Abstract
In recent times, large-scale content-based face image retrieval has grown up with rapid improvement and it is an enabling technology for many emerging applications. Content based face image retrieval is done by computing the similarity between images in the databases and the input/query face image. Content based face image retrieval systems retrieves the image only using low level features therefore the retrieval rate is low in this system. To improve the retrieval rate sparse codeword based scalable face image retrieval system is developed. This system uses both low level features and high level human attributes. The proposed system has several stages to retrieve the images; 1. Low level features are extracted using LTP descriptor and utilize the automatically detected high level human attributes such as hair, Gender and race. 2. Sparse codeword techniques are applied on the low level features and attributes to generate the codeword. 3. The third stage is an indexing; in the indexing attribute embedded inverted indexing method is used. Using the methods mentioned above, face image retrieval system has achieved promising retrieval result. Experiment is conducted on different dataset such as pub fig, LFW and FERET. Among those dataset LFW dataset achieve higher performance.
Highlights
A day the popularity of social networks like Face book, Twitter, Flickr are mostly used by the people
CBIR refers to techniques used to index and retrieve images from databases based on their visual content
The low level features are extracted using Local Ternary pattern (LTP) and two methods are used in this study
Summary
A day the popularity of social networks like Face book, Twitter, Flickr are mostly used by the people. Visual content is typically defined by a set of low level features extracted from an image that describe the colour, texture and/or shape of the entire image It is an enabling technology for many applications such as automatic face annotation and crime investigation. Eng. Technol., 8(22): 2265-2271, 2014 using high level features that is people attributes to construct sparse codeword for the face image retrieval task. A component-based local binary pattern (LBP), is used as a well known feature for face recognition (Ahonen et al, 2004) combined with sparse coding and partial identity information to construct semantic codeword’s for content-based face image retrieval. Geometric feature based recognition techniques are invariant to similarity transformations, robust enough to withstand pose, illumination and expression changes in face. The Experiment is conducted and demonstrates the performances of the proposed work in LFW dataset
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
