Object Detection for Markerless Augmentation using Haar Training

Shubham Paul, Sourabh Dixit, Dr.Chetna Dabas

Abstract


Computer Vision is a field that includes methods for acquiring, processing, analyzing, and understanding images and, in general, high-dimensional data from the real world in order to produce numerical or symbolic information etc[1]. As a highly scientific field, computer vision is concerned with the theory behind artificial systems that extract information from images involving image processing and object recognition. In our research we aim to explore this extensive domain of object recognition and image processing in terms of real time environment and deploy its application on various open source environments like Android. For achieving this we have incorporated a recently introduced Viola Jones, rapid object detection scheme based on a boosted cascade of simple features. For the object detection and recognition, we performed Haar Training on a set of positive and negative samples, which result in creation of Haar Cascade Classifier files in xml formats. These files are then used for detection. Post successful completion, the proposed project could also find its application in Markerless Augmented Reality as recent convergence of imaging sensors and general purpose processors on mobile phones creates an opportunity for a new class of augmented reality applications.

 

Keywords: Computer Vision, Object Recognition, Viola Jones, Android, Haar Training, Haar Cascade Classifier, Markerless Augmented Reality


Full Text:

PDF


DOI: https://doi.org/10.26483/ijarcs.v6i1.2369

Refbacks

  • There are currently no refbacks.




Copyright (c) 2016 International Journal of Advanced Research in Computer Science