TanTriggs image preprocessing for face recognition

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

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.

Unnamed group

Endpoint Name Data Format Nature
image_gray system/array_2d_uint8/1 Input
tantriggs_image system/array_2d_uint8/1 Output

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

Name Description Type Default Range/Choices
sigma0 float64 1.0
sigma1 float64 2.0
gamma float64 0.2
kernel_size uint32 5
threshold float64 10.0
alpha float64 0.1

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 algorithm is a multi-stage image preprocessor relying on the Bob library. It implements the multi-stage preprocessing method described in [Tan07], the steps being a gamma correction, a difference of Gaussian filtering and a contrast equalization

Both inputs and outputs are expected to be grayscale images as two-dimensional arrays of floats (64 bits).

[Tan07]
  1. Tan, B. Triggs: Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions. Analysis and Modeling of Faces and Gestures (2007) 168-182

Experiments

Updated Name Databases/Protocols Analyzers
smarcel/chichan/full_pre_mlbphs_projection/2/mobio-f_TT_MLBPH_PCA98_LDA300_postperf-iso mobio/2@female tutorial/eerhter_postperf_iso/1
smarcel/chichan/full_pre_mlbphs_projection/2/mobio-m_TT_MLBPH_PCA98_LDA300_postperf-iso mobio/2@male tutorial/eerhter_postperf_iso/1
smarcel/chichan/full_pre_mlbphs_projection/2/mobio-m_TT_MLBPH_PCA98_postperf-iso mobio/2@male tutorial/eerhter_postperf_iso/1
smarcel/chichan/full_pre_mlbphs_projection/2/mobio-f_TT_MLBPH_PCA98_postperf-iso mobio/2@female tutorial/eerhter_postperf_iso/1
chichan/chichan/full_pre_mlbphs_projection/2/Prep_MLBPH_XM2VTS_nouniform_PCA xm2vts/1@darkened-lp1,xm2vts/1@lp1 tutorial/eerhter_postperf/1
chichan/chichan/full_pre_mlbphs_projection/2/Prep_MLBPH_XM2VTS_LDA xm2vts/1@darkened-lp1,xm2vts/1@lp1 tutorial/eerhter_postperf/1
chichan/chichan/full_pre_mlbphs_projection/2/Prep_MLBPH_XM2VTS_no_uniform_p98LDA xm2vts/1@darkened-lp1,xm2vts/1@lp1 tutorial/eerhter_postperf/1
chichan/chichan/full_pre_mlbphs_projection/2/Prep_MLBPH_XM2VTS_PCA xm2vts/1@darkened-lp1,xm2vts/1@lp1 tutorial/eerhter_postperf/1
smarcel/tutorial/full_isv/2/mobio_male-gmm_100Gx10I-isv_50Ux10Ix4R-dct_12Bx8Ox45C-seed101 mobio/1@male tutorial/eerhter_postperf_iso/1
tutorial/tutorial/full_isv/2/bancaMc_isv_DCT12x8_100G_U50 banca/1@Mc tutorial/eerhter_postperf_iso/1
tutorial/tutorial/full_isv/2/xm2vtsLp1_isv_DCT12x8_100G_U50 xm2vts/1@lp1 tutorial/eerhter_postperf_iso/1
tutorial/tutorial/full_isv/2/mobioMale_isv_DCT12x8_100G_U50 mobio/1@male tutorial/eerhter_postperf_iso/1
tutorial/tutorial/full_isv/2/bancaP_isv_DCT12x8_100G_U50 banca/1@P tutorial/eerhter_postperf_iso/1
tutorial/tutorial/full_isv/2/atnt_isv_DCT12x8_100G_U50 atnt/1@idiap_test_eyepos 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.

Terms of Service | Contact Information | BEAT platform version 1.3.1rc1 | © Idiap Research Institute - 2013-2019