Stack Overflow
Stack Overflow

Questions tagged [viola-jones]

The Viola–Jones object detection framework is the first object detection framework to provide competitive object detection rates in real-time proposed in 2001 by Paul Viola and Michael Jones.

87 questions
85
votes
6 answers

Viola-Jones' face detection claims 180k features

I've been implementing an adaptation of Viola-Jones' face detection algorithm. The technique relies upon placing a subframe of 24x24 pixels within an image, and subsequently placing rectangular features inside it in every position with every size…
Paul Lammertsma
  • 35,234
  • 14
  • 128
  • 182
58
votes
5 answers

Haar Cascades vs. LBP Cascades in Face Detection

I have been experimenting with face detection in OpenCV (Open Source Computer Vision Library), and found that one could use Haar cascades to detect faces as there are several of them provided with OpenCV. However, I have noticed that there are also…
Bojoeb
  • 603
  • 1
  • 6
  • 6
22
votes
2 answers

How does the Viola-Jones face detection method work?

Please explain to me, in few words, how the Viola-Jones face detection method works.
BlackShadow
  • 1,017
  • 5
  • 19
  • 25
12
votes
2 answers

Getting the confidence level of detectMultiscale in OpenCV with Python?

I'm using a trained opencv cascade classifier to detect hands in video frames, and would like to lower my false positive rate. Reading up on the net, I saw you can do so by accessing the rejectLevels and levelWeights information returned by the…
RonenKi
  • 338
  • 3
  • 11
9
votes
1 answer

The best way to calculate the best threshold with P. Viola, M. Jones Framework

I'm trying to implement P. Viola and M. Jones detection framework in C++ (at the beginning, simply sequence classifier - not cascaded version). I think I have designed all required class and modules (e.g Integral images, Haar features), despite one…
Viper
  • 577
  • 1
  • 7
  • 22
6
votes
1 answer

Viola Jones face detection - variations in object/face size

I'm trying to understand Viola Jones method, and I've mostly got it. It uses simple Haar like features boosted into strong classifiers and organized into layers /cascade in order to accomplish better performances (not bother with obvious 'non…
daneejela
  • 8,695
  • 6
  • 29
  • 40
5
votes
1 answer

How Viola Jones With AdaBoost Algorithm Work in Face Detection?

I've read a lot about Viola Jones method but i still not understand about "Weak Classifier", "Strong Classifier", "Sub Window" in Rectangle features, what is definition about them. And what about "threshold"? How i can know the threshold value? Can…
pacifistazero
  • 79
  • 2
  • 5
4
votes
1 answer

adaboost update weights beta value

Viola-Jones face detection used the adaboost method to train strong classifier. I am confused with the beta param update policy: Why choose beta value like this? The purpose of setting the variable beta is to increase the weight of the Weights. How…
tidy
  • 3,887
  • 5
  • 36
  • 74
4
votes
1 answer

Viola jones weak classifier explanation

I have been trying to understand the paper by viola n jones on face detection. I am not totally sure what this equation's parameters mean from section 3 h(x, f, p, theta) = 1 ; if pf(x) < p theta What I understood was feature (f) is the value that…
Sgt. Pepper
  • 177
  • 11
4
votes
0 answers

Face detection using Viola and Jones approach

I am currently working on face detection using viola and jones approach. I think I am a making some silly assumptions which end up with classifiers of 100% FALSE negative rate and 0% true positive rate. Here is how i generated my training…
Ojo Akintade Samson
  • 55
  • 4
3
votes
1 answer

Number of haar like features in 24x24 window

Referring to the following link Viola & Jones Face Detection The above link contains the calculation regarding the number of haar features corresponding to different templates(below is excerpt from the link). I am not getting how…
Naseer
  • 3,147
  • 5
  • 31
  • 61
3
votes
1 answer

Viola Jones threshold value Haar features error value

I have read the viola paper from 2004. In 3.1 they explain the threshold calculation. But I am super confused. It reads as For each feature, the examples are sorted based on feature value Question1) Is sorted list a list of haar feature values…
Evren Bingøl
  • 1,167
  • 1
  • 16
  • 29
3
votes
1 answer

What is the minimum size object I can detect using OpenCV train_cascade?

I'm in the process of creating a classifier for an electrical outlet (specifically the three open holes that occur twice on standard outlet panels, not the entire panel itself). My question is, what are the ideal traits of positive images and what…
JohnAllen
  • 6,426
  • 9
  • 36
  • 60
3
votes
1 answer

OpenCV Haar Classifier Killed

I am trying to train a Haar Classifier however during Stage 2 it stops with the message Killed PARAMETERS: cascadeDirName: classifier vecFileName: samples.vec bgFileName: negatives.txt numPos: 500 numNeg: 964 numStages: 10 precalcValBufSize[Mb] :…
Colin747
  • 4,695
  • 15
  • 64
  • 108
3
votes
2 answers

how to specify the threshold of weak classifier for adaboost method of face detector

I have read Rapid Object Detection using a Boosted Cascade of Simple Features. In part 3, it defines a weak classifier like this: My question is: how to specify the threshold theta_j? And for strong classfier, my question is like this:
tidy
  • 3,887
  • 5
  • 36
  • 74
1
2 3 4 5 6