Geo-Landmark Recognition and Detection
Nishika Manira1, Swelia Monteiro2, Tashya Alberto3, Tracy Niasso4, Supriya Patil5
1Nishika Manira*, Department of Electronics & Telecommunication Engineering at Padre Conceicao College of Engineering, Verna, Goa, India.
2Swelia Monteiro, Department of Electronics & Telecommunication Engineering at Padre Conceicao College of Engineering, Verna, Goa, India.
3Tashya Alberto, Department of Electronics & Telecommunication Engineering at Padre Conceicao College of Engineering, Verna, Goa, India.
4Tracy Niasso, Department of Electronics & Telecommunication Engineering at Padre Conceicao College of Engineering, Verna, Goa, India.
5Dr. Supriya Patil, Associate professor in Electronics and Telecommunication Engineering Department at Padre Conceicao College of Engineering, Verna, Goa, India.
Manuscript received on May 17, 2021. | Revised Manuscript received on May 22, 2021. | Manuscript published on May 30, 2021. | PP: 95-98 | Volume-10 Issue-7, May 2021 | Retrieval Number: 100.1/ijitee.G89830510721| DOI: 10.35940/ijitee.G8983.0510721
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The widespread use of smartphones and mobile data in the present-day society has exponentially led to the interaction with the physical world. The increase in the amount of image data in web and mobile applications makes image search slow and inaccurate. Landmark recognition, an image retrieval task, faces its challenges due to the uncommon structure it possesses, such as, buildings, cathedrals, castles or museums. These are shot from various angles which are often different from each other, for instance, the exterior and interior of a landmark. This paper makes use of a Convolutional Neural Networks (CNN) based efficient recognition system that serves in navigation, to organize photo collections, identify fake reports and unlabeled landmarks from historical data. It identifies landmarks correctly from a variety of images taken at different viewpoints as well as distances. An appropriate CNN architecture helps to provide the best solution for the currently selected dataset.
Keywords: Convolutional Neural Networks (CNN), Faster Region Based CNN (Faster RCNN), Histogram of Oriented Gradients (HOG), Rectified Linear Unit (ReLU), Region of Interest (RoI), Region Proposal Network (RPN), Residual Networks (ResNet), Visual Geometry Group (VGG).