Welcome to the Bahria University DSpace digital repository. DSpace is a digital service that collects, preserves, and distributes digital material. Repositories are important tools for preserving an organization's legacy; they facilitate digital preservation and scholarly communication.
dc.contributor.author | Khubaib, Muhammad Reg # 43705 | |
dc.contributor.author | Farooqui, Maria Masood Reg # 43724 | |
dc.contributor.author | Khan, Muhammad Owais Reg # 43735 | |
dc.date.accessioned | 2023-03-20T05:55:16Z | |
dc.date.available | 2023-03-20T05:55:16Z | |
dc.date.issued | 2019 | |
dc.identifier.uri | http://hdl.handle.net/123456789/15239 | |
dc.description | Supervised by Aniqa Naeem | en_US |
dc.description.abstract | In this report we give a briefoverview ofthe different methods used for image retrieval model implementing the Convolutional Neural Network (CNN) and propose a new architecture. This model is designed on the test case of landmark images as it is made in the research and implementation for an image retrieval software for the same test The basic idea behind this research is to develop a system that can retrieve I case. information about a landmark when an image is given as input. This type of system will help tourists and explorers in learning more about the different famous landmarks and monuments of the world. The objective of this system is to develop an image of famous monuments and landmarks. recognition procedure to recognise images Different segments/levels ofimage recognition and processing are used including pre processing and model of Convolutional Neural Network which is a type Artificial Neural Networks (ANN). The best thing about this technique detection and extraction and the finally its recognition. For research purposes we have studied and worked on different models of Convolutional Neural Networks (CNNs) is its brilliance in feature on different discussed briefly. According to the tests conducted which will be further CNNs we have concluded that ourself-proposed model has given more accurate results small database, the lower the on our dataset as the deeper the CNN model gets, on a accuracy is. In this report we give a briefoverview ofthe different methods used for image retrieval model implementing the Convolutional Neural Network (CNN) and propose a new architecture. This model is designed on the test case of landmark images as it is made in the research and implementation for an image retrieval software for the same test The basic idea behind this research is to develop a system that can retrieve I case. information about a landmark when an image is given as input. This type of system will help tourists and explorers in learning more about the different famous landmarks and monuments of the world. The objective of this system is to develop an image of famous monuments and landmarks. recognition procedure to recognise images Different segments/levels ofimage recognition and processing are used including pre processing and model of Convolutional Neural Network which is a type Artificial Neural Networks (ANN). The best thing about this technique detection and extraction and the finally its recognition. For research purposes we have studied and worked on different models of Convolutional Neural Networks (CNNs) is its brilliance in feature on different discussed briefly. According to the tests conducted which will be further CNNs we have concluded that ourself-proposed model has given more accurate results small database, the lower the on our dataset as the deeper the CNN model gets, on a accuracy is. | en_US |
dc.language.iso | en_US | en_US |
dc.publisher | Bahria University Karachi Campus | en_US |
dc.relation.ispartofseries | BSCS;MFN BSCS 210 | |
dc.title | LANDMARK RETRIEVAL SYSTEM | en_US |
dc.type | Project Reports | en_US |