Change search
Refine search result
1 - 11 of 11
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Bigham, Jeffrey P
    et al.
    University of Washington, Seattle, USA.
    Kaminsky,, Ryan S
    University of Washington, Seattle, USA.
    Ladner, Richard E
    University of Washington, Seattle, USA.
    Danielsson, Oscar
    University of Washington, Seattle, USA.
    Hempton, Gordon L.
    University of Washington, Seattle, USA.
    WebInSight: Making Web Images Accassible2006In: ASSETS 2006: Proceedings of the Eighth International ACM SIGACCESS Conference on Computers and Accessibility, Association for Computing Machinery (ACM), 2006, p. 181-188Conference paper (Refereed)
    Abstract [en]

    Images without alternative text are a barrier to equal web access for blind users. To illustrate the problem, we conducted a series of studies that conclusively show that a large fraction of significant images have no alternative text. To ameliorate this problem, we introduce WebInSight, a system that automatically creates and inserts alternative text into web pages on-the-fly. To formulate alternative text for images, we present three labeling modules based on web context analysis, enhanced optical character recognition (OCR) and human labeling. The system caches alternative text in a local database and can add new labels seamlessly after a web page is downloaded, resulting in minimal impact to the browsing experience.

  • 2.
    Danielsson, Oscar
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Shape-based Representations and Boosting for Visual Object Class Detection: Models and methods for representaion and detection in single and multiple views2011Doctoral thesis, monograph (Other academic)
    Abstract [en]

    Detection of generic visual object classes (i.e. cars, dogs, mugs or people) in images is a task that humans are able to solve with remarkable ease. Unfortunately this has proven a very challenging task for computer vision. Thereason is that different instances of the same class may look very different, i.e. there is a high intra-class variation. There are several causes for intra-class variation; for example (1) the imaging conditions (e.g. lighting and exposure) may change, (2) different objects of the same class typically differ in shape and appearance, (3) the position of the object relative to the camera (i.e. the viewpoint) may change and (4) some objects are articulate and may change pose. In addition the background class, i.e. everything but the target object class, is very large. It is the combination of very high intra-class variation with a large background class that makes generic object class detection difficult.

    This thesis addresses this challenge within the AdaBoost framework. AdaBoost constructs an ensemble of weak classifiers to solve a given classification task and allows great flexibility in the design of these weak classifiers. This thesis proposes several types of weak classifiers that specifically target some of the causes of high intra-class variation. A multi-local classifier is proposed to capture global shape properties for object classes that lack discriminative local features, projectable classifiers are proposed to handle detection from multiple viewpoints and finally gated classifiers are proposed as a generic way to handle high intra-class variation in combination with a large background class.

    All proposed weak classifiers are evaluated on standard datasets to allow performance comparison to other related methods.

  • 3.
    Danielsson, Oscar
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Carlsson, Stefan
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Generic Object Class Detection using Boosted Configurations of Oriented Edges2010In: Computer Vision – ACCV 2010 / [ed] Kimmel, R; Klette, R; Sugimoto, A, Springer Berlin/Heidelberg, 2010, p. 1-14Conference paper (Refereed)
    Abstract [en]

    In this paper we introduce a new representation for shape-based object class detection. This representation is based on very sparse and slightly flexible configurations of oriented edges. An ensemble of such configurations is learnt in a boosting framework. Each edge configuration can capture some local or global shape property of the target class and the representation is thus not limited to representing and detecting visual classes that have distinctive local structures. The representation is also able to handle significant intra-class variation. The representation allows for very efficient detection and can be learnt automatically from weakly labelled training images of the target class. The main drawback of the method is that, since its inductive bias is rather weak, it needs a comparatively large training set. We evaluate on a standard database [1] and when using a slightly extended training set, our method outperforms state of the art [2] on four out of five classes.

  • 4.
    Danielsson, Oscar
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Carlsson, Stefan
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Generic Object Class Detection using Feature Maps2011In: Proceedings of Scandinavian Conference on Image Analysis, 2011, p. 348-359Conference paper (Refereed)
    Abstract [en]

    In this paper we describe an object class model and a detection scheme based on feature maps, i.e. binary images indicating occurrences of various local features. Any type of local feature and any number of features can be used to generate feature maps. The choice of which features to use can thus be adapted to the task at hand, without changing the general framework. An object class is represented by a boosted decision tree classifier (which may be cascaded) based on normalized distances to feature occurrences. The resulting object class model is essentially a linear combination of a set of flexible configurations of the features used. Within this framework we present an efficient detection scheme that uses a hierarchical search strategy. We demonstrate experimentally that this detection scheme yields a significant speedup compared to sliding window search. We evaluate the detection performance on a standard dataset [7], showing state of the art results. Features used in this paper include edges, corners, blobs and interest points.

  • 5.
    Danielsson, Oscar
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Carlsson, Stefan
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Projectable Classifiers for Multi-View Object Class Recognition2011In: 3rd International IEEE Workshop on 3D Representation and Recognition, 2011Conference paper (Refereed)
    Abstract [en]

    We propose a multi-view object class modeling framework based on a simplified camera model and surfels (defined by a location and normal direction in a normalized 3D coordinate system) that mediate coarse correspondences between different views. Weak classifiers are learnt relative to the reference frames provided by the surfels. We describe a weak classifier that uses contour information when its corresponding surfel projects to a contour element in the image and color information when the face of the surfel is visible in the image. We emphasize that these weak classifiers can possibly take many different forms and use many different image features. Weak classifiers are combined using AdaBoost. We evaluate the method on a public dataset [8], showing promising results on categorization, recognition/detection, pose estimation and image synthesis.

  • 6.
    Danielsson, Oscar
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Carlsson, Stefan
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Sullivan, Josephine
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Automatic Learning and Extraction of Multi-Local Features2009In: Proceedings of the IEEE International Conference on Computer Vision, 2009, p. 917-924Conference paper (Refereed)
    Abstract [en]

    In this paper we introduce a new kind of feature - the multi-local feature, so named as each one is a collection of local features, such as oriented edgels, in a very specific spatial arrangement. A multi-local feature has the ability to capture underlying constant shape properties of exemplars from an object class. Thus it is particularly suited to representing and detecting visual classes that lack distinctive local structures and are mainly defined by their global shape. We present algorithms to automatically learn an ensemble of these features to represent an object class from weakly labelled training images of that class, as well as procedures to detect these features efficiently in novel images. The power of multi-local features is demonstrated by using the ensemble in a simple voting scheme to perform object category detection on a standard database. Despite its simplicity, this scheme yields detection rates matching state-of-the-art object detection systems.

  • 7.
    Danielsson, Oscar
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Carlsson, Stefan
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Sullivan, Josephine
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Object Detection using Multi-Local Feature Manifolds2008In: Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008, 2008, p. 612-618Conference paper (Refereed)
    Abstract [en]

    Many object categories are better characterized by the shape of their contour than by local appearance properties like texture or color. Multi-local features are designed in order to capture the global discriminative structure of an object while at the same time avoiding the drawbacks with traditional global descriptors such as sensitivity to irrelevant image properties. The specific structure of multi-local features allows us to generate new feature exemplars by linear combinations which effectively increases the set of stored training exemplars. We demonstrate that a multi-local feature is a good "weak detector" of shape-based object categories and that it can accurately estimate the bounding box of objects in an image. Using just a single multi-local feature descriptor we obtain detection results comparable to those of more complex and elaborate systems. It is our opinion that multi-local features have a great potential as generic object descriptors with very interesting possibilities of feature sharing within and between classes.

  • 8.
    Danielsson, Oscar Martin
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Category-sensitive hashing and bloom filter based descriptors for online keypoint recognition2015In: 19th Scandinavian Conference on Image Analysis, SCIA 2015, Springer, 2015, p. 329-340Conference paper (Refereed)
    Abstract [en]

    In this paper we propose a method for learning a categorysensitive hash function (i.e. a hash function that tends to map inputs from the same category to the same hash bucket) and a feature descriptor based on the Bloom filter. Category-sensitive hash functions are robust to intra-category variation. In this paper we use them to produce descriptors that are invariant to transformations caused by for example viewpoint changes, lighting variation and deformation. Since the descriptors are based on Bloom filters, they support a ”union” operation. So descriptors of matched features can be aggregated by taking their union.We thus end up with one descriptor per keypoint instead of one descriptor per feature (By keypoint we refer to a world-space reference point and by feature we refer to an image-space interest point. Features are typically observations of keypoints and matched features are observations of the same keypoint). In short, the proposed descriptor has data-defined invariance properties due to the category-sensitive hashing and is aggregatable due to its Bloom filter inheritance. This is useful whenever we require custom invariance properties (e.g. tracking of deformable objects) and/or when we make multiple observations of each keypoint (e.g. tracking, multi-view stereo or visual SLAM).

  • 9.
    Danielsson, Oscar
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Rasolzadeh, Babak
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Nonlinear classification of data2012Patent (Other (popular science, discussion, etc.))
    Abstract [en]

    The present invention relates to a method for nonlinear classification of high dimensional data by means of boosting, whereby a target class with significant intra-class variation is classified against a large background class, where the boosting algorithm produces a strong classifier, the strong classifier being a linear combination of weak classifiers. The present invention specifically teaches that weak classifiers classifiers h 1, h 2, that individually more often than not generate a positive on instances within the target class and a negative on instances outside of the target class, but that never generate a positive simultaneously on one and the same target instance, are categorized as a group of anti-correlated classifiers, and that the occurrence of anti-correlated classifiers from the same group will generate a negative.

  • 10.
    Danielsson, Oscar
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Rasolzadeh, Babak
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Carlsson, Stefan
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Gated Classifiers: Boosting under high intra-class variation2011In: Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, 2011, p. 2673-2680Conference paper (Refereed)
    Abstract [en]

    In this paper we address the problem of using boosting (e.g. AdaBoost [7]) to classify a target class with significant intra-class variation against a large background class. This situation occurs for example when we want to recognize a visual object class against all other image patches. The boosting algorithm produces a strong classifier, which is a linear combination of weak classifiers. We observe that we often have sets of weak classifiers that individually fire on many examples of the target class but never fire together on those examples (i.e. their outputs are anti-correlated on the target class). Motivated by this observation we suggest a family of derived weak classifiers, termed gated classifiers, that suppress such combinations of weak classifiers. Gated classifiers can be used on top of any original weak learner. We run experiments on two popular datasets, showing that our method reduces the required number of weak classifiers by almost an order of magnitude, which in turn yields faster detectors. We experiment on synthetic data showing that gated classifiers enables more complex distributions to be represented. We hope that gated classifiers will extend the usefulness of boosted classifier cascades [29].

  • 11.
    Sullivan, Josephine
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Danielsson, Oscar
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Carlsson, Stefan
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Exploiting Part-Based Models and Edge Boundaries for Object Detection2008In: Digital Image Computing: Techniques and Applications, DICTA 2008, 2008, p. 199-206Conference paper (Refereed)
    Abstract [en]

    This paper explores how to exploit shape information to perform object class recognition. We use a sparse partbased model to describe object categories defined by shape. The sparseness allows the relative spatial relationship between parts to be described simply. It is possible, with this model, to highlight potential locations of the object and its parts in novel images. Subsequently these areas are examined by a more flexible shape model that measures if the image data provides evidence of the existence of boundary/connecting curves between connected hypothesized parts. From these measurements it is possible to construct a very simple cost function which indicates the presence or absence of the object class. The part-based model is designed to decouple variations due to affine warps and other forms of shape deformations. The latter are modeled probabilistically using conditional probability distributions which describe the linear dependencies between the location of a part and a subset of the other parts. These conditional distributions can then be exploited to search efficiently for the instances of the part model in novel images. Results are reported on experiments performed on the ETHZ shape classes database that features heavily cluttered images and large variations in scale.

1 - 11 of 11
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf