Mathematical Problems in Engineering / 2019 / Article / Tab 1

Research Article

EL: Local Image Descriptor Based on Extreme Responses to Partial Derivatives of 2D Gaussian Function

Table 1

Verification, matching, and retrieval results obtained for the EL, SIFT, and RootSIFT descriptor, and the deep-learning-based descriptors DC-S and DC-S2S [18], DDESC [19], and TF-M and TF-R [20]. All results are reported in mAP(%). The scores are given in pairs. The first value represents the score obtained with the basic method and the second with its ZCA variant [26]. Best result in a column is given in bold.

Basic, ZCABasic, ZCABasic, ZCA

SIFT65.12, 74.3525.47, 32.7631.98, 40.36
RootSIFT58.53, 76.7027.22, 36.7733.65, 43.84
DC-S70.04, 81.6324.92, 31.6534.84, 39.68
DC-S2S78.23, 83.0327.69, 32.3434.76, 38.23
DDESC79.51, 81.6528.05, 35.4439.83, 44.55
TF-M81.90, 82.6930.61, 34.2939.40, 40.02
TF-R81.92, 83.2432.64, 34.3737.69, 40.23
EL73.36, 79.9936.92, 43.0040.68, 48.12

We are committed to sharing findings related to COVID-19 as quickly and safely as possible. Any author submitting a COVID-19 paper should notify us at to ensure their research is fast-tracked and made available on a preprint server as soon as possible. We will be providing unlimited waivers of publication charges for accepted articles related to COVID-19. Sign up here as a reviewer to help fast-track new submissions.