P. Androutsos

University of Toronto, Toronto, Ontario, Canada

Are you P. Androutsos?

Claim your profile

Publications (21)20.38 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: There exist many experimental situations in which a subjective rather than an objective test of a specific variable proves to be a much more relevant method of investigation. Examples of such cases abound in experiments involving human perception or human interaction. When performing tests of the human visual process, one particular subject may view something differently than another. In such situations, objective tests are very difficult to generate and often completely unfeasable due to the fact that they do not accurately model human perception. Because of the intimate relationship between image processing and the human eye, subjective tests are extremely important when the final judgement if an image is passed by the human eye. In this paper insight into what method of colour edge detection results in edgemaps which are in best accordance with what the human eye sees. In particular, this paper presents a comparison of the relative subjectively based performances of a group of basic order statistic and difference vector operator detectors.
    11/2006: pages 119-126;
  • [Show abstract] [Hide abstract]
    ABSTRACT: A small world search agent employing peer-to-peer (P2P) concepts borrowed from sociology is employed for performing image retrievals in a small world distributed media index. The Small World Indexing Method (SWIM) allows for a highly networked architecture where index information does not exist as a separate entity on a specific server, but rather is stored within the actual media objects themselves. Since each media object is only responsible for a small portion of the overall index, the loss of portions of the overall network (data objects) accounts for only a small degradation in the overall retrieval performance. Building upon previous work, the graceful degradation which is provided by the SWIM system is addressed here for retrievals which are performed using small world user agents on a large set of MPEG-7 described images.
    IEEE Transactions on Multimedia 05/2006; · 1.75 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a technique employing the concept of small-world theory to achieve an acquaintance network made up of various types of media objects. Mirroring the way in which humans keep track of descriptions of their friends and acquaintances, every media object within the Small World Indexing Model (SWIM) actively participates in storing descriptions of the objects that are most similar to itself. This results in an extremely high level of decentralization, where each object participates as an equal member in a peer-to-peer network and no central index is required. Retrieval within this ubiquitously networked environment is performed using an agent-based technology exploiting similarity between query criteria and node-specific descriptions stored locally by each media project. This framework is extremely general in that it can easily be applied to any multimedia data type and also modified to employ any low-level or semantic descriptor
    IEEE Signal Processing Magazine 04/2006; · 3.37 Impact Factor
  • IEEE Signal Processing Magazine 01/2006; 23(2):142-153. · 3.37 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: A small world search agent employing peer-to-peer concepts borrowed from sociology is employed for performing image retrievals in a small world distributed media index. The small world indexing method (SWIM) allows for a highly networked architecture where index information does not exist as a separate entity on a specific server, but rather is stored within the actual media objects themselves. Since each media object is only responsible for a small portion of the overall index, the loss of portions of the overall network (data objects) accounts for only a small degradation in the overall retrieval performance. Building upon previous work, the graceful degradation which is provided by the SWIM system is addressed here for retrievals which are performed using small world user agents on a large set of MPEG-7 described images.
    Image Processing, 2005. ICIP 2005. IEEE International Conference on; 10/2005
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A fuzzy approach for the aggregation of multiple features in content-based image retrieval is outlined. Color, shape and spatial features extracted using both computational and manual segmentation techniques are used for subsequent generation of hybrid queries to a ground truth image database consisting of architectural photographs. Retrieval results for multiple-feature queries are shown in the form of precision recall graphs. The results indicate that the fuzzy approach presented herein can perform at least as well as a weighted mean approach.
    Signal Processing 01/2005; · 2.24 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Emergence of large digital visual data repositories motivates the need for effective indexing and retrieval tools. In traditional approaches, similarity among two images is a weighted distance between two feature vectors. These techniques, however, do not provide enough flexibility in modelling user queries. This paper proposes a framework where image similarities are obtained through a decision making process using fuzzy theory. The analysis and results of this paper indicate that the aggregation technique presented here provides an effective, general, and flexible tool for similarity calculation based on the combination of individual descriptors and features.
    Circuits and Systems, 2004. ISCAS '04. Proceedings of the 2004 International Symposium on; 06/2004
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The use of low-level visual features such as colour and shape in content-based image retrieval system leads to several ambiguities. Specifically, due to the many-to-many mapping between the low-level feature space and high-level user concepts, a conceptual user query may not be modelled as a single point in the feature space. Furthermore, conceptually similar images may not fall close to each other in the low-level feature space. This work addresses these issues by proposing an interactive technique, query feedback. This method employs user input to represent a high-level conceptual query as various points in the low-level space. Thus, similarity to a given conceptual query is obtained as the fusion of several low-level representations in the feature space.
    Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on; 06/2004
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: From a perceptual standpoint, the subjectivity inherent in understanding and interpreting visual content in multimedia indexing and retrieval motivates the need for online interactive learning. Since efficiency and speed are important factors in interactive visual content retrieval, most of the current approaches impose restrictive assumptions on similarity calculation and learning algorithms. Specifically, content-based image retrieval techniques generally assume that perceptually similar images are situated close to each other within a connected region of a given space of visual features. This paper proposes a novel method for interactive image retrieval using query feedback. Query feedback learns the user query as well as the correspondence between high-level user concepts and their low-level machine representation by performing retrievals according to multiple queries supplied by the user during the course of a retrieval session. The results presented in this paper demonstrate that this algorithm provides accurate retrieval results with acceptable interaction speed compared to existing methods.
    IEEE Transactions on Circuits and Systems for Video Technology 06/2004; · 1.82 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The large volumes of artistic visual data available to museums, art galleries, and online collections motivate the need for effective means to retrieve relevant information from such repositories. This paper proposes a decision making framework for content-based retrieval of art images based on a combination of low-level features. Traditionally, the similarity among two images has been calculated as a weighted distance between two feature vectors. This approach, however, may not be mathematically and computationally appropriate and does not provide enough flexibility in modeling user queries. This paper proposes a framework that generalizes a wide set of previous approaches to similarity calculation including the weighted distance approach. In this framework, image similarities are obtained through a decision making process based on low-level feature distances using fuzzy theory. The analysis and results of this paper indicate that the aggregation technique presented here provides an effective, general, and flexible tool for similarity calculation based on the combination of individual descriptors and features.
    IEEE Transactions on Image Processing 04/2004; 13(3):277-92. · 3.20 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: An open peer-to-peer architecture for performing distributed image indexing and retrieval is proposed. The system employs a sociological model of human acquaintance networks (small world theory) and concepts derived from the nature of the World Wide Web. Retrieval is performed using agents, and a node hopping algorithm is employed that exploits node referrals established from descriptor data stored locally by each node. A general framework for this small world image miner (SWIM) is presented along with a realization using MPEG-7 color structure descriptor data for 2400 images. Results related to search agent path length and network node degree are presented.
    Image Processing, 2004. ICIP '04. 2004 International Conference on; 01/2004
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The obstacle of generating hybrid queries within the context of content-based image retrieval is still very real. In attempts to overcome this, fuzzy aggregation can be used to combine single, simple index queries into larger, more complex ones. This paper outlines the use of a fuzzy aggregation technique for hybrid querying which has the ability to adjust its behavior according operator-controlled parameters. The resulting aggregator can be viewed as a featureadaptive overall similarity measure. For the purposes of this extended summary, the scope of the aggregator is limited to queries involving color content, color coverage, and horizontal /vertical trends, and applied to a media database comprised of COREL images of fixed size. Preliminary results show promise and illustrate that hybrid queries using the aforementioned fuzzy aggregator are effective in their ability to retrieve relevant images while suppressing erroneous retrievals when compared to simple, single-feature queries. In addition, the results obtained are at a minimum compara- ble to multiple-feature queries generated using a weighted mean approach but exhibiting scalability and greater fiexir bility in parameter adjustment.
    Proceedings / ICIP ... International Conference on Image Processing 04/2003;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: As outlined by the ISO committee, the problem of hybrid query generation lies outside the scope of the MPEG-7 standard. This problem of creating intelligent image database queries that both correctly reflect the intentions of the user as well as provide good retrieval results can be approached in various ways. This paper proposes a hybrid query generation scheme which employs fuzzy aggregation for including and excluding palette colors within the context of a fine art database containing various paintings and drawings. The aggregator herein exhibits flexibility in its logical behaviour through parameters that can be set by the designer as well permitting the exclusion of specific colors from queries. This translates to richer controls for a user wishing to locate works from a large art image database that have similar, yet complex color palettes. Experimentation on an image database of 464 paintings and drawings illustrate this fact, and a comparison with a weighted mean approach is provided.
    Digital Signal Processing, 2002. DSP 2002. 2002 14th International Conference on; 02/2002
  • [Show abstract] [Hide abstract]
    ABSTRACT: Digital visual data has been rapidly becoming more and more ubiquitous, and so content-based techniques to perform indexing are imperative. This paper outlines research geared towards an image retrieval system that identifies shapes in images and classify them into appropriate categories. The system functions on pre-processed, segmented images extracting component regions on the basis of color. This is followed by shape analysis using invariant moments with perceptual considerations made on the basis of subjective testing. The subjectivity is incorporated into the system via a set of thresholds whose strictness can be manipulated by the user. The implementation employing SQL and DB2 provided and 84% placement rate for the various images investigated.
    Proc SPIE 01/2001; 4299:486-493.
  • Advances in Intelligent Systems. 01/1999; 21:255-264.
  • [Show abstract] [Hide abstract]
    ABSTRACT: A new technique by which the electron micrographs of (111)7×7 Silicon are analyzed is discussed. In contrast to the conventional manner by which pseudocolor is introduced into normally gray scale surface scans, this method performs a high-level, knowledge based analysis to provide the viewer with additional information about the silicon sample at hand. Namely, blob recognition and analysis, as well as a priori knowledge of (111)7×7 Silicon can be utilized to delineate structural patterns and detect fault locations. The conveyance of information such as this is of much more consequence to an investigator interested in determining a sample’s uniformity and structure.
    Visual Information and Information Systems, Third International Conference, VISUAL '99, Amsterdam, The Netherlands, June 2-4, 1999, Proceedings; 01/1999
  • [Show abstract] [Hide abstract]
    ABSTRACT: A subjective analysis is performed on various classical, and order statistic-based color edge detectors. Order statistic edge detectors imply that image pixels within a specific region, are treated statistically such that outliers can be rejected from the general trends in the data. A different type of subjective rating system is employed here and the rationale behind its use is explained. The importance of subjective edge detection lies in the development of a color edge detector which can accurately simulate what is seen by humans.
    Proc SPIE 01/1998; 3304:260-267.
  • [Show abstract] [Hide abstract]
    ABSTRACT: There exist many experimental situations in which a subjective rather than an objective test of a specific variable proves to be a much more relevant method of investigation. Because of the intimate relationship between image processing and the human eye, subjective tests are extremely important in the final judgement if an image is passed by the human eye. In this paper, insight into what method of colour edge detection results in edge maps which are in best accordance with what the human eye sees. In particular, this paper presents a comparison of the relative subjectively-based performances of a group of basic order statistic and difference vector operator detectors
    Electrical and Computer Engineering, 1997. Engineering Innovation: Voyage of Discovery. IEEE 1997 Canadian Conference on; 06/1997
  • Image Analysis and Processing, 9th International Conference, ICIAP '97, Florence, Italy, September 17-19, 1997, Proceedings, Volume I; 01/1997
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Over the past five years, a huge influx of visual data has arisen within the realm of computing. Consequently, it is evident that a means of automatically indexing this visual information on the basis of content is required. This paper discusses a component of an image retrieval system with the ability to automatically locate and classify an image's constituent shapes. The images employed are pre-processed, and pre-segmented and analysis is performed on component regions which are separated using color. Shape analysis is performed via invariant moments and the subjectivity of shape classification is taken into account using data obtained from human testing. The subjective data is used to generate a predetermined set of classification thresholds for various simple shapes of which 84% were successfully classified.