Results 1 - 10
of
150
Learning Image Similarity from Flickr Groups Using Stochastic Intersection Kernel Machines
"... Measuring image similarity is a central topic in computer vision. In this paper, we learn similarity from Flickr groups and use it to organize photos. Two images are similar if they are likely to belong to the same Flickr groups. Our approach is enabled by a fast Stochastic Intersection Kernel MAchi ..."
Abstract
-
Cited by 38 (1 self)
- Add to MetaCart
Measuring image similarity is a central topic in computer vision. In this paper, we learn similarity from Flickr groups and use it to organize photos. Two images are similar if they are likely to belong to the same Flickr groups. Our approach is enabled by a fast Stochastic Intersection Kernel MAchine (SIKMA) training algorithm, which we propose. This proposed training method will be useful for many vision problems, as it can produce a classifier that is more accurate than a linear classifier, trained on tens of thousands of examples in two minutes. The experimental results show our approach performs better on image matching, retrieval, and classification than using conventional visual features. 1.
Efficient Manifold Ranking for Image Retrieval
, 2011
"... Manifold Ranking (MR), a graph-based ranking algorithm, has been widely applied in information retrieval and shown to have excellent performance and feasibility on a variety of data types. Particularly, it has been successfully applied to content-based image retrieval, because of its outstanding abi ..."
Abstract
-
Cited by 26 (10 self)
- Add to MetaCart
(Show Context)
Manifold Ranking (MR), a graph-based ranking algorithm, has been widely applied in information retrieval and shown to have excellent performance and feasibility on a variety of data types. Particularly, it has been successfully applied to content-based image retrieval, because of its outstanding ability to discover underlying geometrical structure of the given image database. However, manifold ranking is computationally very expensive, both in graph construction and ranking computation stages, which significantly limits its applicability to very large data sets. In this paper, we extend the original manifold ranking algorithm and propose a new framework named Efficient Manifold Ranking (EMR). We aim to address the shortcomings of MR from two perspectives: scalable graph construction and efficient computation. Specifically, we build an anchor graph on the data set instead of the traditional k-nearest neighbor graph, and design a new form of adjacency matrix utilized to speed up the ranking computation. The experimental results on a real world image database demonstrate the effectiveness and efficiency of our proposed method. With a comparable performance to the original manifold ranking, our method significantly reduces the computational time, makes it a promising method to large scale real world retrieval problems.
Application Potential of Multimedia Information Retrieval
, 2007
"... This paper will first briefly survey the existing impact of MIR in applications. It will then analyze the current trends of MIR research which can have an influence on future applications. It will then detail the future possibilities and bottlenecks in applying the MIR research results in the main t ..."
Abstract
-
Cited by 12 (0 self)
- Add to MetaCart
This paper will first briefly survey the existing impact of MIR in applications. It will then analyze the current trends of MIR research which can have an influence on future applications. It will then detail the future possibilities and bottlenecks in applying the MIR research results in the main target application areas, such as consumer (e.g. personal video recorders, web information retrieval), public safety (e.g. automated smart surveillance systems) and professional world (e.g. automated meeting capture and summarization). In particular, recommendations will be made to the research community regarding the challenges that need to be met to make the knowledge transfer towards the applications more efficient and effective. It will also attempt to study the trends in the applications which can inform the MIR community on directing intellectual resources towards MIR problems which can have a maximal real-world impact.
Image Retrieval with Relevance Feedback based on Genetic Programming
- In SBBD
, 2008
"... Abstract. This paper presents a new content-based image retrieval framework with relevance feedback. This framework employs Genetic Programming to discover a combination of descriptors that better characterizes the user perception of image similarity. Several experiments were conducted to validate t ..."
Abstract
-
Cited by 6 (3 self)
- Add to MetaCart
(Show Context)
Abstract. This paper presents a new content-based image retrieval framework with relevance feedback. This framework employs Genetic Programming to discover a combination of descriptors that better characterizes the user perception of image similarity. Several experiments were conducted to validate the proposed framework. These experiments employed three different image databases and color, shape, and texture descriptors to represent the content of database images. The proposed framework was compared with three other relevance feedback methods regarding their efficiency and effectiveness in image retrieval tasks. Experiment results demonstrate the superiority of the proposed method. 1.
Learning How to Extract Rotation-Invariant and Scale-Invariant Features from Texture Images
, 2007
"... Abstract — Learning how to extract texture features from noncontrolled environments characterized by distorted images is a still-open task. By using a new rotation-invariant and scaleinvariant image descriptor based on Steerable Pyramid Decomposition, and a novel multi-class recognition method based ..."
Abstract
-
Cited by 6 (4 self)
- Add to MetaCart
(Show Context)
Abstract — Learning how to extract texture features from noncontrolled environments characterized by distorted images is a still-open task. By using a new rotation-invariant and scaleinvariant image descriptor based on Steerable Pyramid Decomposition, and a novel multi-class recognition method based on Optimum-Path Forest, a new texture recognition system is proposed. By combining the discriminating power of our image descriptor and classifier, our system uses small size feature vectors to characterize texture images without compromising overall classification rates. State-of-the-art recognition results are further presented on the Brodatz dataset. High classification rates demonstrate the superiority of the proposed system. Index Terms — texture recognition, machine learning, image feature extraction, steerable pyramid decomposition, optimumpath forest classifier. Fig. 1. directional vs. nondirectional visual cues. Fig. 3. fine vs. coarse visual cues. Fig. 2. smooth vs. rough visual cues. Fig. 4. uniform vs. non-uniform visual cues. I.
Perceptual Dimensions for Surface Texture Retrieval
, 2008
"... This copy of the thesis has been supplied on condition that anyone who consults it is understood to recognise that the copyright rests with its author and that no quotation from the thesis and no information derived from it may be published without the prior written consent of the author or of the U ..."
Abstract
-
Cited by 6 (0 self)
- Add to MetaCart
(Show Context)
This copy of the thesis has been supplied on condition that anyone who consults it is understood to recognise that the copyright rests with its author and that no quotation from the thesis and no information derived from it may be published without the prior written consent of the author or of the University (as may be appropriate). ii This thesis presents a methodology for developing perceptually relevant surface texture retrieval systems. Generally such systems have been researched using image texture which has been captured under unknown or uncontrolled conditions (e.g. Brodatz). However, it is known that changes in illumination affect both the visual appearance of surfaces and the computational features extracted from their images. In contrast this thesis either uses surface information directly, or computes features obtained from images captured under controlled lighting conditions. Psychophysical experiments were conducted in which observers were asked to place texture samples into groups. Multidimensional Scaling was applied to the resulting similarity matrices to obtain a more manageable reduced perceptual space. A four-dimensional representation was found to capture the majority of the variability. A corresponding feature space was created by linearly combining selected trace transform features. Retrieval was performed simply by determining the n closest neighbours to the query’s feature vector. An average retrieval precision of 60 % was obtained in blind tests.
Towards Ontologies for Image Interpretation and Annotation
"... Due to the well-known semantic gap problem, a wide number of approaches have been proposed during the last decade for automatic image annotation, i.e. the textual description of images. Since these approaches are still not sufficiently efficient, a new trend is to use semantic hierarchies of concept ..."
Abstract
-
Cited by 5 (1 self)
- Add to MetaCart
(Show Context)
Due to the well-known semantic gap problem, a wide number of approaches have been proposed during the last decade for automatic image annotation, i.e. the textual description of images. Since these approaches are still not sufficiently efficient, a new trend is to use semantic hierarchies of concepts or ontologies to improve the image annotation process. This paper presents an overview and an analysis of the use of semantic hierarchies and ontologies to provide a deeper image understanding and a better image annotation in order to furnish retrieval facilities to users. 1
A Costanzo, Counter-forensics of SIFT-based copy-move detection by means of keypoint classification
- EURASIP J. Image Video Process. 2013
, 2013
"... Copy-move forgeries are very common image manipulations that are often carried out with malicious intents. Among the techniques devised by the Image Forensic community, those relying on SIFT features are the most effective ones. In this paper we approach the copy-move scenario from the perspective o ..."
Abstract
-
Cited by 5 (3 self)
- Add to MetaCart
(Show Context)
Copy-move forgeries are very common image manipulations that are often carried out with malicious intents. Among the techniques devised by the Image Forensic community, those relying on SIFT features are the most effective ones. In this paper we approach the copy-move scenario from the perspective of an attacker whose goal is to remove such features. The attacks conceived so far against SIFT-based forensic techniques implicitly assume that all SIFT keypoints have similar properties. On the contrary, we base our attacking strategy on the observation that it is possible to classify them in different typologies. Then one may devise attacks tailored to each specific SIFT class, thus improving the performance in terms of removal rate and visual quality. To validate our ideas, we propose to use a SIFT classification scheme based on the gray scale histogram of the neighborhood of SIFT keypoints. Once the classification is performed, then we attack the different classes by means of class-specific methods. Our experiments lead to three interesting results: (i) there is a significant advantage in using SIFT classification; (ii) the classification-based attack is robust against different SIFT implementations; and (iii) we are able to impair a state-of-the-art SIFT-based copy-move detector in realistic cases. 1 1
Article Ontology-Based Classification of Building Types Detected from Airborne Laser Scanning Data
, 2014
"... remote sensing ..."
(Show Context)
Improving automatic image annotation based on word co-occurrence
, 2008
"... Abstract. Accuracy of current automatic image labeling methods is un-der the requirements of annotation-based image retrieval systems. The performance of most of these labeling methods is poor if we just consider the most relevant label for a given region. However, if we look within the set of the t ..."
Abstract
-
Cited by 4 (2 self)
- Add to MetaCart
(Show Context)
Abstract. Accuracy of current automatic image labeling methods is un-der the requirements of annotation-based image retrieval systems. The performance of most of these labeling methods is poor if we just consider the most relevant label for a given region. However, if we look within the set of the top−k candidate labels for a given region, accuracy of most of these systems is improved. In this paper we take advantage of this fact and propose a method (NBI) based on word co-occurrences that uses the näıve Bayes formulation for improving automatic image anno-tation methods. Our approach utilizes co-occurrence information of the candidate labels for a region with those candidate labels for the other surrounding regions, within the same image, for selecting the correct la-bel. Co-occurrence information is obtained from an external collection of manually annotated images: the IAPR-TC12 benchmark. Experimen-tal results using a k−nearest neighbors method as our annotation sys-tem, give evidence of significant improvements after applying the NBI method. NBI is efficient since the co-occurrence information was ob-tained off-line. Furthermore, our method can be applied to any other annotation system that ranks labels by their relevance. 1
