Giter Site home page Giter Site logo

Comments (9)

mrnugget avatar mrnugget commented on July 3, 2024

So how about "Can not get new positive sample. The most possible reason is insufficient count of samples in given vec-file."? Do you have enough samples?

from opencv-haar-classifier-training.

ktkathi avatar ktkathi commented on July 3, 2024

I have
positive image : 500 sample
negative image : 500 sample
(size of file: w 200 h 100, file type: png)

and i create sample with this command :
perl bin/createsamples.pl positives.txt negatives.txt samples 500 "opencv_createsamples -bgcolor 0 -bgthresh 0 -maxxangle 1.1 -maxyangle 1.1 maxzangle 0.5 -maxidev 40 -w 200 -h 100"

after i use this command for training:
opencv_traincascade -data classifier -vec samples.vec -bg negatives.txt -numStages 15 -minHitRate 0.995 -maxFalseAlarmRate 0.5 -numPos 500 -numNeg 500 -w 200 -h 100 -mode ALL -precalcValBufSize 1024 -precalcIdxBufSize 1024 -featureType LBP

what wrong parameter that i used it?

Please advice. Thank you.

from opencv-haar-classifier-training.

mrnugget avatar mrnugget commented on July 3, 2024

I can't spot something that's obviously wrong. Are you using OpenCV 2.4.9?

from opencv-haar-classifier-training.

ktkathi avatar ktkathi commented on July 3, 2024

I try again but it's work no error. What happen? That's true?(see in picture)
capture

from opencv-haar-classifier-training.

mrnugget avatar mrnugget commented on July 3, 2024

No idea :)

On Mon, 14 Nov 2016 at 11:23, ktkathi [email protected] wrote:

I try again but it's work no error. What happen? That's true?(see in
picture)
[image: capture]
https://cloud.githubusercontent.com/assets/3676454/20261092/fb0a3f9e-aa8e-11e6-82b8-8c9a5ef384b6.PNG


You are receiving this because you commented.

Reply to this email directly, view it on GitHub
#23 (comment),
or mute the thread
https://github.com/notifications/unsubscribe-auth/ABIV5RxXDllUVfxFK9DcZQegof31o-Ydks5q-DaogaJpZM4KxHI3
.

from opencv-haar-classifier-training.

ktkathi avatar ktkathi commented on July 3, 2024

Hello Mr.Nugget
I'm Finish trained 15 stage and then i follow your description to generate xml file. After i run this command :
./facedetect --cascade="~/finished_classifier.xml"

the result is

image

is right? where finished_classifier.xml?

and i see in path opencv-haar-classifier-training-master/classifier , i found cascade.xml , params.xml and all stage.xml file. Is this true result?

What file that i use to my android application?

please advice me, Thank you so much.

from opencv-haar-classifier-training.

mrnugget avatar mrnugget commented on July 3, 2024

Use the path to casecade.xml instead of the ~/finished_classifier.xml, which is just a placeholder.

from opencv-haar-classifier-training.

ktkathi avatar ktkathi commented on July 3, 2024

Thanks a lot ;-)

from opencv-haar-classifier-training.

mrnugget avatar mrnugget commented on July 3, 2024

Glad it worked!

from opencv-haar-classifier-training.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.