evaluators

Type Members

1. case class Box(topLeft: Point[_2D], bottomRight: Point[_2D]) extends Product with Serializable

   

   simple box structure to capture landmark region

2. class CollectiveLikelihoodEvaluator extends PairEvaluator[PixelImage[RGBA]]

   

   Collective Likelihood: models the average squared distance of images as normal (valid for many pixels, large averages: Central Limit Theorem) for Details see "Markov Chain Monte Carlo for Automated Face Image Analysis" in IJCV 2016

3. case class FaceBox(topLeft: Point[_2D], bottomRight: Point[_2D], certainty: Double) extends Product with Serializable

   

   a face detection candidate

4. class FaceBoxEvaluator extends DistributionEvaluator[RenderParameter]

   

   evaluate face position with respect to a given detection face box (has scale and position)

5. case class HistogramRGB extends DistributionEvaluator[RGB] with Product with Serializable

   

   Provides specific implementation of a Histogram for a sequence/image of RGB values for RGBA images alpha value is used as mask

6. class ImageRendererEvaluator extends DistributionEvaluator[RenderParameter]

   

   evaluate the rendered image with given image evaluator

7. class IndependentPixelEvaluator extends PairEvaluator[PixelImage[RGBA]]

   

   evaluate each pixel independently, uses alpha channel to determine between foreground and background

8. class LabeledImageRendererEvaluator extends DistributionEvaluator[(RenderParameter, PixelImage[Int])]

   

   evaluate the rendered image with given image evaluator and a segmentation label

9. class LabeledIndependentPixelEvaluator extends DistributionEvaluator[LabeledPixelImage[RGBA]]

   

   evaluate each pixel independently, uses alpha channel to determine between foreground, background and label to destinguish between face and occlusion/non-face.

   evaluate each pixel independently, uses alpha channel to determine between foreground, background and label to destinguish between face and occlusion/non-face.

   The face region is labeled as 1 (according to the following publication)

   This evaluator is an implementation of Equation 2, 4, 5 and 7 of: Occlusion-aware 3D Morphable Face Models, Bernhard Egger, Andreas Schneider, Clemens Blumer, Andreas Morel-Forster, Sandro Schönborn, Thomas Vetter IN: British Machine Vision Conference (BMVC), September 2016 https://dx.doi.org/10.5244/C.30.64

10. case class LandmarkMapEvaluator(detectionMap: LandmarkDetectionMap, renderer: ParametricLandmarksRenderer) extends DistributionEvaluator[RenderParameter] with Product with Serializable

    

    The LandmarkMapEvaluator evaluates landmark positions by a simple look-up in a LandmarkDetectionMap.

    The LandmarkMapEvaluator evaluates landmark positions by a simple look-up in a LandmarkDetectionMap. These maps usually include a noise-model through precomputation.

    detectionMap

    detection map of this landmark, contains log certainty of detecting landmark at every location

    renderer

    landmarks renderer to calculate landmarks position of current sample

11. class LandmarkPointEvaluator extends DistributionEvaluator[RenderParameter]

    

    likelihood evaluator for a single landmark position

12. class LandmarksInBoxEvaluator extends DistributionEvaluator[Seq[TLMSLandmark2D]]

    

    evaluate position of landmarks with respect to given box returns 0 if all landmarks are in box, else -infinity

13. class MappedImageRendererEvaluator[A] extends DistributionEvaluator[RenderParameter]

    

    evaluate the transformed, rendered image with given image evaluator

14. class TrimmedIndependentPixelEvaluator extends PairEvaluator[PixelImage[RGBA]]

    

    Ignore 1-alpha pixels with small likelihood.

    Ignore 1-alpha pixels with small likelihood. Evaluate only on alpha-fraction with the largest likelihood.

    visualizationCallback: gives you the log likelihood values per pixel. Could be used to visualze the values per pixel.