Copyright © All rights reserved micansinfotech.com
Scalable image search based on visual similarity has been an active topic of research in recent years. State-of-the-art solutions often use hashing methods to embed high-dimensional image features into Hamming space, where search can be performed in real-time based on Hamming distance of compact hash codes. Unlike traditional metrics (e.g., Euclidean) that offer continuous distances, the Hamming distances are discrete integer values. As a consequence, there are often a large number of images sharing equal Hamming distances to a query, which largely hurts search results where fine-grained ranking is very important. This paper introduces an approach that enables query-adaptive ranking of the returned images with equal Hamming distances to the queries. This is achieved by firstly offline learning bitwise weights of the hash codes for a diverse set of predefined semantic concept classes. We formulate the weight learning process as a quadratic programming problem that minimizes intra-class distance while preserving inter-class relationship captured by original raw image features. Query-adaptive weights are then computed online by evaluating the proximity between a query and the semantic concept classes. With the query-adaptive bitwise weights, returned images can be easily ordered by weighted Hamming distance at a finer-grained hash code level rather than the original Hamming distance level. Experiments on a Flickr image dataset show clear improvements from our proposed approach.
The user login and register for the specific image query search and they are provided key to login, if the entered key and user key are same then they can login with admin permission.
In this module, the user can give query based on their respective idea.Then the given query image feature is extracted and they are embedding hash codes into that query image.By extracting features it simplifies the amount of resources required to describe a large set of data accurately.( Feature extraction is a special form of dimensionality reduction).In this work we represent images using the popular bag-of-vi-sual-words (BoW) framework, where local invariant image descriptors (e.g., SIFT) are extracted and quantized based on a set of visual words. The BoW features are then embedded into compact hash codes for efficient search.
In this module, we generate and embed images with hash codes (If two objects are equal according to the equals (Object) method, then calling the hash Code method on each of the two objects must produce the same integer result.)The embedded hash codes generate 2 types of hash codes. General hash code(usual hash code for particular image group) Class specific hash code(it is specific for image in that group)
In this module, we extend the framework for query-adaptive hash code selection. The se-mantic concept classes are used to infer query semantics, which guides the selection of a good set of hash codes for the query, and the computation of corresponding query-adaptive weights on the chosen hash codes. e selected class-specific codes are used together with the general codes for image search.
And then we save images to database based on the hash code and query of the user, and they are retrieved from the database.Query adaptive weights will be based on both general and class specific codesThe hash code is then used to predict query-adaptive bitwise weights (we generate query-adaptive bitwise weights using algorithm) by harnessing a set of semantic concept classes with pre-computed class-specific bitwise weights.Finally, the query-adaptive weights are applied to rank search results using weighted (query-adaptive) Hamming distance
While traditional image search engines heavily rely on textual words associated to the images, scalable content-based search is receiving increasing attention. Apart from providing better image search experience for ordinary Web users, large-scale similar image search has also been demonstrated to be very helpful for solving a number of very hard problems in computer vision and multimedia such as image categorization.
In this work we represent images using the popular bag-of-visual-words (BoW) framework, where local invariant image descriptors (e.g., SIFT) are extracted and quantized based on a set of visual words. The BoW features are then embedded into compact hash codes for efficient search. For this, we consider state-of-the-art techniques including semi-supervised hashing and semantic hashing with deep belief networks. Hashing is preferable over tree-based indexing structures (e.g., kd-tree) as it generally requires greatly reduced memory and also works better for high-dimensional samples.
With the hash codes, image similarity can be efficiently measured (using logical XOR operations) in Hamming space by Hamming distance, an integer value obtained by counting the number of bits at which the binary values are different. In large scale applications, the dimension of Hamming space is usually set as a small number (e.g., less than a hundred) to reduce memory cost and avoid low recall.
We have presented a novel framework for query-adaptive image search with hash codes. By harnessing a large set of predefined semantic concept classes, our approach is able to predict query-adaptive bitwise weights of hash codes in real-time, with which search results can be rapidly ranked by weighted Hamming distance at finer-grained hash code level. This capability largely alleviates the effect of a coarse ranking problem that is common in hashing-based image search. Experimental results on a widely adopted Flickr image dataset confirmed the effectiveness of our proposal.
To answer the question of “how much performance gain can class-specific hash codes offer?”, we further extended our framework for query-adaptive hash code selection. Our findings indicate that the class-specific codes can further improve search performance significantly. One drawback, nevertheless, is that nontrivial extra memory is required by the use of additional class-specific codes, and therefore we recommend careful examination of the actual application needs and hardware environment in order to decide whether this extension could be adopted.