scholarly journals An Information Foraging Theory Based User Study of an Adaptive User Interaction Framework for Content-Based Image Retrieval

2011 ◽  
pp. 241-251 ◽  
Author(s):  
Haiming Liu ◽  
Paul Mulholland ◽  
Dawei Song ◽  
Victoria Uren ◽  
Stefan Rüger
Keyword(s):  
Image Retrieval ◽  
User Study ◽  
User Interaction ◽  
Foraging Theory ◽  
Content Based Image Retrieval ◽  
Information Foraging

scholarly journals Automatic content-based image retrieval using hierarchical clustering algorithms

2021 ◽  
Author(s):  
Kambiz Jarrah
Keyword(s):  
Image Retrieval ◽  
Hierarchical Clustering ◽  
Relevance Feedback ◽  
Clustering Algorithms ◽  
User Interaction ◽  
Content Based Image Retrieval ◽  
Feature Weight ◽  
High Level ◽  
Tree Map ◽  
Self Organizing

The overall objective of this thesis is to present a methodology for guiding adaptations of an RBF-based relevance feedback network, embedded in automatic content-based image retrieval (CBIR) systems, through the principle of unsupervised hierarchical clustering. The main focus of this thesis is two-fold: introducing a new member of Self-Organizing Tree Map (SOTM) family, the Directed self-organizing tree map (DSOTM) that not only provides a partial supervision on cluster generation by forcing divisions away from the query class, but also presents an objective verdict on resemblance of the input pattern as its tree structure grows; and using a base-10 Genetic Algorithm (GA) approach to accurately determine the contribution of individual feature vectors for a successful retrieval in a so-called "feature weight detection process." The DSOTM is quite attractive in CBIR since it aims to reduce both user workload and subjectivity. Repetitive user interaction steps are replaced by a DSOTM module, which adaptively guides relevance feedback, to bridge the gap between low-level image descriptors and high-level semantics. To further reduce this gap and achieve an enhanced performance for the automatic CBIR system under study, a GA-based approach was proposed in conjunction with the DSOTM. The resulting framework is referred to as GA-based CBIR (GA-CBIR) and aims to import human subjectivity by automatically adjusting the search process to what the system evolves "to believe" is significant content within the query. In this engine, traditional GA operators work closely with the DSOTM to better attune the apparent discriminative characteristics observed in an image by a human user.

Multi-Modal Content Based Image Retrieval in Healthcare

2011 ◽  
pp. 44-59 ◽  
Author(s):  
Jinman Kim ◽  
Ashnil Kumar ◽  
Tom Weidong Cai ◽  
David Dagan Feng
Keyword(s):  
Feature Extraction ◽  
Clinical Practice ◽  
Image Retrieval ◽  
User Interaction ◽  
Content Based Image Retrieval ◽  
Similarity Measurement ◽  
Application Domain ◽  
Pet Ct ◽  
The Future ◽  
Future Challenges

Multi-modal imaging requires innovations in algorithms and methodologies in all areas of CBIR, including feature extraction and representation, indexing, similarity measurement, grouping of similar retrieval results, as well as user interaction. In this chapter, we will discuss the rise of multi-modal imaging in clinical practice. We will summarize some of our pioneering CBIR achievements working with these data, exemplified by a specific application domain of PET-CT. We will also discuss the future challenges in this significantly important emerging area.

scholarly journals Inverse Foraging

2021 ◽  
Vol 5 (3) ◽  
pp. 1-18
Author(s):  
Maria L. Montoya Freire ◽  
Antti Oulasvirta ◽  
Mario Di Francesco
Keyword(s):  
Open Problem ◽  
User Study ◽  
Synthetic Data ◽  
Accurate Method ◽  
Foraging Theory ◽  
Viewing Time ◽  
User Interest ◽  
Information Foraging ◽  
Body Postures ◽  
Foraging Models

Users' engagement with pervasive displays has been extensively studied, however, determining how their content is interesting remains an open problem. Tracking of body postures and gaze has been explored as an indication of attention; still, existing works have not been able to estimate the interest of passers-by from readily available data, such as the display viewing time. This article presents a simple yet accurate method of estimating users' interest in multiple content items shown at the same time on displays. The proposed approach builds on the information foraging theory, which assumes that users optimally decide on the content they consume. Through inverse foraging, the parameters of a foraging model are fitted to the values of viewing times observed in practice, to yield estimates of user interest. Different foraging models are evaluated by using synthetic data and with a controlled user study. The results demonstrate that inverse foraging accurately estimates interest, achieving an R2 above 70% in comparison to self-reported interest. As a consequence, the proposed solution allows to dynamically adapt the content shown on pervasive displays, based on viewing data that can be easily obtained in field deployments.

scholarly journals Automatic content-based image retrieval using hierarchical clustering algorithms

2021 ◽  
Author(s):  
Kambiz Jarrah
Keyword(s):  
Image Retrieval ◽  
Hierarchical Clustering ◽  
Relevance Feedback ◽  
Clustering Algorithms ◽  
User Interaction ◽  
Content Based Image Retrieval ◽  
Feature Weight ◽  
High Level ◽  
Tree Map ◽  
Self Organizing

The overall objective of this thesis is to present a methodology for guiding adaptations of an RBF-based relevance feedback network, embedded in automatic content-based image retrieval (CBIR) systems, through the principle of unsupervised hierarchical clustering. The main focus of this thesis is two-fold: introducing a new member of Self-Organizing Tree Map (SOTM) family, the Directed self-organizing tree map (DSOTM) that not only provides a partial supervision on cluster generation by forcing divisions away from the query class, but also presents an objective verdict on resemblance of the input pattern as its tree structure grows; and using a base-10 Genetic Algorithm (GA) approach to accurately determine the contribution of individual feature vectors for a successful retrieval in a so-called "feature weight detection process." The DSOTM is quite attractive in CBIR since it aims to reduce both user workload and subjectivity. Repetitive user interaction steps are replaced by a DSOTM module, which adaptively guides relevance feedback, to bridge the gap between low-level image descriptors and high-level semantics. To further reduce this gap and achieve an enhanced performance for the automatic CBIR system under study, a GA-based approach was proposed in conjunction with the DSOTM. The resulting framework is referred to as GA-based CBIR (GA-CBIR) and aims to import human subjectivity by automatically adjusting the search process to what the system evolves "to believe" is significant content within the query. In this engine, traditional GA operators work closely with the DSOTM to better attune the apparent discriminative characteristics observed in an image by a human user.

scholarly journals An Ensemble Stacked four Layered Architectures for Image Retrieval

2020 ◽  
Vol 8 (5) ◽  
pp. 2245-2253
Keyword(s):  
Image Retrieval ◽  
Layer Structure ◽  
User Interaction ◽  
Recovery Process ◽  
Image Recovery ◽  
Content Based Image Retrieval ◽  
Present System ◽  
Image Server ◽  
Image Retrieval System ◽  
Color Texture

It becomes possible to use large image server rapidly increasing. Content-Based Image Retrieval (CBIR) is an effective method for conducting its management and retrieval. This paper suggests the benefit of the image retrieval system based on content as well as innovative technologies. Compared to the shortcoming that the present system uses only a certain feature, this paper establishes a method that integrates color, texture and shape for image recovery and shows its additional benefit. Content Based image retrieval is a program that retrieves multiple images from an extensive collection of databases. The paper starts by explaining CBIR's fundamental aspects. Image Retrieval features such as color, texture and form will be addressed first. They address the similarity tests depending on which games are made and images are retrieved for a short time. The technique uses a four-layer structure that combines the characteristics of advancing inquiry and involves a combination of gabor and ripplet transition. Two image sets are obtained in the essential layer using the gabor and ripplet-based recovery techniques individually, as well as the top identified and critical images from the grapples of the top up-and-comer structure diagrams. The graph grapples use each individual part to recover six image frames from those in the image server as a demand for an increase in the next layer. The images throughout the six frames of images are analyzed for positive and negative information age in the third layer, and simpleMKL is correlated with acquiring expertise with proper examination subordinate variation loads to achieve the final result of image recovery. User interaction with the recovery system is critical for content-based image recovery, as dynamic request creation and adjustment can only be accomplished by including the user in the recovery process.

Sign in / Sign up

Export Citation Format

Share Document