The Beauty of Local Invariant Features Svetlana Lazebnik
The Beauty of Local Invariant Features Svetlana Lazebnik Beckman Institute, University of Illinois at Urbana-Champaign IMA Recognition Workshop University of Minnesota May 22, 2006
What are Local Invariant Features? • Descriptors of image patches that are invariant to certain classes of geometric and photometric transformations Lowe (2004)
A Historical Perspective Model-based methods: local shape, no appearance information ACRONYM: Brooks and Binford (1981) Alignment: Huttenlocher & Ullman (1987) Invariants: Rothwell et al. (1992) Appearance-based methods: global appearance, no local shape Eigenfaces: Turk & Pentland (1991) Appearance manifolds: Murase & Nayar (1995) Color histograms: Swain & Ballard (1990) Local invariant features: local shape + appearance pattern +
Feature Detection and Description 1. Detect regions 2. Normalize regions 3. Compute appearance descriptors SIFT: Lowe (2004) covariant detection invariant description
Advantages • Locality – Robustness to clutter and occlusion • Repeatability – The same feature occurs in multiple images of the same scene or class • Distinctiveness – Salient appearance pattern that provides strong matching constraints • Invariance – Allow matching despite scale changes, rotations, viewpoint changes • Sparseness – Relatively few features per image, compact and efficient representation • Flexibility – Many existing types of detectors, descriptors
Scale-Covariant Detectors • Laplacian, Hessian, Difference-of-Gaussian (blobs) Lindeberg (1998), Lowe (1999, 2004) • Harris-Laplace (corners) Mikolajczyk & Schmid (2001)
Scale-Covariant Detectors • Salient (high entropy) regions • Circular edge-based regions Kadir & Brady (2001) Jurie & Schmid (2003)
Affine-Covariant Detectors • Laplacian, Hessian-Affine (blobs) Gårding & Lindeberg (1996), Mikolajczyk et al. (2004) • Harris-Affine (corners) Mikolajczyk & Schmid (2002)
Affine-Covariant Detectors • Edge- and intensity-based regions Tuytelaars & Van Gool (2004) • Maximally stable extremal regions (MSER) Matas et al. (2002)
Types of Descriptors • Differential invariants Koenderink & Van Doorn (1987), Florack et al. (1991) • Filter banks: complex, Gabor, steerable, … • Multidimensional histograms Johnson & Hebert (1999) Lazebnik, Schmid & Ponce (2003) Belongie, Malik & Puzicha (2002) Lowe (1999, 2004) PCA-SIFT: Ke & Sukthankar (2004) GLOH: Mikolajczyk & Schmid (2004)
Applications (1) • Wide-baseline matching and recognition of specific objects Tuytelaars & Van Gool (2004) Lowe (2004) Ferrari, Tuytelaars & Van Gool (2005) Rothganger, Lazebnik, Schmid & Ponce (2005)
Applications (2) • Category-level recognition based on geometric correspondence Lazebnik, Schmid & Ponce (2004) Berg, Berg & Malik (2005)
Applications (3) • Learning parts and visual vocabularies Constellation model Fergus, Perona & Zisserman (2003) Weber, Welling & Perona (2000) Bag of features Csurka, Dance, Fan, Willamowski & Bray (2004) Dorko & Schmid (2005) Sivic, Russell, Efros, Zisserman & Freeman (2005) Sivic & Zisserman (2003)
Applications (4) • Building global image models invariant to a wide range of deformations Lazebnik, Schmid & Ponce (2005)
Comparative Evaluations • Flat scenes Mikolajczyk & Schmid (2004), Mikolajczyk et al. (2004) – MSER and Hessian regions have the highest repeatability – Harris and Hessian regions provide the most correspondences – SIFT (GLOH, PCA-SIFT) descriptors have the highest performance • 3 D objects Moreels & Perona (2006) – Features on 3 D objects are much more unstable than on planar objects – All detectors and descriptors perform poorly for viewpoint changes > 30° – Hessian with SIFT or shape context perform best
Comparative Evaluations • Object classes Mikolajczyk, Liebe & Schiele (2005) – Hessian regions with GLOH perform best – Salient regions work well for object classes • Texture and object classes Zhang, Marszalek, Lazebnik & Schmid (2005) – Laplacian regions with SIFT perform best – Combining multiple detectors and descriptors improves performance – Scale+rotation invariance is sufficient for most datasets
Sparse vs. Dense Features: UIUC texture dataset 25 classes, 40 samples each Lazebnik, Schmid & Ponce (2005)
Sparse vs. Dense Features: UIUC texture dataset Multi-classification accuracy vs. training set size Invariant local features SVM Non-invariant dense patches NN Baseline (global features) SVM NN • A system with intrinsically invariant features can learn from fewer training examples Zhang, Marszalek, Lazebnik & Schmid (2005)
Sparse vs. Dense Features: CURe. T dataset Dana, van Ginneken, Nayar, and Koenderink (1999) 61 classes, 92 samples each, 43 training Non-invariant features (SVM) Non-invariant features (NN) Invariant local features (SVM) Baseline – global features Invariant local features (NN) Relative Strengths Sparse locally invariant features: Dense non-invariant features: High-resolution images Low-resolution images Non-homogeneous patterns Homogeneous, high-frequency patterns Viewpoint changes Lighting changes
Anticipating Criticism • Existing local features are not ideal for category-level recognition and scene understanding – Designed for wide-baseline matching and specific object recognition – Describe texture and albedo pattern, not shape – Do not explain the whole image • A little invariance goes a long way – It is best to use features with the lowest level of invariance required by a given task – Scale+rotation is sufficient for most datasets Zhang, Marszalek, Lazebnik & Schmid (2005) • Denser sets of local features are more effective – Hessian detector produces the most regions and performs best in several evaluations – Regular grid of fixed-size patches is best for scene category recognition Fei-Fei & Perona (2005)
Future Work • Systematic evaluation of sparse vs. dense features • Combining sparse and dense representations, e. g. , keypoints and segments Russell, Efros, Sivic, Freeman & Zisserman (2006) • Learning detectors and descriptors automatically • Developing shape-based features
- Slides: 21