Abstract
Searching through information based on a photograph, which may contain graphics and images, has become a popular trend, such as in electronic books, journals, and products. Although many context-based methods have been proposed to retrieve images, most work focuses on selecting appropriate features for different objects. In the present study, we apply sparse representation to simultaneously retrieve image and graphics from a photograph. The sparse vector can be regarded as the similarity between the query photograph and dataset. The image with the largest entry (or several largest entries) can be assigned as the retrieved result. In the sparse representation framework, the common image features are used. Experimental results demonstrate that if the similarity vector in photograph retrieval is sparse, feature extraction is no longer critical. Compared with similar works in photograph retrieval, the proposed method has better retrieval accuracy.
Highlights
Photograph retrieval is a key component in many Web and e-business applications such as searching electronic books, journals, and products, as well as related information retrieval, e.g., mobile visual research [1], e-learning systems [2], and modality recognition for medical images [3]
A near-neighbor search is applied for retrieval. In contrast to these works, we propose a more robust method based on sparse representation that. In contrast to these works, we propose a more robust method based on sparse representation does not need to classify images and graphics and chooses different features
Unlike exiting methods, which use feature-based sparse representation to build a dictionary for contend-based image retrieval, we directly use the image features as dictionary
Summary
Photograph retrieval is a key component in many Web and e-business applications such as searching electronic books, journals, and products, as well as related information retrieval, e.g., mobile visual research [1], e-learning systems [2], and modality recognition for medical images [3]. With the popularization of mobile devices, photographs have become a new and important method to record information. Photograph retrieval is critical in mobile visual research. In an e-learning system, students can learn remotely by watching videos, and important concepts and data are often presented using graphs and images. Students can use graphics and images in lecture videos as query to retrieve knowledge from an electronic database
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
