| Resumen |
Electro-mechanical meters are commonly used to
measure the consumption of utilities. There are basically two
kinds of analog meters: the ones that use rotary dials and the
ones with pointer-type dials. Former approaches have dealt with
the first kind of meters. Considering that reading the last ones can
be confusing, in this work we introduce a methodology to enable
the automatic reading of such devices. This methodology uses an
image acquired with a smartphone and by applying a sequence
of image processing functions finds and extracts the dials of such
meters. Then identifies the position of the pointers and a clever
implementation enables the reading. The proposed method was
tested with a database, getting promising results. The database
is composed with images taken under different light conditions,
perspectives and angles. |
