Recognition with local features: the kernel recipe

Wallraven,; Caputo, D.; Gräf,

doi:10.1109/iccv.2003.1238351

Cited by 265 publications

(223 citation statements)

References 22 publications

Supporting

Mentioning

219

Contrasting

Order By: Relevance

“…For their simplicity and satisfactory performance, bag-of-features representations have become widely used for image classification and retrieval [18][19][20]. The basic idea is to select a collection of representative patches of the image, compute a visual descriptor for each patch, and use the resulting distribution of descriptors to characterize the whole image.…”

Section: Image Description By Low-level Featuresmentioning

confidence: 99%

Prosemantic Features for Content-Based Image Retrieval

Ciocca

Cusano

Santini

et al. 2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Esta es la versión de autor de la comunicación de congreso publicada en: This is an author produced version of a paper published in: Abstract. We present here, an image description approach based on prosemantic features. The images are represented by a set of low-level features related to their structure and color distribution. Those descriptions are fed to a battery of image classifiers trained to evaluate the membership of the images with respect to a set of 14 overlapping classes. Packing together the scores vectors of prosemantic features are obtained, and used to index the images in an image retrieval system. To verify the effectiveness of the approach, we designed a target search experiment in which both low-level and prosemantic features are embedded into a content-based image retrieval system exploiting relevance feedback. The experiments show that the use of prosemantic features allows for a more successful and quick retrieval of the query images.

show abstract

Section: Image Description By Low-level Featuresmentioning

confidence: 99%

Prosemantic Features for Content-Based Image Retrieval

Ciocca

Cusano

Santini

et al. 2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Match kernels between sets of local features have long been exploited [27,26]. The kernel function is computed to measure the similarity between two images/video sequences represented by sets of local feature vectors.…”

Section: Match Kernelsmentioning

confidence: 99%

“…Match kernels between sets of local features have long been exploited in visual recognition [26,27]. Without relying on any mid-level feature representations, match kernels are able to compute the similarity between sets of unordered local features and have shown the effectiveness in image and object recognition.…”

Section: Introductionmentioning

confidence: 99%

Action recognition via spatio-temporal local features: A comprehensive study

Zhen

Shao

2016

Image and Vision Computing

View full text Add to dashboard Cite

Local methods based on spatio-temporal interest points (STIPs) have shown their effectiveness for human action recognition. The bag-of-words (BoW) model has been widely used and dominated in this field. Recently, a large number of techniques based on local features including improved variants of the BoW model, sparse coding (SC), Fisher kernels (FK), vector of locally aggregated descriptors (VLAD) as well as the naive Bayes nearest neighbor (NBNN) classifier have been proposed and developed for visual recognition. However, some of them are proposed in the image domain and have not yet been applied to the video domain and it is still unclear how effectively these techniques would perform on action recognition. In this paper, we provide a comprehensive study on these local methods for human action recognition. We implement these techniques and conduct comparison under unified experimental settings on three widely used benchmarks, i.e., the KTH, UCF-YouTube and HMDB51 datasets. We discuss insightfully the findings from the experimental results and draw useful conclusions, which are expected to guide practical applications and future work for the action recognition community.

show abstract

“…By introducing a Mercer kernel, a non-linear SVM can be constructed replacing the scalar products in the linear SVM via the kernel function. SVMs have demonstrated remarkable performance on object recognition and categorization [13] and biomedical imaging [14]. As probabilistic method we chose Spin GlassMarkov Random Fields (SG-MRF, [2]), a fully connected MRF which integrates results of statistical mechanics with Gibbs probability distributions via non linear kernel mapping [2].…”

Section: Introductionmentioning

confidence: 99%

Melanoma Recognition Using Representative and Discriminative Kernel Classifiers

Tommasi

Torre

Caputo³

2006

Computer Vision Approaches to Medical Image Analysis

View full text Add to dashboard Cite

Abstract. Malignant melanoma is the most deadly form of skin lesion. Early diagnosis is of critical importance to patient survival. Existent visual recognition algorithms for skin lesions classification focus mostly on segmentation and feature extraction. In this paper instead we put the emphasis on the learning process by using two kernel-based classifiers. We chose a discriminative approach using support vector machines, and a probabilistic approach using spin glass-Markov random fields. We benchmarked these algorithms against the (to our knowledge) state-of-the-art method on melanoma recognition, exploring how performance changes by using color or textural features, and how it is affected by the quality of the segmentation mask. We show with extensive experiments that the support vector machine approach outperforms the existing method and, on two classes out of three, it achieves performances comparable to those obtained by expert clinicians.

show abstract

Recognition with local features: the kernel recipe

Abstract: Recent developments in computer vision

Cited by 265 publications

References 22 publications

Prosemantic Features for Content-Based Image Retrieval

Prosemantic Features for Content-Based Image Retrieval

Action recognition via spatio-temporal local features: A comprehensive study

Melanoma Recognition Using Representative and Discriminative Kernel Classifiers

Contact Info

Product

Resources

About