Object instance recognition using feature symbol triplets

Details Object instance recognition using feature symbol triplets Object instance recognition using feature symbol triplets

2006-01-27

2008-08-12

Holmes, Michael B (Department: 2129)

Data processing: artificial intelligence

Neural network

Learning task

Reexamination Certificate

active

07412427

ABSTRACT:
A feature symbol triplets object instance recognizer and method for recognizing specific objects in a query image. Generally, the recognizer and method find repeatable features in the image, and match the repeatable features between a query image and a set of training images. More specifically, the recognizer and method finds features in the query image and then groups all possible combinations of three features in to feature triplets. Small regions or “patches” in the query image, and an affine transformation is applied to the patches to identify any similarity between patches in a query image and training images. The affine transformation is computed using position of neighboring features in each feature triplet. Next, all similar patches are found, and then pairs of images are aligned to determine if the patches agree in the position of the object. If they do, then it is said that object is found and identified.

REFERENCES:
patent: 6262742 (2001-07-01), Tampieri
patent: 6975755 (2005-12-01), Baumberg
patent: 2005/0190949 (2005-09-01), Weber
Lee, Three Dimensional Pattern Recognition Using Feature-Based Indexing and Rule-Based Search, Graduate College University of Nevada Las Vegas, Dec. 2003.
Unsalan et al., Classifying Land Development in High Resolution Satellite Images Using Straight Line Statistics, 1051-4651/02, 2002, IEEE.
Brown, M., and Lowe, D.G., “Invariant Features from interest point groups” inBritish Machine and Vision Conference, Cardiff, Wales (2002), pp. 656-665.
Fergus, R., Perona, P., Zisserman, A., “Object class recognition by unsupervised scale-invariant learning”, inIEEE Proc. of Computer Vision and Pattern Recognition(2003), pp. 264-271.
Lamdan, Y., and Wolfson, H. J., “Geometric hashing: A general and efficient model-based recognition scheme” inProceedings of the International Conference of Computer Vision(1988), pp. 238-249.
Lowe, D.G., “Distinctive image features from scale-invariant keypoints”, inInt'l J. of Computer Vision 60(2004), pp. 91-110.
Lowe, D.G., “Local feature view clustering for 3D object recognition” inIEEE Proc. of Computer Vision and Pattern Recognition(2001), pp. 682-688.
Lowe, D.G., “Object recognition from local scale-invariant features”, inIEEE Proc. of Int'l Conf. on Computer Vision(1999), pp. 1150-1157.
Mikolajczyk, K., Schmid, C., “An affine invariant interest point detector”, inIEEE Proc. of European Conf. on Computer Vision(2002), pp. 128-142.
Mikolajczyk, K., Schmid, C., “A performance evaluation of local descriptors”, inIEEE Trans. on Pattern Recognition and Machine Intelligence, Oct. 2005 (vol. 27, No. 10), pp. 1615-1630.
Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J., “Object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints”,Int'l Journal of Computer Vision, To appear—2005, available at: http://lear.inrialpes.fr/pubs/index.php?idAuthor=108.
Schmid, C., Mohr, R., “Local gray value invariants for image retrieval”, inIEEE Trans. on Pattern Recognition and Machine Intelligence19 (1997), pp. 530-534.
Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T., “Discovering objects and their location in images”, inIEEE Proc. of Int'l Conf. on Computer Vision, Oct. 2005.
Viola, P., Jones, M., “Rapid object detection using a boosted cascade of simple features”, inProc. CVPR. (2001), pp. 511-518.
Weber, M., Welling, M., Perona, P., “Unsupervised learning of models for recognition”, inIEEE Proc. of European Conf. on Computer Vision(2000), pp. 18-32.

Affiliated with

Also associated with

Rating

Object instance recognition using feature symbol triplets does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Object instance recognition using feature symbol triplets, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Object instance recognition using feature symbol triplets will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3999607