Guest Editorial: Special Issue on Recent Advances in Content Analysis for Media Computing (original) (raw)
Related papers
Learning in Region-Based Image Retrieval
Lecture Notes in Computer Science, 2003
In this paper, several effective learning algorithms using global i mage representations are adjusted and introduced to region-based image retrieval (RBIR). First, the query point movement technique is considered. By assembling all the segmented regions of positive examples together and resizing the regions to emphasize the latest positive examples, a composite image is formed as the new query. Second, the application of support vector machines (SVM) in relevance feedback for RBIR is investigated. Both the one class SVM as a class distribution estimator and two classes SVM as a classifier are taken into account. For the latter, two representative display strategies are studied. Last, a region reweighting algorithm is proposed inspired by those feature re-weighting ones. Experimental results on a database of 10,000 general-purpose images demonstrate the effectiv eness of the proposed learning algorithms.
Relevance Feedback in Region-Based Image Retrieval
IEEE Transactions on Circuits and Systems for Video Technology, 2004
Relevance feedback and region-based representations are two effective ways to improve the accuracy of content-based image retrieval systems. Although these two techniques have been successfully investigated and developed in the last few years, little attention has been paid to combining them together. We argue that integrating these two approaches and allowing them to benefit from each other will yield better performance than using either of them alone. To do that, on the one hand, two relevance feedback algorithms are proposed based on region representations. One is inspired from the query point movement method. By assembling all of the segmented regions of positive examples together and reweighting the regions to emphasize the latest ones, a pseudo image is formed as the new query. An incremental clustering technique is also considered to improve the retrieval efficiency. The other is the introduction of existing support vector machine-based algorithms. A new kernel is proposed so as to enable the algorithms to be applicable to region-based representations. On the other hand, a rational region weighting scheme based on users' feedback information is proposed. The region weights that somewhat coincide with human perception not only can be used in a query session, but can also be memorized and accumulated for future queries. Experimental results on a database of 10 000 general-purpose images demonstrate the effectiveness of the proposed framework.
Region-Based Image Retrieval Using Relevance Feature Weights
INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGENT SYSTEMS
We propose a new region-based CBIR (content-based image retrieval) system. One of the main objectives of our work is to reduce the semantic gap between the visual characteristics of the query and the high level semantic sought by the user. This is achieved by allowing the user to select specific regions and expressing his interest in a more accurate way. Moreover, the proposed approach overcomes the challenge of choosing suitable features to describe the image content. More specifically, relevance weights are automatically associated with each visual feature in order to better represent the visual content of the images. To evaluate these objectives, we compare the obtained results with those obtained using traditional CBIR systems.
Region-based relevance feedback in image retrieval
2002 IEEE International Symposium on Circuits and Systems. Proceedings (Cat. No.02CH37353)
Relevance feedback and region-based representation of images are two effective ways to improve accuracy in content-based image retrieval. In this paper, we propose a novel relevance feedback approach based on region representation. It can be considered as a special case of the query point movement method in region-based image retrieval. By assembling all the segmented regions of positive examples together and resizing the regions to emphasize the latest positive examples, we form a composite image as the optimal query. A region-based image similarity measure is used to calculate the distance between the optimal query and an image in the database. An incremental clustering technique is also considered to improve the retrieval efficiency. Experimental results show that the proposed approach is effective in improving the performance of content-based image retrieval systems.
A General and Effective Two-Stage Approach for Region-Based Image Retrieval
2010
Content-based image retrieval (CBIR) has received substantial attentions for the past decades. It is motivated by the rapid accumulation of large collections of digital images which, in turn, create the need for efficient retrieval schemes. Many research works further utilize regional features to obtain the semantics of images for better retrieval performance. In this paper, a two-stage retrieval strategy is presented to improve the performance of region-based image retrieval (RBIR). In this approach, an image is first segmented into a fixed number of rectangular regions. Then, each region is represented by its low-frequency discrete cosine transform (DCT) coefficients in the YUV color space. At the first stage of retrieval, the threshold-based pruning (TBP) serves as a filter to remove those candidates with widely distinct features. At the second stage, a more detailed feature comparison (DFC) is conducted over the remaining candidates. In the experimental system, users can represent their region of interest (ROI) by selecting different strategies, setting parameter values, and/or adjusting the weights of features as the search progresses. The experimental results show that both efficiency and accuracy can be improved by using the proposed two-stage approach.
2009
Recently, digital content has become a significant and inevitable asset for any enterprise and the need for visual content management is on the rise as well. There has been an increase in attention towards the automated management and retrieval of digital images owing to the drastic development in the number and size of image databases. A significant and increasingly popular approach that aids in the retrieval of image data from a huge collection is called Content-based image retrieval (CBIR). Content-based image retrieval has attracted voluminous research in the last decade paving way for development of numerous techniques and systems besides creating interest on fields that support these systems. CBIR indexes the images based on the features obtained from visual content so as to facilitate speedy retrieval. In this paper, we have presented an elegant and effective system for content-based image indexing and retrieval. The system exploits the global and regional features of the images for indexing and fractional distance measure as similarity measure for retrieval. The images are quantized before extracting the global features. We have also presented a novel approach for image segmentation to extract the region features effectively. R*-Tree data structure is used in indexing the region features. The experimental results show that the proposed system can improve the retrieval accuracy as well as reduce the time for retrieval.
Effective and efficient region-based image retrieval
Journal of Visual Languages & Computing, 2003
Content-based image retrieval (CBIR) is a challenging task. Current research works attempt to obtain and use the semantics of image to perform better retrieval. Towards this goal, segmentation of an image into regions has been used in recent years, since local properties of regions can help matching objects between images and thereby contribute towards a more effective CBIR. This paper improves on a CBIR technique, called SNL (Sridhar, Nascimento, Li) that utilizes the regional properties of the images. In SNL each image is segmented and features including the color, shape, size and spatial position of the obtained regions are extracted. Regions are then compared using the integrated region matching (IRM) distance measure, which is not a metric, which prevents the use of metric access structures or filtering techniques based on the triangle inequality. We overcome this issue, by using MiCRoM, a true metric distance to compare segmented images. This resulting approach, called SNL n ; can be used in conjunction with a filtering technique to reduce substantially the number of images compared. Albeit metric-based, SNL n is computationally expensive. We address this drawback, in the SNL þ approach, where we replace the expensive metric distance in SNL n by the inexpensive original (non-metric) IRM distance. We found that one can still make use of the same filtering technique, at the expense of little loss in retrieval effectiveness. Thus, the main contribution of this paper is SNL þ ; a very effective and highly efficient region-based image retrieval technique.
Region-Based Image Retrieval Using Multiple-Features
Lecture Notes in Computer Science, 2002
Content-based image retrieval from large multimedia databases effectively and efficiently is a challenging task. In this paper, we propose a retrieval technique that utilizes the regional properties of the images. After image segmentation, each region is represented by its colour, shape, size, and spatial position. Regions of different images are matched and a distance measure between the whole images is calculated. The relative importance of the above features is investigated, and colour plays a major role in the process of distance computation. Our representation is robust to minor inaccuracy in image segmentation, is invariant to scaling and can perceive geometric changes like translation and rotation. The experimental results indicate that our technique outperforms recently proposed techniques. ¤ Work partially supported by the Canadian Natural Sciences and Engineering Research Council (NSERC).
A region-similarity-based image retrieval system
The 10th International …, 2004
In this document, we present an image retrieval system that is based on a segmented representation of the visual content. This representation leads to a comparison of the image content that is more "semantic" than a classical global comparison. The system compares regions using fuzzy similarity measures that have been show to be psychologically intuitive and easy to aggregate. We then exploit the aggregation between regional similarity measures to let the user build four different types of original visual requests. Our system can handle these requests easily, thanks to its open architecture that let the expert user modify its parameters and compose new aggregation operators on them.
An Image Retrieval System Based on Region Classification
Lecture Notes in Computer Science, 2004
I hereby declare that all information in this document has been obtained and presented in accordance with academic rules and ethical conduct. I also declare that, as required by these rules and conduct, I have fully cited and referenced all material and results that are not original to this work.