Stamps (2% of outliers version#10)

A data set representing forged (photocopied or scanned+printed) stamps and genuine (ink) stamps. The features are based on color and printing properties of the stamps. Forged stamps are considered to be outliers. The stamps data set is not taken from the UCI repository, but was used in [1].

References:

[1] B. Micenkova, J. van Beusekom, and F. Shafait. Stamp verification for automated document authentication. In 5th Int. Workshop on Computational Forensics, 2012.

Download all data set variants used (371.2 kB).

Normalized, without duplicates
Not normalized, without duplicates

Normalized, without duplicates

This version contains 9 attributes, 315 objects, 6 outliers (1.90%)

Download raw algorithm results (2.7 MB) Download raw algorithm evaluation table (39.9 kB)

Best Parameters

The following table contains the best (overall and per-method) results for each method and evaluation measure (when the same score was achieved twice, only the smallest k is given).
The Maximum F1-Measure is complimentary in addition to the measures in the original publication.

Algorithm	k	P@n	Adj. P@n	AP	Adj. AP	Max-F1	Adj. MF1	ROC AUC
KNN	1	0.16667	0.15049	0.19849	0.18293	0.38710	0.37520	0.95604
KNNW	1	0.16667	0.15049	0.22196	0.20686	0.42857	0.41748	0.96170
LOF	1	0.16667	0.15049	0.08497	0.06720	0.26667	0.25243	0.67503
LOF	4	0.16667	0.15049	0.14771	0.13116	0.22222	0.20712	0.91316
SimplifiedLOF	3	0.16667	0.15049	0.10083	0.08337	0.23529	0.22045	0.74595
SimplifiedLOF	6	0.16667	0.15049	0.11881	0.10170	0.21277	0.19748	0.90992
SimplifiedLOF	26	0.00000	-0.01942	0.10707	0.08973	0.25532	0.24086	0.91208
LoOP	3	0.16667	0.15049	0.22475	0.20970	0.28571	0.27184	0.72330
LoOP	26	0.00000	-0.01942	0.10800	0.09068	0.24490	0.23024	0.91046
LDOF	3	0.16667	0.15049	0.11336	0.09614	0.25000	0.23544	0.64455
LDOF	4	0.16667	0.15049	0.20409	0.18863	0.28571	0.27184	0.69525
LDOF	37	0.00000	-0.01942	0.10231	0.08488	0.25000	0.23544	0.90723
ODIN	32	0.00000	-0.01942	0.12119	0.10413	0.23529	0.22045	0.91505
ODIN	33	0.00000	-0.01942	0.11982	0.10273	0.23077	0.21583	0.91586
ODIN	50	0.16667	0.15049	0.09926	0.08177	0.19231	0.17662	0.87190
FastABOD	3	0.16667	0.15049	0.19221	0.17653	0.30769	0.29425	0.94498
FastABOD	4	0.00000	-0.01942	0.20273	0.18725	0.36364	0.35128	0.95685
FastABOD	6	0.00000	-0.01942	0.18032	0.16440	0.37500	0.36286	0.95200
KDEOS	3	0.16667	0.15049	0.05988	0.04162	0.20000	0.18447	0.50755
KDEOS	68	0.00000	-0.01942	0.12631	0.10935	0.26087	0.24652	0.92179
KDEOS	71	0.00000	-0.01942	0.12895	0.11203	0.24390	0.22922	0.92287
KDEOS	72	0.00000	-0.01942	0.12734	0.11039	0.25641	0.24197	0.92341
LDF	2	0.16667	0.15049	0.15237	0.13591	0.28571	0.27184	0.87325
LDF	3	0.16667	0.15049	0.19227	0.17659	0.33333	0.32039	0.94175
INFLO	1	0.16667	0.15049	0.09603	0.07847	0.22222	0.20712	0.66640
INFLO	4	0.16667	0.15049	0.21403	0.19877	0.28571	0.27184	0.73679
INFLO	24	0.00000	-0.01942	0.10303	0.08561	0.20513	0.18969	0.90129
COF	2	0.16667	0.15049	0.07141	0.05338	0.20000	0.18447	0.60572
COF	7	0.16667	0.15049	0.28650	0.27265	0.28571	0.27184	0.93204
COF	15	0.16667	0.15049	0.15922	0.14290	0.27273	0.25861	0.93743
COF	22	0.16667	0.15049	0.18468	0.16884	0.29630	0.28263	0.93743

Plots

Precision at n

Adjusted precision at n

Average precision

Adjusted average precision

Maximum F1 score

Adjusted maximum F1 score

ROC AUC

Diversity

A: KNN, B: KNNW, C: LOF, D: SimplifiedLOF, E: LoOP, F: LDOF
G: ODIN, H: KDEOS, I: COF, J: FastABOD, K: LDF, L: INFLO

Not normalized, without duplicates