Giter VIP home page Giter VIP logo

viola-jones's Introduction

Viola-Jones Detection Framework

This is an implement of Viola-Jones Detection Framework and is used in human face detection.

Requirements

This implement of Viola-Jones Framework require python version 3.5.2, and depends on the following modules:

module version comment
numpy 1.13.3
scipy 1.0.0
opencv-python 3.4.0.14 for capturing image
scikit-learn 0.19.1 for shuffling data

Usage

Run the following command to begin face detection:

python detect.py

Main Concepts

Haar-like Features

Haar-like features are proposed by Viola and Jones, adapting the idea (from Papageoriou et al) of using Haar wavelets.

Haar-like Features proposed by Viola and Jones

In this implement, five types of Haar-like features are used. They are: left-right, top-bottom, horizontal-middle, vertical-middle, diagonal.

Haar-like Features in this implement

Integral Image

To speed up features extraction process, an intermediate representation for the image called integral image is used.

Integral Image

AdaBoost

AdaBoost is short for Adaptive Boosting, which is a kind of method of ensemble learning.

For more info about AdaBoost, refers to GitHub - Donny-Hikari/AdaBoost

BoostedCascade

To speed up detection process, as well as to decrease the false positive rate while sustaining a high detection rate (i.e. to improve precision), Viola and Jones invent the boosted cascade. That is, to cascade multiple AdaBoost classifiers.

The Attentional Cascade

References

  1. Yoav Freund; Robert E. Schapire. AT&T Labs โ€“ Research, Shannon Laboratory. Journal of Japanese Society for Artificial Intelligence,14(5):771-780, September 1999. A Short Introduction to Boosting.

  2. Paul Viola; Michael J. Jones. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, May 2004. Rapid Object Detection Using a Boosted Cascade of Simple Features.

  3. Paul Viola; Michael J. Jones. International Journal of Computer Vision 57(2), 137โ€“154, 2004. Robust Real-Time Face Detection.

Author

Donny Hikari
Donny Hikari

viola-jones's People

Contributors

donny-hikari avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

viola-jones's Issues

How to get modelfile?

So i tried train.py and done generatingfeature. I have problem when try to load modelfile. the modelfile and feature is not the same so how to process the feature and get the modelfile?

how to use

excuse me sir,
can you tell me how to use your code?
where can i start? im trying to train my face dataset, but I got many error.

Training part was done successfully but am facing some issue in detect part.

File "/Users/Apple/Downloads/Self-driving-Car-master/ViolaJonesFaceDetection/Viola-Jones-master/boostedcascade/boostedcascade.py", line 539, in loadModel
Ftarget, f, d, validset_rate, CIsteps, detectWndH, detectWndW, features_cnt = np.load(filename+'-variables.npy')
ValueError: need more than 3 values to unpack

My -variables.npy looks like this:
cat Model/-variables.npy
?NUMPYv{'descr': '<i8', 'fortran_order': False, 'shape': (3,), }
??

modelfile and dataset

excuse me, sir
i would like to know abaout your database and your modelfile, can you give me your modelfile or your data training that you use?

please.
thank you. sorry if i disturb you

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.