CascadeTrainingTool
An useful windows application as user interface to cascade classifier training using OpenCV applications.
Install / Use
/learn @hzawary/CascadeTrainingToolREADME
CascadeTrainingTool
An useful windows application as user interface to cascade classifier training using OpenCV applications.

Base program developed using Visual Studio 2015, C# .Net 4.6, compiled in x86 windows 10.
By References:
- http://note.sonots.com/SciSoftware/haartraining.html
- http://docs.opencv.org/2.4/doc/user_guide/ug_traincascade.html
- http://www.technolabsz.com/2011/08/how-to-do-opencv-haar-training.html
- http://coding-robin.de/2013/07/22/train-your-own-opencv-haar-classifier.html
- http://www.technolabsz.com/2012/07/how-to-do-opencv-haar-training-in.html
- http://www.prodigyproductionsllc.com/articles/programming/how-to-train-opencv-haar-classifiers/
Requiring before runnig the program
- Adding complied OpenCV apps in bin project directory. In this project used opencv_annotation.exe, opencv_createsamples.exe, opencv_ffmpeg300.dll, opencv_traincascade.exe, opencv_world300.dll, opencv_world300d.dll files about 18 MB (OpenCV v3.0).
- Mentioned files can be download from here.
Short keys
- Ctrl+Right and Ctrl+Left for goto next image and previous image respectively.
- Ctrl+Up and Ctrl+Down for accept image as positive and negative respectively and goto the next image.
The result program structure
- Negatives: Directory include a text file and negative images.
- Positives: Directory include a text file and positive images.
- samples.vec: Vector file from positive images.
- Cascade _ ??x??: Directory (an arbitrary name) include trained xml files from vector file and negative images.
Related Skills
node-connect
347.2kDiagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps
frontend-design
108.0kCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
openai-whisper-api
347.2kTranscribe audio via OpenAI Audio Transcriptions API (Whisper).
qqbot-media
347.2kQQBot 富媒体收发能力。使用 <qqmedia> 标签,系统根据文件扩展名自动识别类型(图片/语音/视频/文件)。
