BEAT - tpereira/lbphs_features

This algorithm is a legacy one. The API has changed since its implementation. New versions and forks will need to be updated.

This algorithm is splittable

Endpoint Groups 1

Algorithms have at least one input and one output. All algorithm endpoints are organized in groups. Groups are used by the platform to indicate which inputs and outputs are synchronized together. The first group is automatically synchronized with the channel defined by the block in which the algorithm is deployed.

Group: main

Endpoint Name	Data Format	Nature
image	system/array_3d_uint8/1	Input
eye_centers	system/eye_positions/1	Input
features	system/array_1d_floats/1	Output

Parameters 8

Parameters allow users to change the configuration of an algorithm when scheduling an experiment

Name	Description	Type	Default
lbp_neighbours	Number of neighbours considered for the LBP bin computation	uint32	8
left-eye-x	The horizontal position of the left eye (subject perspective) in the cropped image	uint32	48
left-eye-y	The vertical position of the left eye (subject perspective) in the cropped image	uint32	16
crop-height	The height of the cropped image	uint32	80
lbp_radius	Radius considered in the LBP bin computation	uint32	1
crop-width	The width of the cropped image	uint32	64
right-eye-x	The horizontal position of the right eye (subject perspective) in the cropped image	uint32	15
right-eye-y	The vertical position of the right eye (subject perspective) in the cropped image	uint32	16

import bob
import numpy

class Algorithm:

def setup(self, parameters):
        """Loads the parameters of the algorithm"""
        self.crop_height    = parameters.get('crop-height')
        self.crop_width     = parameters.get('crop-width')
        self.right_eye_y    = parameters.get('right-eye-y')
        self.right_eye_x    = parameters.get('right-eye-x')
        self.left_eye_y     = parameters.get('left-eye-y')
        self.left_eye_x     = parameters.get('left-eye-x')
        self.lbp_radius     = parameters.get('lbp_radius')
        self.lbp_neighbours = parameters.get('lbp_neighbours')

self.cropper = bob.ip.FaceEyesNorm(int(self.crop_height),
            int(self.crop_width), int(self.right_eye_y), int(self.right_eye_x),
            int(self.left_eye_y), int(self.left_eye_x))

#self.lbp_block_size = parameters.get('block-size')
        #self.lbp_block_overlap = parameters.get('block-overlap')

self.lbp_extractor = bob.ip.LBP(neighbors=int(self.lbp_neighbours), uniform=True, radius=float(self.lbp_radius))
        
        #self.lbp_extractor = bob.ip.LBPHSFeatures(
        #    int(self.lbp_block_size),
        #    int(self.lbp_block_size),
        #    int(self.lbp_block_overlap),
        #    int(self.lbp_block_overlap),
        #    bob.ip.LBP(8, 2., uniform=True)
        #)

return True

def process(self, inputs, outputs):
        """Processes an image by aligning the face and extracting LBPHS features.""" 
        image = bob.ip.rgb_to_gray(inputs["image"].data.value)
        eye_centers = inputs["eye_centers"].data

cropped_image = self.cropper(image, float(eye_centers.right.y),
            float(eye_centers.right.x), float(eye_centers.left.y),
            float(eye_centers.left.x))

lbpimage = numpy.ndarray(self.lbp_extractor.get_lbp_shape(cropped_image), 'uint16') # allocating the image with lbp codes
        self.lbp_extractor(cropped_image, lbpimage) # calculating the lbp image
        features = bob.ip.histogram(lbpimage, 0, self.lbp_extractor.max_label-1, self.lbp_extractor.max_label).astype('float')
        features /= sum(features) #normalizing

outputs["features"].write({
          "value" : features
        })

return True

The code for this algorithm in Python
The ruler at 80 columns indicate suggested POSIX line breaks (for readability).
The editor will automatically enlarge to accomodate the entirety of your input
Use keyboard shortcuts for search/replace and faster editing. For example, use Ctrl-F (PC) or Cmd-F (Mac) to search through this box

This algorithms extracts Local Binary Pattern Histogram Sequence (LBPHS) features as introduced by [Ahonen04]. First, the image is aligned accorsing to the hand-labeled eye locations. Then, uniform circular Local Binary Patterns (LBPs) [Ojala96] are extracted from the aligned image. Afterwards, the image is split into (possibly overlapping) blocks, and a local histogram of LBP features is extracted for each block. Finally, all histograms are concatenated to form the full LBPHS feature vector.

[Ojala96]

Ojala, M. Pietikainen, D. Harwood: A comparative study of texture measures with classification based on feature distributions. Pattern Recognition 29 (1996) 51-59

[Ahonen04]

Ahonen, A. Hadid, M. Pietikainen: Face Recognition with Local Binary Patterns. ECCV (1) 2004: 469-481

Experiments

Attestation:

Privacy:

Status:

			Updated	Name	Databases/Protocols	Analyzers
				tpereira/tutorial/full_lbphs/2/btas2015_LBP-baseline_periocular_mobio-male_det	mobio/1@male	tutorial/eerhter_postperf_iso/1
				tpereira/tutorial/full_lbphs/2/btas2015_LBP-baseline_periocular_mobio-female_det	mobio/1@female	tutorial/eerhter_postperf_iso/1

This table shows the number of times this algorithm has been successfully run using the given environment. Note this does not provide sufficient information to evaluate if the algorithm will run when submitted to different conditions.

algorithms tpereira lbphs_features_1block 7

Endpoint Groups 1

Group: main

Parameters 8

Experiments

algorithms

tpereira

lbphs_features_1block

7