• Corpus ID: 7730736

Enhancing bag of visual words with color information for iconic image classification

@inproceedings{Kopf2017EnhancingBO,
  title={Enhancing bag of visual words with color information for iconic image classification},
  author={Stephan Kopf and Mariia Zrianina and Benjamin Guthier and Lydia Weiland and Philipp Schaber and Simone Paolo Ponzetto and Wolfgang Effelsberg},
  year={2017}
}
Iconic images represent an abstract topic and use a presentation that is intuitively understood within a certain cultural context. For example, the abstract topic “global warming” may be represented by a polar bear standing alone on an ice floe. This paper presents a system for the classification of iconic images. It uses a variation of the Bag of Visual Words approach with enhanced feature descriptors. Our novel color pyramids feature incorporates color information into the classification… 
Classification of iconic images
Iconic images represent an abstract topic and use a presentation that is intuitively understood within a certain cultural context. For example, the abstract topic “global warming” may be represented
Image classification by addition of spatial information based on histograms of orthogonal vectors
TLDR
The proposed image representation outperforms the existing state-of-the-art in terms of classification accuracy and incorporates the spatial information to the inverted index of BoVW model by calculating the global relative spatial orientation of visual words in a rotation invariant manner.
Adding Color Information to Spatially-Enhanced, Bag-of-Visual-Words Models
TLDR
This paper presents a method of Adding Color Information to Spatially-Enhanced, Bag-of-Visual-Words Models and shows that color information in these models is influenced by the content of the text itself.

References

SHOWING 1-10 OF 12 REFERENCES
Automatic classification of iconic images based on a multimodal model. An interdisciplinary project
The term “iconic image” refers here to images produced to create privileged associations between a particular visual representation and a referent. They are highly recognizable for media users and
Computing iconic summaries of general visual concepts
  • R. Raguram, S. Lazebnik
  • Computer Science
    2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
  • 2008
TLDR
Results on four large-scale datasets demonstrate the ability of the approach to discover plausible themes and recurring visual motifs for challenging abstract concepts such as ldquoloverdquo and ldQuobeautyrDquo.
Finding iconic images
  • Tamara L. Berg, A. Berg
  • Computer Science
    2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
  • 2009
TLDR
It is demonstrated that is it possible to automatically find representative example images of a specified object category using a category independent composition model that predicts whether they contain a large clearly depicted object, and outputs an estimated location of that object.
Generating Descriptive Visual Words and Visual Phrases for Large-Scale Image Applications
TLDR
Desc descriptive visual words (DVWs) and descriptive visual phrases (DVPs) are proposed as the visual correspondences to text words and phrases, where visual phrases refer to the frequently co-occurring visual word pairs.
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
  • S. Lazebnik, C. Schmid, J. Ponce
  • Computer Science
    2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
TLDR
This paper presents a method for recognizing scene categories based on approximate global geometric correspondence that exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories.
Discriminative spatial saliency for image classification
TLDR
This work proposes to learn the discriminative spatial saliency of images while simultaneously learning a max margin classifier for a given visual classification task, and treats the saliency maps as latent variables and allow them to adapt to the image content to maximize the classification score, while regularizing the change in thesaliency maps.
Contour-based classification of video objects
TLDR
An approach which classifies a segmented video object base by matching curvature features of the contours of these object views to a database containing preprocessed views of prototypical objects using a modified curvature scale space technique.
Towards Effective Image Classification Using Class-Specific Codebooks and Distinctive Local Features
TLDR
A new codebook generation approach is proposed through employing a new clustering method that generates class-specific codebooks along with a novel feature selection method in the bag-of-words model to decrease the inverse effects of these limitations in image classification problems.
A survey on image retrieval performance of different bag of visual words indexing techniques
TLDR
Locality sensitive hashing, SR-tree based indexing and naive L1 and L2 norm based distance metric calculation are used here to compute near similar visual word vectors of a query image.
Shape-based posture and gesture recognition in videos
TLDR
This work presents a new three-step approach to classifying the posture or gesture of a person based on segmentation, classification, and aggregation, and compares the classification rates of postures and gestures for the standard CSS and the new approach.
...
1
2
...