Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/363458
Title: | Design and Development of Content Based Image Retrieval Techniques for Mobile Applications |
Researcher: | Aiswarya K. S. |
Guide(s): | N. Santhi |
Keywords: | Engineering Engineering and Technology Engineering Electrical and Electronic |
University: | Noorul Islam Centre for Higher Education |
Completed Date: | 2021 |
Abstract: | Content-based image retrieval (CBIR) has become an important research topic in the last two decades. Several application-specific image retrieval systems have been proposed recently, and Mobile image retrieval is particularly a hot topic among these latest trends. We proposed a CBIR system for Retrieving mobile-based scalable images using a position scale orientation-scale invariant feature transform algorithm. Here, the key points are explored by using a novel scalable mobile image retrieval technique using the PSO SIFT (Position Scale Orientation Scale Invariant Feature Transform) algorithm. The main aim is to find relevant information by exploring the key points from a group of images than using one input image. The proposed method then mines similar images based on the saliency from a group of images and then calculates the key features for image retrieval. newline Also, a modified version of mobile image retrieval by using PSO SIFT algorithm and Contextual Saliency is proposed. Principal component analysis has been used here for dimensionality reduction by filtering prominent features, and the image similarity search is computed over this feature space. The model also uses multiple appropriate images similar to the query image from the device database by extracting visual information based contextual saliency. Identifying appropriate images for retrieval can help to find suitable image features and could reduce the bandwidth requirement by limiting the number of transmitted features. This technique also helped to increase the retrieval performance. newline By considering the success of automated feature extraction methods, we proposed a CBIR technique that uses a multi-level stacked autoencoder for feature selection and dimensionality reduction. The approach uses feature descriptors derived from a stacked autoencoder where both the abstract feature extraction and the dimensionality reduction are handled simultaneously. A query image space is created first before the actual retrieval process by combining the |
Pagination: | 3752 kb |
URI: | http://hdl.handle.net/10603/363458 |
Appears in Departments: | Department of Electronics and Communication Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
80_recommendation.pdf | Attached File | 134.67 kB | Adobe PDF | View/Open |
certificate.pdf | 499.5 kB | Adobe PDF | View/Open | |
chapter 1.pdf | 195.22 kB | Adobe PDF | View/Open | |
chapter 2.pdf | 211.43 kB | Adobe PDF | View/Open | |
chapter 3.pdf | 981.53 kB | Adobe PDF | View/Open | |
chapter 4.pdf | 837.54 kB | Adobe PDF | View/Open | |
chapter 5.pdf | 525.66 kB | Adobe PDF | View/Open | |
chapter 6.pdf | 737.38 kB | Adobe PDF | View/Open | |
chapter 7.pdf | 99.73 kB | Adobe PDF | View/Open | |
front page.pdf | 254.45 kB | Adobe PDF | View/Open | |
list of publications based on thesis.pdf | 58.8 kB | Adobe PDF | View/Open | |
references.pdf | 119.55 kB | Adobe PDF | View/Open | |
table of contents.pdf | 346.88 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: