*******************************************************************************
Instruction for BSS1 (Nov. 5, 2012)
Yagi laboratory, Department of Intelligent Media
The Institute of Scientific and Industrial Research, Osaka University
http://www.am.sanken.osaka-u.ac.jp/index.html
*******************************************************************************

-------------------------------------------------------------------------------
1. Contents
-------------------------------------------------------------------------------

BSS1 is composed of dissimilarity score matrices from 1,936 probe subjects and 2015 gallery subjects, which is a subset of OULP-V1C1-B75 defined in [1]. The individual dissimilarity scores are computed from the following gait features, which are extracted from the silhouette sequences of each subject.

- BSS1_DissimilarityScoreMatrix_GEI.csv: GEI (gait energy image)

- BSS1_DissimilarityScoreMatrix_Period.csv: Period

- BSS1_DissimilarityScoreMatrix_Height.csv: Height


Moreover, the subject ID lists for probe and gallery were provided as follows, respectively.

- BSS1_ProbeIDList.csv

- BSS1_GalleryIDList.csv


Detailed procedures of preprocess and feature extraction are found in [1]. 

[1] H. Iwama, M. Okumura, Y. Makihara, and Y. Yagi, ``The OU-ISIR Gait Database Comprising the Large Population Dataset and Performance Evaluation of Gait Recognition,'' IEEE Trans. on Information Forensics and Security, Vol. 7, No. 5, pp. 1511-1521, Oct. 2012.


-------------------------------------------------------------------------------
2. Protocols
-------------------------------------------------------------------------------

-------------------------
2.1 Protocol 1 (BSS1-P1)
-------------------------

Three-dimensional dissimilarity scores from GEI, Period, and Height are fused in this protocol.

Subject ID lists for training (development) and test (evaluation) of the score-level fusion are provided as follows, respectively.

- BSS1_Protocol1_TrainingIDList.csv

- BSS1_Protocol1_TestIDList.csv

Based on the subject ID lists, sub-matrices of dissimilarity scores for training and test can be extracted for each of GEI, Period, and Height.