Kadir–Brady saliency detector

The Kadir–Brady saliency detector extracts features of objects in images that are distinct and representative.

The detector uses the algorithms to more efficiently remove background noise and so more easily identify features which can be used in a 3D model.

As the detector scans images it uses the three basics of global transformation, local perturbations and intra-class variations to define the areas of search, and identifies unique regions of those images rather than using the more traditional corner or blob searches.

[4] This leads to a more object oriented search than previous methods and outperforms other detectors due to non blurring of the images, an ability to ignore slowly changing regions and a broader definition of surface geometry properties.

However, there are three broad classes of image change under which good performance may be required: Global transformation: Features should be repeatable across the expected class of global image transformations.

These include both geometric and photometric transformations that arise due to changes in the imaging conditions.

This property will be evaluated on the repeatability and accuracy of localization and region estimation.

Local perturbations: Features should be insensitive to classes of semi-local image disturbances.

For example, a feature responding to the eye of a human face should be unaffected by any motion of the mouth.

The detector can be required to detect the foreground region despite changes in the background.

In the field of Information theory Shannon entropy is defined to quantify the complexity of a distribution p as

(e.g., in an 8 bit grey level image, D would range from 0 to 255 for each pixel) is defined so that

The first version of the Kadir–Brady saliency detector[10] only finds Salient regions invariant under similarity transformation.

Previous method is invariant to the similarity group of geometric transformations and to photometric shifts.

However, as mentioned in the opening remarks, the ideal detector should detect region invariant up to viewpoint change.

There are several detector [] can detect affine invariant region which is a better approximation of viewpoint change than similarity transformation.

In practice the affine invariant saliency detector starts with the set of points and scales generated from the similarity invariant saliency detector then iteratively approximates the suboptimal parameters.

A more robust method would be to pick regions rather than points in entropy space.

A global threshold approach would result in highly salient features in one part of the image dominating the rest.

The method works as follows: The algorithm is implemented as GreedyCluster1.m in matlab by Dr. Timor Kadir[5] In the field of computer vision different feature detectors have been evaluated by several tests.

[6] The following subsection discuss the performance of Kadir–Brady saliency detector on a subset of a test in the paper.

In order to measure the consistency of a region detected on the same object or scene across images under global transformation, repeatability score, which is first proposed by Mikolajczyk and Cordelia Schmid in [18, 19] is calculated as follows:[7][8] Firstly, overlap error

In general we would like a detector to have a high repeatability score and a large number of correspondences.

The precise procedure is given in the Matlab code from Detector evaluation #Software implementation.

Repeatability measures over intra-class variation and image perturbations is proposed.

A region is matched if it fulfills three requirements: In detail the average correspondence score S is measured as follows.

is computed for M/2 different selections of the reference image and averaged to give S. The score is evaluated as a function of the number of detected regions N. The Kadir–Brady saliency detector gives the highest score across three test classes which are motorbike, car and face.

In contrast, other detectors maps show a much more diffuse pattern over the entire area caused by poor localization and false responses to background clutter.

If the detector is robust to background clutter then the average correspondence score S should be similar for both subsets of images.

However, in the task of 3D object recognition where all three types of image change are combined, saliency detector might still be powerful.