240 likes | 352 Views
Bag of Features Approach: recent work, using geometric information. Problem. Search for object occurrences in very large image collection. 2 sub problems. Object Category Recognition and Specific Object Recognition. Motivation. Look for product information Look for similar products.
E N D
Bag of Features Approach: recent work, using geometric information
Problem • Search for object occurrences in very large image collection
2 sub problems • Object Category Recognition and Specific Object Recognition
Motivation • Look for product information • Look for similar products
Related work on large scale image search • Most systems build upon the BoF framework [Sivic & Zisserman 03] • Large (hierarchical) vocabularies [NisterStewenius 06] • Improveddescriptorrepresentation [Jégou et al 08, Philbin et al 08] • Geometry used in index [Jégou et al 08, Perdoc’h et al 09] • Query expansion [Chum et al 07] • … • Efficiency improved by: • Min-hash and Geometrical min-hash [Chum et al. 07-09] • Compressing the BoF representation [Jégou et al. 09]
Creating a visual vocabulary 1 2 3 4
Inverted Index Index construction Searching
Use geometry • Possible directions: • Change/optimize spatial verification stage • Insert a new geometric information to the index • Ordered BOF • Bundled features • Visual phrases • Change the searching algorithm
Survey for today • Spatial Bag-of-features [Cao, CVPR2010] • Image Retrieval with Geometry-Preserving Visual Phrases [Zhang Jia Chen, CVPR2011] • Smooth Object Retrieval using a Bag of Boundaries [ArandjeloviZisserman, ICCV2011]
Spatial BOF • Basic idea:
Spatial BOF • Constructing linear and circular ordered bag-of-features:
Spatial BOF • Translation invariance:
Spatial BOF • Pros: • Gets better performance than BOF+RANSAC for large scale dataset* • Same format as standard BOF • Cons: • Is dataset dependent because of need of training • Do not present the results for large scale dataset with transfer learning from another dataset • Future work • Check it with cross training for large dataset. Otherwise, it is not worth working further.
Geometry-Preserving Visual Phrases • Basic idea:
Geometry-Preserving Visual Phrases • Representation • Quantize image to 10x10 grid • Histogram of GVPs of length k • GVP dictionary size is “choose k from N visual words”
Geometry-Preserving Visual Phrases • Pros: • Outperforms BOV + RANSAC • Cons: • Only translation invariant because of memory • Future work
BOF for smooth objects Idea: Gradient Segment The information used for retrieval Query object
BOF for smooth objects Results:
BOF for smooth objects Segmentation phase • Over segmentation with super-pixels • Classification of super-pixels: • 3208 feature vector (median(Mag(Grad)), 4 bits, color histogram, BOF) • SVM • Post-processing
BOF for smooth objects Boundary description phase: • Sample points on the boundary • Calculate HoG at each point in 3 scales 340 dimensional L2 normalized vector * The descriptor is not rotation invariant
BOF for smooth objects Retrieval procedure: • Boundary descripors are quantized (k=10k) • Standard BOF scheme* • Spatial verification for top 200 with loose affine homography (errors up to 100pixs) * No spatial information is recorded in the histogram
BOF for smooth objects • Pros: • Solves the smooth object retrieval problem • Fast • Cons: • Is dataset dependent because of need of training • Limited to objects with “solid” materials – segmentation has to catch the object’s boundary • Future work • Eliminate the training step
Summary • There is an active research in the field of CBIR to exploit geometry information. • Each method with its limitations • Still no widely accepted solution • Like spatial verification with RANSAC