2009
1.
Rahman, Md. Mahmudur; Bhattacharya, Prabir; Desai, Bipin C
A unified image retrieval framework on local visual and semantic concept-based feature spaces Journal Article
In: Journal of Visual Communication and Image Representation, vol. 20, no. 7, pp. 450-462, 2009, ISSN: 1047-3203.
Abstract | Links | BibTeX | Tags: Classification, Content-based image retrieval, Learning methods, Relevance feedback, Self-organizing map, Similarity fusion, Support vector machine
@article{RAHMAN2009450,
title = {A unified image retrieval framework on local visual and semantic concept-based feature spaces},
author = {Md. Mahmudur Rahman and Prabir Bhattacharya and Bipin C Desai},
url = {https://www.sciencedirect.com/science/article/pii/S1047320309000686},
doi = {https://doi.org/10.1016/j.jvcir.2009.06.001},
issn = {1047-3203},
year = {2009},
date = {2009-01-01},
journal = {Journal of Visual Communication and Image Representation},
volume = {20},
number = {7},
pages = {450-462},
abstract = {This paper presents a learning-based unified image retrieval framework to represent images in local visual and semantic concept-based feature spaces. In this framework, a visual concept vocabulary (codebook) is automatically constructed by utilizing self-organizing map (SOM) and statistical models are built for local semantic concepts using probabilistic multi-class support vector machine (SVM). Based on these constructions, the images are represented in correlation and spatial relationship-enhanced concept feature spaces by exploiting the topology preserving local neighborhood structure of the codebook, local concept correlation statistics, and spatial relationships in individual encoded images. Finally, the features are unified by a dynamically weighted linear combination of similarity matching scheme based on the relevance feedback information. The feature weights are calculated by considering both the precision and the rank order information of the top retrieved relevant images of each representation, which adapts itself to individual searches to produce effective results. The experimental results on a photographic database of natural scenes and a bio-medical database of different imaging modalities and body parts demonstrate the effectiveness of the proposed framework.},
keywords = {Classification, Content-based image retrieval, Learning methods, Relevance feedback, Self-organizing map, Similarity fusion, Support vector machine},
pubstate = {published},
tppubtype = {article}
}
This paper presents a learning-based unified image retrieval framework to represent images in local visual and semantic concept-based feature spaces. In this framework, a visual concept vocabulary (codebook) is automatically constructed by utilizing self-organizing map (SOM) and statistical models are built for local semantic concepts using probabilistic multi-class support vector machine (SVM). Based on these constructions, the images are represented in correlation and spatial relationship-enhanced concept feature spaces by exploiting the topology preserving local neighborhood structure of the codebook, local concept correlation statistics, and spatial relationships in individual encoded images. Finally, the features are unified by a dynamically weighted linear combination of similarity matching scheme based on the relevance feedback information. The feature weights are calculated by considering both the precision and the rank order information of the top retrieved relevant images of each representation, which adapts itself to individual searches to produce effective results. The experimental results on a photographic database of natural scenes and a bio-medical database of different imaging modalities and body parts demonstrate the effectiveness of the proposed framework.
2008
2.
Rahman, Md. Mahmudur; Desai, Bipin C; Bhattacharya, Prabir
Medical image retrieval with probabilistic multi-class support vector machine classifiers and adaptive similarity fusion Journal Article
In: Computerized Medical Imaging and Graphics, vol. 32, no. 2, pp. 95-108, 2008, ISSN: 0895-6111.
Abstract | Links | BibTeX | Tags: Classification, Classifier combination, Content-based image retrieval, Inverted file, Medical imaging, Similarity fusion, Support vector machine
@article{RAHMAN200895,
title = {Medical image retrieval with probabilistic multi-class support vector machine classifiers and adaptive similarity fusion},
author = {Md. Mahmudur Rahman and Bipin C Desai and Prabir Bhattacharya},
url = {https://www.sciencedirect.com/science/article/pii/S0895611107001383},
doi = {https://doi.org/10.1016/j.compmedimag.2007.10.001},
issn = {0895-6111},
year = {2008},
date = {2008-01-01},
journal = {Computerized Medical Imaging and Graphics},
volume = {32},
number = {2},
pages = {95-108},
abstract = {We present a content-based image retrieval framework for diverse collections of medical images of different modalities, anatomical regions, acquisition views, and biological systems. For the image representation, the probabilistic output from multi-class support vector machines (SVMs) with low-level features as inputs are represented as a vector of confidence or membership scores of pre-defined image categories. The outputs are combined for feature-level fusion and retrieval based on the combination rules that are derived by following Bayes’ theorem. We also propose an adaptive similarity fusion approach based on a linear combination of individual feature level similarities. The feature weights are calculated by considering both the precision and the rank order information of top retrieved relevant images as predicted by SVMs. The weights are dynamically updated by the system for each individual search to produce effective results. The experiments and analysis of the results are based on a diverse medical image collection of 11,000 images of 116 categories. The performances of the classification and retrieval algorithms are evaluated both in terms of error rate and precision–recall. Our results demonstrate the effectiveness of the proposed framework as compared to the commonly used approaches based on low-level feature descriptors.},
keywords = {Classification, Classifier combination, Content-based image retrieval, Inverted file, Medical imaging, Similarity fusion, Support vector machine},
pubstate = {published},
tppubtype = {article}
}
We present a content-based image retrieval framework for diverse collections of medical images of different modalities, anatomical regions, acquisition views, and biological systems. For the image representation, the probabilistic output from multi-class support vector machines (SVMs) with low-level features as inputs are represented as a vector of confidence or membership scores of pre-defined image categories. The outputs are combined for feature-level fusion and retrieval based on the combination rules that are derived by following Bayes’ theorem. We also propose an adaptive similarity fusion approach based on a linear combination of individual feature level similarities. The feature weights are calculated by considering both the precision and the rank order information of top retrieved relevant images as predicted by SVMs. The weights are dynamically updated by the system for each individual search to produce effective results. The experiments and analysis of the results are based on a diverse medical image collection of 11,000 images of 116 categories. The performances of the classification and retrieval algorithms are evaluated both in terms of error rate and precision–recall. Our results demonstrate the effectiveness of the proposed framework as compared to the commonly used approaches based on low-level feature descriptors.