A Hybrid Approach for Landmark Recognition using Deep Local Features and Residual Network-50
As smartphones and mobile data become universal in modern society, the opportunities to interact with the real world would grow tremendously. Latest Technologies such as Oculus Rift and Google Glass attempt to bridge the gap between the virtual and the material. With advancements in computing speed...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2021-01-01
|
| Series: | ITM Web of Conferences |
| Subjects: | |
| Online Access: | https://www.itm-conferences.org/articles/itmconf/pdf/2021/05/itmconf_icacc2021_02001.pdf |
| _version_ | 1819112424144371712 |
|---|---|
| author | Nimbare Nishant Shah Parth Shah Shail Mangrulkar Ramchandra |
| author_facet | Nimbare Nishant Shah Parth Shah Shail Mangrulkar Ramchandra |
| author_sort | Nimbare Nishant |
| collection | DOAJ |
| description | As smartphones and mobile data become universal in modern society, the opportunities to interact with the real world would grow tremendously. Latest Technologies such as Oculus Rift and Google Glass attempt to bridge the gap between the virtual and the material. With advancements in computing speed and image recognition, the idea of augmented reality (AR) becomes more tangible. However, the sheer complexity of image processing and feature recognition is an area of concern for AR. A successful AR system must distinguish among many landmarks and identify or classify the existence of new landmarks. AR algorithms naturally lend themselves to using deep learning because of the adaptability required to various factors. This paper aims to develop and refine a deep learning algorithm that can distinguish landmarks from images using a google landmark database of known landmarks. Instance-level recognition is universally used in areas of Landmark recognition and is also the upcoming research area. Instance-level recognition is the brain behind Landmark recognition. As in Landmarks, the goal is to seek an instance of a common group instead of a group, requiring new deep learning techniques. In this paper, three different VGG16, Inceptionv3, and ResNet50 models are trained using the transfer learning technique and a Pure Convolutional Neural Network (CNN) model is also trained from scratch. This paper proposes a modified version of the ResNet50 model to increase the accuracy and performance of the models used. The revised version of Resnet50 contains an additional Deep Local Features (DeLF) processing layer before generating the final output. |
| first_indexed | 2024-12-22T04:13:17Z |
| format | Article |
| id | doaj.art-e4a1f2a642524203bd4c1c5656bd0527 |
| institution | Directory Open Access Journal |
| issn | 2271-2097 |
| language | English |
| last_indexed | 2024-12-22T04:13:17Z |
| publishDate | 2021-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | ITM Web of Conferences |
| spelling | doaj.art-e4a1f2a642524203bd4c1c5656bd05272022-12-21T18:39:29ZengEDP SciencesITM Web of Conferences2271-20972021-01-01400200110.1051/itmconf/20214002001itmconf_icacc2021_02001A Hybrid Approach for Landmark Recognition using Deep Local Features and Residual Network-50Nimbare NishantShah ParthShah ShailMangrulkar RamchandraAs smartphones and mobile data become universal in modern society, the opportunities to interact with the real world would grow tremendously. Latest Technologies such as Oculus Rift and Google Glass attempt to bridge the gap between the virtual and the material. With advancements in computing speed and image recognition, the idea of augmented reality (AR) becomes more tangible. However, the sheer complexity of image processing and feature recognition is an area of concern for AR. A successful AR system must distinguish among many landmarks and identify or classify the existence of new landmarks. AR algorithms naturally lend themselves to using deep learning because of the adaptability required to various factors. This paper aims to develop and refine a deep learning algorithm that can distinguish landmarks from images using a google landmark database of known landmarks. Instance-level recognition is universally used in areas of Landmark recognition and is also the upcoming research area. Instance-level recognition is the brain behind Landmark recognition. As in Landmarks, the goal is to seek an instance of a common group instead of a group, requiring new deep learning techniques. In this paper, three different VGG16, Inceptionv3, and ResNet50 models are trained using the transfer learning technique and a Pure Convolutional Neural Network (CNN) model is also trained from scratch. This paper proposes a modified version of the ResNet50 model to increase the accuracy and performance of the models used. The revised version of Resnet50 contains an additional Deep Local Features (DeLF) processing layer before generating the final output.https://www.itm-conferences.org/articles/itmconf/pdf/2021/05/itmconf_icacc2021_02001.pdflandmark recognitiondelfresnet50transfer learningcnninceptionv3vgg16instance-level recognition |
| spellingShingle | Nimbare Nishant Shah Parth Shah Shail Mangrulkar Ramchandra A Hybrid Approach for Landmark Recognition using Deep Local Features and Residual Network-50 ITM Web of Conferences landmark recognition delf resnet50 transfer learning cnn inceptionv3 vgg16 instance-level recognition |
| title | A Hybrid Approach for Landmark Recognition using Deep Local Features and Residual Network-50 |
| title_full | A Hybrid Approach for Landmark Recognition using Deep Local Features and Residual Network-50 |
| title_fullStr | A Hybrid Approach for Landmark Recognition using Deep Local Features and Residual Network-50 |
| title_full_unstemmed | A Hybrid Approach for Landmark Recognition using Deep Local Features and Residual Network-50 |
| title_short | A Hybrid Approach for Landmark Recognition using Deep Local Features and Residual Network-50 |
| title_sort | hybrid approach for landmark recognition using deep local features and residual network 50 |
| topic | landmark recognition delf resnet50 transfer learning cnn inceptionv3 vgg16 instance-level recognition |
| url | https://www.itm-conferences.org/articles/itmconf/pdf/2021/05/itmconf_icacc2021_02001.pdf |
| work_keys_str_mv | AT nimbarenishant ahybridapproachforlandmarkrecognitionusingdeeplocalfeaturesandresidualnetwork50 AT shahparth ahybridapproachforlandmarkrecognitionusingdeeplocalfeaturesandresidualnetwork50 AT shahshail ahybridapproachforlandmarkrecognitionusingdeeplocalfeaturesandresidualnetwork50 AT mangrulkarramchandra ahybridapproachforlandmarkrecognitionusingdeeplocalfeaturesandresidualnetwork50 AT nimbarenishant hybridapproachforlandmarkrecognitionusingdeeplocalfeaturesandresidualnetwork50 AT shahparth hybridapproachforlandmarkrecognitionusingdeeplocalfeaturesandresidualnetwork50 AT shahshail hybridapproachforlandmarkrecognitionusingdeeplocalfeaturesandresidualnetwork50 AT mangrulkarramchandra hybridapproachforlandmarkrecognitionusingdeeplocalfeaturesandresidualnetwork50 |