Hi All, before posting your question, please look at this FAQ carefully! Also you can read OpenCV haartraining article.  If you are sure, there is no answer to your question, feel free to post comment.  Also please, put comments about improvement of this post.  This post will be updated, if needed.

In OpenCV/Samples there is  facedetect program.  This program can detect  faces on images and video.  It’s very fun, but its speed leaves much to be desired =(.  Of course  with OpenMP,  it works  faster; on Intel Core Duo 2.7GHZ, it works fast;  but will it work fast on ARM? I have big doubts.  I compiled facedetect without OpenMP and on average it takes 600 ms for 640×480 resolution to find one face.   I wanted to find out, if it’s possible to improve this time by software means or not…  After some investigations, code refactoring and improvements, facedetect started to work 2.5 time faster, even on ARM.  Of course, without big quality loss =)

If you want to generate cascade with OpenCV training tools, you should be ready for waiting plenty of time. For example, on training set: 3000 positive / 5000 negative, it takes about 6 days! to get cascade for face detection.  I wanted to generate many cascades with different training sets, also I added my own features to standart OpenCV’s ones  and refactor algorithms a little bit.  So waiting for 6 days to understand, that your cascade does nothing good =) was really anoying.  To reduce time, I chose paralleling methods.

OpenCV’s standart cascades allow to detect faces and eyes.  I wanted to create cascade in similar way to detect another objects:  pringles or plate for example.  I found some material in Net how to use OpenCV training tools, also I investigated training tool’s source  code myself  to found out, what training parameters can be tuned.

Prepare images.

For training, I needed thousands of images, containing my object with different lightning conditions and perspectives. After trying to find required number of pictures with Google ,  I understood, that it’s really difficult task =).  So I decided to take video with my object,  then I wrote simple program to crop object from video, frame by frame.  In such way,  I generated about 3000 positive samples (cropped images  with my object).  Resolution varied from 50×50 to 100×100.  The advantage of this method – you  get many samples with different reflections, illuminations and backgrounds.  It’s very important, that all these images “features” are various!

Today’s story is about improving performance of OpenCV library on the ARM-based platforms.

As you already know (from here or from here or may be even from here), face detection algorithm implemented by OpenCV library doesn’t work perfectly on ARM processors. Science doesn’t know for certain why this happens. There might be several possible reasons. One of our assumption was missing of hardware support for floating point operations. So we tried to translate Viola-Jones algorithm from floating point to fixed point. And that’s how we did this…