Comments (3)
hi thanx for your interest.
jsfeat impl of HAAR cascades is based on an old version of trainer from OpenCV and it is compatible to stump based classifiers. Classifiers for face, hand and eye detection are already included.
from jsfeat.
Hi Eugene,
I'm also curious about how to convert an opencv haar cascade xml file into the jsfeat format. Do you have a conversion tool? I'd prefer not to retrain if possible since it takes so long. For instance my cascade looks like this
<?xml version="1.0"?>
<opencv_storage>
<cascade>
<stageType>BOOST</stageType>
<featureType>HAAR</featureType>
<height>40</height>
<width>80</width>
<stageParams>
<boostType>GAB</boostType>
<minHitRate>9.9900001287460327e-01</minHitRate>
<maxFalseAlarm>5.0000000000000000e-01</maxFalseAlarm>
<weightTrimRate>9.4999999999999996e-01</weightTrimRate>
<maxDepth>1</maxDepth>
<maxWeakCount>100</maxWeakCount></stageParams>
<featureParams>
<maxCatCount>0</maxCatCount>
<featSize>1</featSize>
<mode>ALL</mode></featureParams>
<stageNum>20</stageNum>
<stages>
<!-- stage 0 -->
<_>
<maxWeakCount>13</maxWeakCount>
<stageThreshold>-1.0350964069366455e+00</stageThreshold>
<weakClassifiers>
<_>
<internalNodes>
0 -1 85 -1.3720529153943062e-02</internalNodes>
<leafValues>
5.0184500217437744e-01 -3.8205981254577637e-01</leafValues></_>
<_>
<internalNodes>
0 -1 145 -1.1965321376919746e-02</internalNodes>
<leafValues>
-8.7071585655212402e-01 1.8524530529975891e-01</leafValues></_>
<_>
and so on down to the features
<features>
<_>
<rects>
<_>
0 0 78 40 -1.</_>
<_>
39 0 39 40 2.</_></rects>
<tilted>0</tilted></_>
Any ideas? The cascade I have was created by following this guide:
http://coding-robin.de/2013/07/22/train-your-own-opencv-haar-classifier.html
from jsfeat.
Hi,
In the same idea as the previous post, is it possible to convert haar cascade files from js-detect library for jsfeat ? If yes, could you please explain it to me ? I would like to detect nose thanks your library but the classifier doesn't exist yet.
from jsfeat.
Related Issues (20)
- Execution time static image processing vs webcam example
- An error in the docs HOT 1
- Simpler examples HOT 3
- Dose it support React Native HOT 1
- Can i use jsfeat with react-native? HOT 1
- Uncaught ReferenceError: module is not defined HOT 4
- Support for iOS 11 HOT 3
- Adding more functionalities
- Help needed!!, ORB matching - How train pattern using image from image folder instead of webcam. HOT 3
- background removal from face portrait
- Tracking a soccer ball in video HOT 1
- Demos stopped working HOT 3
- Hi Mate! There is a 404 Problem with Ur online demo. HOT 1
- demo's don't work "WebRTC not available" HOT 2
- How to transform canvas getImageData() to single channel matrix?
- Natural feature tracking/matching (NFT) in videostream
- Any details of yape06, such as paper or blog
- Pull request guidelines HOT 2
- Canny edges coordinates
- jsfeat.point2d_t is not a constructor, jsfeat.js vs jsfeat-min.js
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from jsfeat.