Improving Landmark Recognition using Saliency detection and Feature classification
This work addresses the problem of fine-grained landmark recognition for computer vision applications, but it is incremental as it builds upon existing methods like GBVS, kNN, and Random Forest.
The authors tackled fine-grained landmark recognition by proposing an ensemble network that combines saliency detection and feature classification, achieving robust classification on a new dataset with challenges like clutter and occlusion.
Image Landmark Recognition has been one of the most sought-after classification challenges in the field of vision and perception. After so many years of generic classification of buildings and monuments from images, people are now focussing upon fine-grained problems - recognizing the category of each building or monument. We proposed an ensemble network for the purpose of classification of Indian Landmark Images. To this end, our method gives robust classification by ensembling the predictions from Graph-Based Visual Saliency (GBVS) network alongwith supervised feature-based classification algorithms such as kNN and Random Forest. The final architecture is an adaptive learning of all the mentioned networks. The proposed network produces a reliable score to eliminate false category cases. Evaluation of our model was done on a new dataset, which involves challenges such as landmark clutter, variable scaling, partial occlusion, etc.