Ask Your Question

How different is Open CV train cascading from IBM Visual Recognition [closed]

asked 2016-04-11 14:30:03 -0500

Indira gravatar image

How different is Open CV train cascading from IBM Visual Recognition ? Is IBM visual recognition using open CV internally? . IBM is providing a service to get the classifier. i could see that it gives only score and the object name.But does it give the annotation of the object where it is located ? For my requirement i need to identify and annotate (location) the object of interest in a video. So i want to understand the differences between these two and need to decide which is best way to go with whether to create our own trained classifier xml or to use IBM service for it.

edit retag flag offensive reopen merge delete

Closed for the following reason the question is answered, right answer was accepted by Indira
close date 2016-05-25 15:32:35.164404


In my opinion, IBM Visual Recognition is better as it is part of Watson environment and it uses convolutional neural networks (state of the art method in computer vision wheras OpenCV cascade classifier is a pretty old method):

Convolutional neural networks are used as semantic classifiers that recognize many visual entities such as settings, objects, and events

Also, they offer the service (after some money of course) and the training is made on their side whereas with OpenCV you will have to do it on your computer and the training process is very time consuming especially for Haar cascade classifier.

Eduardo gravatar imageEduardo ( 2016-04-12 04:21:57 -0500 )edit

1 answer

Sort by ยป oldest newest most voted

answered 2016-04-12 09:00:35 -0500

berak gravatar image

Cascade classifiers detect a single object class, IBM's Visual Recognition is a scene recognition service. 2 different pair of shoes.

edit flag offensive delete link more


Like @berak said, people are always mixing up object detection and object/scene recognition, which are basically two complete different fields of research.

StevenPuttemans gravatar imageStevenPuttemans ( 2016-04-13 04:50:37 -0500 )edit

I'm new to this area.Could you just brief me about the difference between object and scene recognition.i was thinking that we train the classifier and use that to detect object interest in a image/video. when I saw the same kind implementation in https://visual-recognition-demo.myblu... i got this doubt. please brief the difference between these two.

Indira gravatar imageIndira ( 2016-04-13 14:23:54 -0500 )edit

Question Tools

1 follower


Asked: 2016-04-11 14:30:03 -0500

Seen: 83 times

Last updated: Apr 11 '16