Institute of Natural and Mathematical Sciences

Permanent URI for this community

https://mro.massey.ac.nz/handle/10179/4224

Browse

Browsing Institute of Natural and Mathematical Sciences by Author "Barczak, Andre L.C."

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A color hand gesture database for evaluating and improving algorithms on hand gesture and posture recognition
    (Massey University, 2005) Dadgostar, Farhad; Barczak, Andre L.C.; Sarrafzadeh, Abdolhossein
    With the increase of research activities in vision-based hand posture and gesture recognition, new methods and algorithms are being developed. Although less attention is being paid to developing a standard platform for this purpose. Developing a database of hand gesture images is a necessary first step for standardizing the research on hand gesture recognition. For this purpose, we have developed an image database of hand posture and gesture images. The database contains hand images in different lighting conditions and collected using a digital camera. Details of the automatic segmentation and clipping of the hands are also discussed in this paper.
  • Thumbnail Image
    Item
    Real-time hand tracking using a set of cooperative classifiers based on Haar-like features
    (Massey University, 2005) Barczak, Andre L.C.; Dadgostar, Farhad
    In this paper we discuss the importance of the choice of features in digital image object recognition. The features can be classified as invariants or noninvariants. Invariant features are robust against one or more modifications such as rotations, translations, scaling and different light (illumination) conditions. Non-invariant features are usually very sensitive to any of these modifiers. On the other hand, non-invariant features can be used even in the event of translation, scaling and rotation, but the feature choice is in some cases more important than the training method. If the feature space is adequate then the training process can be straightforward and good classifiers can be obtained. In the last few years good algorithms have been developed relying on noninvariant features. In this article, we show how non-invariant features can cope with changes even though this requires additional computation at the detection phase. We also show preliminary results for a hand detector based on a set of cooperative Haar-like feature detectors. The results show the good potential of the method as well as the challenges to achieve real-time detection.