Mathematical Problems in Engineering / 2016 / Article / Tab 2

Research Article

Color, Scale, and Rotation Independent Multiple License Plates Detection in Videos and Still Images

Table 2

Performance comparison of the proposed LP detection method with few of the competitive LP detection methods from the literature.

Algorithm and referencesData setNumber of images in data setTypes of vehicles present in data setLP detection rate

CIP [3]Proprietary80Cars91.25%
ESM [4]Proprietary9825Vans, trucks, cars99.6%
FCC [5]Proprietary150Not reported95.3%
SCW [6]Media-lab (proprietary)1334Vans, trucks, cars96.5%
RTR [7]Proprietary400Not reported83.5%
RTR [7]Caltech1999Cars84.8%
SWHVP [8]Proprietary522Motorcycles97.55%
Two pass [9]Proprietary9026Cars, trucks97.16%
RELIP [10]Proprietary100Not reported97%
PVW [11]Proprietary410Not reported93.2%
VEDA [12]Proprietary664Cars91.65%
AOLP [13]Media-lab741Vans, trucks, cars92.1%
AOLP [13]AOLP (proprietary)2049Cars and vans93.33%
DIP-GA [14]Proprietary800Vans, trucks, cars98.75%
DIP-GA [14]Media-lab335Vans, trucks, cars97.61%
Proposed geometry-based clustering methodMedia-lab741Vans, trucks, cars97.3%
Proposed geometry-based clustering methodProprietary159Cars, trucks, motorcycles98.74%
Proposed geometry-based clustering methodMedia-lab and proprietary900Vans, trucks, cars, motorcycles97.56%
Proposed geometry-based clustering methodAOLP2049Cars and vans93.7%

Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.