Amphora Detection Based on a Gradient Weighted Error in a Convolution Neuronal Network

Jérome Pasquet, Stella Demesticha, Dimitrios Skarlatos, Djamal Merad, Pierre Drap

Abstract

In this paper, we propose a method based on pixel prediction to detect objects into a large image. We propose to integrate theWeighted Error Layer (WEL) in a Convolution Neuronal Network (CNN) architecture in order to weight the error during the backpropagation and to reduce the impact of the borders. We estimate the orientation of the objects when the detection step is achieved. Our proposed layer is evaluated on real data in order to detect amphorae on the Mazatos underwater archaeological site.

Download

IMEKO-TC4-ARCHAEO-2017-135.pdf

DOI

-

IMEKO TC

TC4 - Measurement of Electrical Quantities

Back to the proceedings