ATiTHi: A Deep Learning Approach for Tourist Destination Classification using Hybrid Parametric Optimization

Abstract

A picture is best way to explore the tourist destination by visual content. The content-based image classification of tourist destinations makes it possible to understand the tourism liking by providing a more satisfactory tour. It also provides an important reference for tourist destination marketing. To enhance the competitiveness of the tourism market in India, this research proposes an innovative tourist spot identification mechanism by identifying the content of significant numbers of tourist photos using convolutional neural network (CNN) approach. It overcomes the limitations of manual approaches by recognizing visual information in photos. In this study, six thousand photos from different tourist destinations of India were identified and categorized into six major categories to form a new dataset of Indian Trajectory. This research employed Transfer learning (TF) strategies which help to obtain a good performance measure with very small dataset for image classification.VGG-16, VGG-19, MobileNetV2, InceptionV3, ResNet-50 and AlexNet CNN model with pretrained weight from ImageNet dataset was used for initialization and then an adapted classifier was used to classify tourist destination images from the newly prepared dataset. Hybrid hyperparameter optimization employ to find out hyperparameter for proposed Atithi model which lead to more efficient model in classification. To analyse and compare the performance of the models, known performance indicators were selected. As compared to the AlexNet model (0.83), MobileNetV2(0.93), VGG-19(0.918), InceptionV3(0.89), ResNet-50(0.852) the VGG16 model has performed the best in terms of accuracy (0.95). These results show the effectiveness of the current model in tourist destination image classification.