Beruflich Dokumente
Kultur Dokumente
Idea:
find bits, then say object is present if bits are ok
Advantage:
objects with complex configuration spaces dont make good templates internal degrees of freedom aspect changes (possibly) shading variations in texture etc.
Computer Vision - A
Simplest
Define a set of local feature templates
could find these with filters, etc. corner detector+filters
Think of objects as patterns Each template votes for all patterns that contain it Pattern with the most votes wins
Computer Vision - A
Figure from Local grayvalue invariants for image retrieval, by C. Schmid and R. Mohr, IEEE Trans. Pattern Analysis and Machine Intelligence, 1997 copyright 1997, IEEE
Computer Vision - A
Probabilistic interpretation
Write
Assume
Computer Vision - A
Computer Vision - A
Figure from Local grayvalue invariants for image retrieval, by C. Schmid and R. Mohr, IEEE Trans. Pattern Analysis and Machine Intelligence, 1997 copyright 1997, IEEE
Computer Vision - A
Figure from Local grayvalue invariants for image retrieval, by C. Schmid and R. Mohr, IEEE Trans. Pattern Analysis and Machine Intelligence, 1997 copyright 1997, IEEE
Computer Vision - A
Computer Vision - A
Notice that once some facial features have been found, the position of the rest is quite strongly constrained.
Figure from, Finding faces in cluttered scenes using random labelled graph matching, by Leung, T. ;Burl, M and Perona, P., Proc. Int. Conf. on Computer Vision, 1995 copyright 1995, IEEE
Computer Vision - A
Detection
Computer Vision - A
Issues
Plugging in values for position of nose, eyes, etc.
search for next one given what weve found when to stop searching when nothing that is added to the group could change the decision i.e. its not a face, whatever features are added or its a face, and anything you cant find is occluded what to do next look for another eye? or a nose? probably look for the easiest to find
Computer Vision - A
Figure from, Finding faces in cluttered scenes using random labelled graph matching, by Leung, T. ;Burl, M and Perona, P., Proc. Int. Conf. on Computer Vision, 1995 copyright 1995, IEEE
Computer Vision - A
Pruning
Prune using a classifier
crude criterion: if this small assembly doesnt work, there is no need to build on it.
Computer Vision - A
Pruning
Prune using a classifier
better criterion: if there is nothing that can be added to this assembly to make it acceptable, stop equivalent to projecting classifier boundaries.
Computer Vision - A
Horses
Computer Vision - A
Computer Vision - A
Now in each state we could emit a measurement, with probability depending on the state and the measurement We observe these measurements
Computer Vision - A
HMMs - dynamics
Computer Vision - A
Computer Vision - A
Trellises
Each column corresponds to a measurement in the sequence Trellis makes the collection of legal paths obvious Now we would like to get the path with the largest negative log-posterior Trellis makes this easy, as follows.
Computer Vision - A
Computer Vision - A
Fitting an HMM
I have:
sequence of measurements collection of states topology
I want
state transition probabilities measurement emission probabilities
Straightforward application of EM
discrete vars give state for each measurement M step is just averaging, etc.
Computer Vision - A
Computer Vision - A
Computer Vision - A
For both isolated word recognition tasks and for recognition using a language model that has five word sentences (words always appearing in the order pronoun verb noun adjective pronoun), Starner and Pentlands displays a word accuracy of the order of 90%. Values are slightly larger or smaller, depending on the features and the task, etc.
User gesturing
Figure from Real time American sign language recognition using desk and wearable computer based video, T. Starner, et al. Proc. Int. Symp. on Computer Vision, 1995, copyright 1995, IEEE
Computer Vision - A
HMMs can be spatial rather than temporal; for example, we have a simple model where the position of the arm depends on the position of the torso, and the position of the leg depends on the position of the torso. We can build a trellis, where each node represents correspondence between an image token and a body part, and do DP on this trellis.
Computer Vision - A
Computer Vision - A
Figure from Efficient Matching of Pictorial Structures, P. Felzenszwalb and D.P. Huttenlocher, Proc. Computer Vision and Pattern Recognition2000, copyright 2000, IEEE
Computer Vision - A
Computer Vision - A
Computer Vision - A
Computer Vision - A