Improving a Discriminative Approach to Object Recognition Using Image Patches

Deselaers, Thomas; Keysers, Daniel; Ney, Hermann

doi:10.1007/11550518_41

Cited by 33 publications

(16 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here again, using the histogram distortion model usually gave an improvement over the normal Jeffrey Divergence, and a further improvement can be achieved using the discriminatively trained log-linear model. Although the model we present is clearly much simpler than the models presented in [1,2,4,8,11], we achieve very competitive error rates. Using SVMs, the results are in the same area as those using the maximum entropy training.…”

Section: Resultsmentioning

confidence: 86%

See 1 more Smart Citation

Sparse Patch-Histograms for Object Classification in Cluttered Images

Deselaers

Hegerath

Keysers

et al. 2006

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. We present a novel model for object recognition and detection that follows the widely adopted assumption that objects in images can be represented as a set of loosely coupled parts. In contrast to former models, the presented method can cope with an arbitrary number of object parts. Here, the object parts are modelled by image patches that are extracted at each position and then efficiently stored in a histogram. In addition to the patch appearance, the positions of the extracted patches are considered and provide a significant increase in the recognition performance. Additionally, a new and efficient histogram comparison method taking into account inter-bin similarities is proposed. The presented method is evaluated for the task of radiograph recognition where it achieves the best result published so far. Furthermore it yields very competitive results for the commonly used Caltech object detection tasks.

show abstract

Section: Resultsmentioning

confidence: 86%

“…These multiple patch sizes allow to account for objects of various sizes and lead to a certain invariance with respect to scale changes. A very similar approach to account for different scales was used in [11].…”

Section: Featuresmentioning

confidence: 99%

Sparse Patch-Histograms for Object Classification in Cluttered Images

Deselaers

Hegerath

Keysers

et al. 2006

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…To this end, each model point is equipped with an individual weight, relative to its importance. This approach has also been followed by Deselaers et al [3] and Maji and Malik [12]; yet they do not allow for negative weights, which we employ to represent anti-shapes. This approach results in models, which are discriminative for the target object, and therefore reduce false-positive rates.…”

Section: Introductionmentioning

confidence: 99%

Discriminative Generalized Hough transform for localization of joints in the lower extremities

et al. 2010

View full text Add to dashboard Cite

A fully automatic iterative training approach for the generation of discriminative shape models for usage in the Generalized Hough Transform (GHT) is presented. The method aims at capturing the shape variability of the target object contained in the training data as well as identifying confusable structures (anti-shapes) and integrating this information into one model. To distinguish shape and anti-shape points and to determine their importance, an individual positive or negative weight is estimated for each model point by means of a discriminative training technique. The model is built from edge points surrounding the target point and the most confusable structure as identified by the GHT. Through an iterative approach, the performance of the model is gradually improved by extending the training dataset with images, where the current model failed to localize the target point. The proposed method is successfully tested on a set of 670 long-leg radiographs, where it achieves a localization rate of 74-97% for the respective tasks.

show abstract

“…A spatial color descriptor was proposed to overcome this drawback by including a color adjacency histogram and a color vector angle histogram [6] . Many other approaches are based on regions or blocks [7,8] .…”

Section: Introductionmentioning

confidence: 99%

Image block feature vectors based on a singular-value information metric and color-texture description

Wang

Lü

Sheng-jun

et al. 2007

J. of Shanghai Univ.

View full text Add to dashboard Cite

In this work, image feature vectors are formed for blocks containing sufficient information, which are selected using a singular-value criterion. When the ratio between the first two SVs are below a given threshold, the block is considered informative. A total of 12 features including statistics of brightness, color components and texture measures are used to form intermediate vectors. Principal component analysis is then performed to reduce the dimension to 6 to give the final feature vectors. Relevance of the constructed feature vectors is demonstrated by experiments in which k-means clustering is used to group the vectors hence the blocks. Blocks falling into the same group show similar visual appearances.

show abstract

Improving a Discriminative Approach to Object Recognition Using Image Patches

Cited by 33 publications

References 14 publications

Sparse Patch-Histograms for Object Classification in Cluttered Images

Sparse Patch-Histograms for Object Classification in Cluttered Images

Discriminative Generalized Hough transform for localization of joints in the lower extremities

Image block feature vectors based on a singular-value information metric and color-texture description

Contact Info

Product

Resources

About