"fork":false,"pushed_at":"2025-05-17T05:01:23.000Z","size":10775,"stargazers_count":1,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-21T19:39:08.274Z","etag":null,"topics":["opencv","python","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/iammm0.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-05-16T14:41:26.000Z","updated_at":"2025-05-29T05:09:25.000Z","dependencies_parsed_at":"2025-05-16T16:39:41.605Z","dependency_job_id":"5b5db6ad-0de3-4d34-aab3-3067056ddfe4","html_url":"https://github.com/iammm0/newton-ring-analyzer","commit_stats":null,"previous_names":["iammm0/newton-ring-analyzer"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/iammm0/newton-ring-analyzer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iammm0%2Fnewton-ring-analyzer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iammm0%2Fnewton-ring-analyzer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iammm0%2Fnewton-ring-analyzer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iammm0%2Fnewton-ring-analyzer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iammm0","download_url":"https://codeload.github.com/iammm0/newton-ring-analyzer/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iammm0%2Fnewton-ring-analyzer/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267899108,"owners_count":24162985,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-07-30T02:00:09.044Z","response_time":70,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["opencv","python","pytorch"],"created_at":"2025-05-27T13:13:29.074Z","updated_at":"2025-07-30T16:33:22.053Z","avatar_url":"https://github.com/iammm0.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# 🧠 牛顿环识别项目说明文档\n\n本项目基于 `PyTorch` +`OpenCV` 实现牛顿环图像中圆环结构的自动识别与参数提取，支持单图、多图、深度模型和传统图像处理方法组合使用。\n\n建议：`Python` 版本：`3.11.*`\n\n---\n\n## 🎯 项目目标\n\n- 自动检测图像中的牛顿环圆结构\n- 提取有效参数（直径、圆心位置、数量）\n- 支持完整/部分/偏移牛顿环图像\n- 提供传统视觉 \u0026 深度学习双路线融合方案\n\n---\n\n\n\n## 🛠 技术路径概览\n\n| 组件         | 技术                  |\n|--------------|-----------------------|\n| 图像预处理    | OpenCV（模糊、边缘）  |\n| 掩膜生成      | 自动生成伪掩膜 / 手工 |\n| 图像分割模型  | PyTorch U-Net         |\n| 圆检测辅助    | Hough变换 + 圆心拟合  |\n| 参数提取      | `cv2.minEnclosingCircle` + 拟合优化 |\n\n进入项目根目录：\n\n```\ncd newton-ring-analyzer\n```\n\n激活虚拟环境：\n\n```\n.\\.venv\\Scripts\\activate  \n```\n\n安装所需第三方库：\n\n```bash\npip install -r requirements.txt\n```\n\n\n\n## 📁 项目结构调整建议\n\n```\nproject_root/\n├── scripts/                    # 执行脚本总目录\n│   ├── single/                 # 针对单张图像执行的脚本\n│   │   ├── main.py             # 使用模型检测\n│   │   ├── main_with_fallback.py  # 模型+OpenCV融合检测\n│   ├── batch/                  # 批量处理整个文件夹\n│   │   ├── analyze_all.py\n│   │   ├── analyze_all_with_fallback.py\n│   │   ├── analyze_processed_images.py\n│   ├── traditional/            # 仅使用传统方法（无模型）\n│   │   ├── detect_by_opencv.py\n│   ├── training/               # 训练模型脚本\n│   │   ├── train_model.py\n│   │   ├── fine_tune_model.py\n│   ├── generate/               # 数据生成脚本\n│   │   ├── generate_data.py\n│   │   ├── generate_pseudo_masks.py\n│   │   ├── preprocess_all.py\n├── analysis/                   # 参数提取逻辑\n├── model/                      # 模型结构和加载\n├── preprocessing/             # 图像预处理逻辑\n├── utils/                      # 数据集加载和合成工具\n├── data/                       # 图像数据和掩膜\n│   ├── test_images/\n│   ├── processed_images/\n│   ├── real_data/\n├── saved_model.pth\n├── fine_tuned_model.pth\n├── README.md\n```\n\n---\n\n\n\n## 🧪 执行命令索引\n\n### ✅ 使用模型检测单张图片\n\n```bash\npython scripts/single/main.py data/test_images/test1.jpg --mode newton --use_model --model_path fine_tuned_model.pth\n```\n\n### ✅ 使用模型 + OpenCV 兜底检测单张图片\n\n```bash\npython scripts/single/main_with_fallback.py data/test_images/test1.jpg --model_path fine_tuned_model.pth\n```\n\n---\n\n### 📂 批量检测整个文件夹（processed 或原图）\n\n```bash\npython scripts/batch/analyze_all.py\npython scripts/batch/analyze_processed_images.py\npython scripts/batch/analyze_all_with_fallback.py\n```\n\n---\n\n### 🧠 使用 OpenCV 圆检测法（不依赖模型）\n\n```bash\npython scripts/traditional/detect_by_opencv.py data/test_images/test1.jpg\n```\n\n---\n\n### 🧠 训练/微调模型\n\n```bash\npython scripts/training/train_model.py\npython scripts/training/fine_tune_model.py\n```\n\n---\n\n### 🛠 数据生成与预处理\n\n```bash\npython scripts/generate/generate_data.py\npython scripts/generate/preprocess_all.py\npython scripts/generate/generate_pseudo_masks.py\n```\n\n---\n\n\n\n## 🧪 训练流程相关命令索引\n\n### 📸 1. 生成合成训练数据（牛顿环图像 + 掩膜）\n\n```bash\npython scripts/generate/generate_data.py\n```\n\n输出到：\n\n```bash\ndata/images/\ndata/masks/\n```\n\n------\n\n### 🧼 2. 预处理图像（灰度/模糊/边缘）\n\n```bash\npython scripts/generate/preprocess_all.py\n```\n\n输出到：\n\n```bash\ndata/processed_images/\n```\n\n------\n\n### 🧩 3. 自动生成伪掩膜用于真实图微调训练（从 edges.png → mask）\n\n```\npython scripts/generate/generate_pseudo_masks.py\n```\n\n输出到：\n\n```bash\nreal_data/images/\nreal_data/masks/\n```\n\n------\n\n## 🧠 模型训练命令\n\n### 📌 4. 初次训练（使用合成图像）\n\n```bash\npython scripts/training/train_model.py\n```\n\n输出模型文件：\n\n```bash\nsaved_model.pth\n```\n\n------\n\n### 🔁 5. 微调训练（使用真实图伪掩膜）\n\n```bash\npython scripts/training/fine_tune_model.py\n```\n\n输出模型文件：\n\n```bash\nfine_tuned_model.pth\n```\n\n## ✅ 总结\n\n根据需求灵活选择：\n- 单图检测 vs 批量检测\n- 模型预测 vs OpenCV圆检测 vs 融合检测\n- 数据增强、掩膜伪生成、微调训练等脚本组件组合\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiammm0%2Fnewton-ring-analyzer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fiammm0%2Fnewton-ring-analyzer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiammm0%2Fnewton-ring-analyzer/lists"}