Image information systems: where do we go from here?

Chang, Shih‐Fu; Hsu, Arding

doi:10.1109/69.166986

Cited by 177 publications

(37 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Accordingly, if the value of other optimized points are greater than Th M and the distance between them is also greater than Th D , these points are also selected as the optimal queries. The reasonable ranges for α and β can be in [0.6-1] and [1][2][3] intervals, respectively. For example, in Fig.…”

Section: Optimization Algorithmmentioning

confidence: 99%

“…Moreover, a series of words do not fully describe the image content. Due to these reasons, efforts were directed toward content-based image retrieval (CBIR) [2][3][4]. In medical applications, with the rapid growth of technology and appearance of different imaging systems, and consequently increase in medical images, utilization of content-based medical image retrieval (CBMIR) systems became unavoidable due to effective and accurate diagnosis, research, and medical education [5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimal Query-Based Relevance Feedback in Medical Image Retrieval Using Score Fusion-Based Classification

Behnam

Pourghassem

2014

J Digit Imaging

View full text Add to dashboard Cite

In this paper, a new content-based medical image retrieval (CBMIR) framework using an effective classification method and a novel relevance feedback (RF) approach are proposed. For a large-scale database with diverse collection of different modalities, query image classification is inevitable due to firstly, reducing the computational complexity and secondly, increasing influence of data fusion by removing unimportant data and focus on the more valuable information. Hence, we find probability distribution of classes in the database using Gaussian mixture model (GMM) for each feature descriptor and then using the fusion of obtained scores from the dependency probabilities, the most relevant clusters are identified for a given query. Afterwards, visual similarity of query image and images in relevant clusters are calculated. This method is performed separately on all feature descriptors, and then the results are fused together using feature similarity ranking level fusion algorithm. In the RF level, we propose a new approach to find the optimal queries based on relevant images. The main idea is based on density function estimation of positive images and strategy of moving toward the aggregation of estimated density function. The proposed framework has been evaluated on ImageCLEF 2005 database consisting of 10,000 medical X-ray images of 57 semantic classes. The experimental results show that compared with the existing CBMIR systems, our framework obtains the acceptable performance both in the image classification and in the image retrieval by RF.

show abstract

Section: Optimization Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Optimal Query-Based Relevance Feedback in Medical Image Retrieval Using Score Fusion-Based Classification

Behnam

Pourghassem

2014

J Digit Imaging

View full text Add to dashboard Cite

show abstract

“…However these psudo-content-based retrieval techniques face some limitations because of their fundamental dependance on such intermediate models of "meaning" [13,2,5]. In the first level, it is difficult to design a sufficient annotation language that can contain all the possible ranges of meaning.…”

Section: Nature Of Image Informationmentioning

confidence: 99%

Intermediate Annotationless Dynamical Object-Index-Based Query in Large Image Archives with Holographic Representation

Khan

1996

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

SUMMARYThis paper presents a new parallel and distributed associative network based technique for content-based image retrieval (CBIR) with dynamic indices. Unlike any prior artificial associative networks (AAM), this new associative search network has the unique ability to explicitly focus on any subset of pixels in the image. It can also provide a feedback meta-quantity on the quality of outgoing information. The network is founded on a bi-modal representation of information elements which in addition to basic information also includes meta-states. Its computational model has been derived from optical holography. These unique capabilities coupled with usual advantages of associative computing (adaptability, efficiency, ability to cope with imprecision, parallel and distributed mode of computation) now for the first time makes it possible to realize a CBIR technique based on associative computing. This new CBIR strategy provides an inquirer greater flexibility to independently and dynamically construct object-indices without depending on the fixed, pre-defined adhoc indices used by traditional CBIR approaches. The paper presents the mechanism, architecture and performance of an image archival and retrieval system realized with this new network.1 This manuscript has been accepted for publication in the Journal of Visual Communication and Image Representation for its special Issue on Indexing, Storage, Retrieval and Browsing of Image and Video and will appear in Vol 7, no 4, in 1997. INTERMEDIATE ANNOTATIONLESS DYNAMICAL OBJECT-INDEX BASED QUERY IN LARGE IMAGE ARCHIVES WITH HOLOGRAPHIC REPRESENTATION ABSTRACTThis paper presents a new parallel and distributed associative network based technique for content-based image retrieval (CBIR) with dynamic indices. Unlike any prior artificial associative networks (AAM), this new associative search network has the unique ability to explicitly focus on any subset of pixels in the image. It can also provide a feedback meta-quantity on the quality of outgoing information. The network is founded on a bi-modal representation of information elements which in addition to basic information also includes meta-states. Its computational model has been derived from optical holography. These unique capabilities coupled with usual advantages of associative computing (adaptability, efficiency, ability to cope with imprecision, parallel and distributed mode of computation) now for the first time makes it possible to realize a CBIR technique based on associative computing. This new CBIR strategy provides an inquirer greater flexibility to independently and dynamically construct object-indices without depending on the fixed, pre-defined adhoc indices used by traditional CBIR approaches. The paper presents the mechanism, architecture and performance of an image archival and retrieval system realized with this new network.

show abstract

“…How to effectively and rapidly process image data has been becoming a hot topic of image processing field [1]. CBIR(Content-Based Image Retrieval) is one focus in the research field [2]. CBIR can be divided mainly into three steps: index construction based on low-level features, distance calculation and the query.…”

Section: Introductionmentioning

confidence: 99%

Salient Region Detection based on Frequency-tuning and Region Contrast

Fu¹,

Guo²,

Wu³

2014

Proceedings of the 3rd International Conference on Computer Science and Service System

View full text Add to dashboard Cite

Abstract-Frequency-tuned saliency detection analyzes image saliency from the perspective of frequency domain and fully combines image segmentation method, which outputs welldefined boundaries of salient objects. However, the method ignores spatial relationships across image parts. This paper proposes an improved saliency detection method on the basis of the frequency-tuned method. In this method, we first segment the input image into regions and then analyze the image from the frequency domain. After that, we preprocess it using Gaussian filter to eliminate noise and coding artifacts. For each region, we can get saliency map in region-level based on region contrast. Finally, salient regions are selected by "winner-take-all" (WTA) neural network and Inhibition of Return(IOR) mechanism. The proposed salient region detection algorithm combines the virtues of frequency-tuning and region contrast. The experimental results show the feasibility and validity of this algorithm.

show abstract

Image information systems: where do we go from here?

Cited by 177 publications

References 25 publications

Optimal Query-Based Relevance Feedback in Medical Image Retrieval Using Score Fusion-Based Classification

Optimal Query-Based Relevance Feedback in Medical Image Retrieval Using Score Fusion-Based Classification

Intermediate Annotationless Dynamical Object-Index-Based Query in Large Image Archives with Holographic Representation

Salient Region Detection based on Frequency-tuning and Region Contrast

Contact Info

Product

Resources

About