A context-aware semantic modeling framework for efficient image retrieval
- PDF / 2,005,771 Bytes
- 27 Pages / 595.276 x 790.866 pts Page_size
- 28 Downloads / 234 Views
ORIGINAL ARTICLE
A context-aware semantic modeling framework for efficient image retrieval K. S. Arun1 • V. K. Govindan1
Received: 8 April 2015 / Accepted: 18 January 2016 Ó Springer-Verlag Berlin Heidelberg 2016
Abstract In recent years, high-level image representation is gaining popularity in image classification and retrieval tasks. This paper proposes an efficient scheme known as semantic context model to derive high-level image descriptors well suited for the retrieval operation. Semantic context model uses an undirected graphical model based formulation which jointly exploits low-level visual features and contextual information for classifying local image blocks into some predefined concept classes. Contextual information involves concept co-occurrences and their spatial correlation statistics. More expressive potential functions are introduced to capture the structural dependencies among various semantic concepts. The proposed framework proceeds in three steps. Initially, optimal values of model parameters that impose spatial consistency of concept labels among local image blocks are learned from the training data. Then, the semantics associated with the constituent blocks of an unseen image are inferred using an improved message-passing algorithm. Finally, a compact but discriminative image signature is derived by integrating the frequency of occurrence of various regional semantics. Experimental results on various benchmark datasets show that semantic context model can effectively resolve local ambiguities and consequently improve concept recognition performance in complex images. Moreover, the retrieval efficiency of the new semantics based image feature is found to be much better than state-of-the-art approaches. & K. S. Arun [email protected] V. K. Govindan [email protected] 1
Department of Computer Science and Engineering, National Institute of Technology, Calicut, India
Keywords Image retrieval Semantic gap Contextual information Graphical models
1 Introduction In past few years, there has been exponential increase in the size of image databases due to the acceptance and wide usage of various digital imaging techniques. Such image collections will be worthless unless there are some intelligent mechanisms to efficiently manage these large volumes of digital image data. Recently, content based image retrieval (CBIR) has been evolved as an efficient mechanism towards this end. In general, traditional CBIR frameworks involves the design of automated procedures for extracting various low-level visual features such as color, texture, shape etc. by directly analysing image pixels to facilitate the search and the retrieval of desired images from a given repository. Unfortunately, the performance of most CBIR systems are inherently constrained by the lowlevel visual features because they often fail to capture the high-level semantics perceived by humans. This is known as the semantic gap problem in image retrieval. Nowadays, semantics-based image modeling appears to be an effective solution for mini
Data Loading...
