Abstract:
Tourism plays significant role for enhancing economic potential worldwide. The natural beauty
and historical interests of Bangladesh remarked as a major tourist destination for the
international tourists. In this study, we target to propose a Machine learning based application to
recognize historical interests and tourist spots from an images. Making use of on-device Neural
Engine comes with modern devices makes the application robust and internet free user
experience. One of the difficult tasks to collect real images from tourist sites. Our collected
images were in different sizes because of using different smartphones. We used following
machine learning algorithms– Convolution Neural Network (CNN), Support Vector Machine
(SVM), Long Short-Term Memory (LSTM), K-Nearest Neighbor (KNN) and Recurrent Neural
Network (RNN). In this proposed framework, tourists can effortlessly detect their targeted places
that can boost the tourism sector of Bangladesh. For this regard, Convolutional Neural Network
(CNN) achieved best accuracy.