Content-based image retrieval: approaches and trends of the new age
Proceedings of the 7th ACM SIGMM international workshop on Multimedia information retrieval
Real-time computerized annotation of pictures
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
A survey of content-based image retrieval with high-level semantics
Pattern Recognition
Learning the Lie Groups of Visual Invariance
Neural Computation
Image retrieval: Ideas, influences, and trends of the new age
ACM Computing Surveys (CSUR)
Recognition of digital images of the human face at ultra low resolution via illumination spaces
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
| Hi-index | 0.00 |
Accounting for spatial image transformations is a requirement for multimedia problems such as video classification and retrieval, face/object recognition or the creation of image mosaics from video sequences. We analyze a transformation invariant metric recently proposed in the machine learning literature to measure the distance between image manifolds - the tangent distance (TD) - and show that it is closely related to alignment techniques from the motion analysis literature. Exposing these relationships results in benefits for the two domains. On one hand, it allows leveraging on the knowledge acquired in the alignment literature to build better classifiers. On the other, it provides a new interpretation of alignment techniques as one component of a decomposition that has interesting properties for the classification of video. In particular, we embed the TD into a multiresolution framework that makes it significantly less prone to local minima. The new metric - multiresolution tangent distance (MRTD) - can be easily combined with robust estimation procedures, and exhibits significantly higher invariance to image transformations than the TD and the Euclidean distance (ED). For classification, this translates into significant improvements in face recognition accuracy. For video characterization, it leads to a decomposition of image dissimilarity into "differences due to camera motion" plus "differences due to scene activity" that is useful for classification. Experimental results on a movie database indicate that the distance could be used as a basis for the extraction of semantic primitives such as action and romance.