| dc.description.abstract | Ancient artifacts of Sri Lanka are
used as major sources of getting historical
information about Sri Lanka. Acquiring the
necessary information about those artifacts
become a huge challenge for the visitant of
artifacts. Text based search engines are
typically used to retrieve information about
ancient artifacts of Sri Lanka. These systems
require the user to formulate a text query
that provides information such as the place,
where the object is placed or where does that
can be found, what is the century object
belonged. Oppositely visual search systems
can be used. They provide information to
users of the system such as scholars, tourists,
local explores in a most intuitive and
immediate way by using an image as a query.
This research involves in developing a chat
application along with Convolutional Neural
Networks for image recognition of ancient
artifacts. The image recognition model will
be a part of the chat bot that has ability to
retrieve more information about recognized
images. Convolutional Neural Networks,
Recurrent Neural Network, TensorFlow,
Keras have been used as core technologies in
this research project. As the research
involves in developing a chat application
with image recognition capabilities, the
application will improve the knowledge
sharing of Sri Lankan ancient legacy to the
word in an effective way. | en_US |
