Robust classification of arbitrary object classes based on hierarchical spatial feature-matching

Lang, Graham K.; Seitz, Peter

doi:10.1007/s001380050065

Cited by 9 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After that, three different spatial pyramids are used: the whole image without subdivision (1x1), image parts divided into 4 quarters (2x2) and a pyramid with three horizontal bars (1x3). L 1 -BRD is used to calculate histogram dissimilarities followed by the extended Gaussian kernel (14) to be used in SRKDA [3] as in the winner's method. Parameters are calculated on validation set and further used for test set.…”

Section: Pascal Voc 2008mentioning

confidence: 99%

Use bin-ratio information for category and scene classification

Xie

Ling

et al. 2010

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

Section: Pascal Voc 2008mentioning

confidence: 99%

Use bin-ratio information for category and scene classification

Xie

Ling

et al. 2010

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Classical 'texton' or 'bag of features' representations are global histograms over quantized image descriptors -'level 0' of the hyperfeature representation [31,29]. Histograms of quantized 'level 1' features have also been used to classify textures and to recognize regularly textured objects [37,42] and a hierarchical feature-matching framework for simple second level features has been developed [25].…”

Section: Previous Workmentioning

confidence: 99%

Hyperfeatures – Multilevel Local Coding for Visual Recognition

Agarwal

Triggs

2006

Computer Vision – ECCV 2006

121

View full text Add to dashboard Cite

Abstract. Histograms of local appearance descriptors are a popular representation for visual recognition. They are highly discriminant and have good resistance to local occlusions and to geometric and photometric variations, but they are not able to exploit spatial co-occurrence statistics at scales larger than their local input patches. We present a new multilevel visual representation, 'hyperfeatures', that is designed to remedy this. The starting point is the familiar notion that to detect object parts, in practice it often suffices to detect co-occurrences of more local object fragments -a process that can be formalized as comparison (e.g. vector quantization) of image patches against a codebook of known fragments, followed by local aggregation of the resulting codebook membership vectors to detect cooccurrences. This process converts local collections of image descriptor vectors into somewhat less local histogram vectors -higher-level but spatially coarser descriptors. We observe that as the output is again a local descriptor vector, the process can be iterated, and that doing so captures and codes ever larger assemblies of object parts and increasingly abstract or 'semantic' image properties. We formulate the hyperfeatures model and study its performance under several different image coding methods including clustering based Vector Quantization, Gaussian Mixtures, and combinations of these with Latent Dirichlet Allocation. We find that the resulting high-level features provide improved performance in several object image and texture image classification tasks.

show abstract

“…is developed in [23], and histograms of quantized 'level 1' features are used to classify textures and recognize regularly textured objects in [36,41]. Hyperfeature stacks also have analogies with multilevel neural models such as the neocognitron [16], Convolutional Neural Networks (CNN) [27] and HMAX [37,43,34].…”

Section: Previous Workmentioning

confidence: 99%

Multilevel Image Coding with Hyperfeatures

Agarwal

Triggs

2007

Int J Comput Vis

View full text Add to dashboard Cite

Histograms of local appearance descriptors are a popular representation for visual recognition. They are highly discriminant with good resistance to local occlusions and to geometric and photometric variations, but they are not able to exploit spatial co-occurrence statistics over scales larger than the local input patches. We present a multilevel visual representation that remedies this. The starting point is the notion that to detect object parts in images, in practice it often suffices to detect co-occurrences of more local object fragments. This can be formalized by coding image patches against a codebook of known fragments or a more general statistical model and locally histogramming the resulting labels to capture their co-occurrence statistics. Local patch descriptors are converted into somewhat less local histograms over label occurrences. The histograms are themselves local descriptor vectors so the process can be iterated to code ever larger assemblies of object parts and increasingly abstract or 'semantic' image properties. We call these higher-level descriptors "hyperfeatures". We formulate the hyperfeature model and study its performance under several different image coding methods including k-means based Vector Quantization, Gaussian Mixtures, and combinations of these with Latent Dirichlet Allocation. We find that the resulting high-level features provide improved performance in several object image and texture image classification tasks.

show abstract

Robust classification of arbitrary object classes based on hierarchical spatial feature-matching

Cited by 9 publications

References 28 publications

Use bin-ratio information for category and scene classification

Use bin-ratio information for category and scene classification

Hyperfeatures – Multilevel Local Coding for Visual Recognition

Multilevel Image Coding with Hyperfeatures

Contact Info

Product

Resources

About