oru.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Tolt, Gustav
Publications (5 of 5) Show all publications
Tolt, G. & Kalaykov, I. (2005). A fuzzy-similarity-based approach for high-speed real-time image processing. In: Intelligent Control, 2005 : Proceedings of the 2005 IEEE International Symposium on, Mediterrean Conference on Control and Automation . Paper presented at 2005 IEEE International Symposium on Intelligent Control and 13th Mediterranean Conference on Control and Automation (pp. 1240-1245).
Open this publication in new window or tab >>A fuzzy-similarity-based approach for high-speed real-time image processing
2005 (English)In: Intelligent Control, 2005 : Proceedings of the 2005 IEEE International Symposium on, Mediterrean Conference on Control and Automation , 2005, p. 1240-1245Conference paper, Published paper (Refereed)
Abstract [en]

In this paper, we present a number of algorithms for performing some basic image processing tasks. The common denominator is the fuzzy similarity framework, that is used for representing vagueness and uncertainty associated with the similarity concept. The algorithms are designed so as to be implementable on FPGAs, making extensive use of the FPGA's parallel processing capabilities. Due to the limited space, we give pointers to previously published work for more details about the algorithms

Keywords
FPGA, fuzzy logic, image processing, parallel processing, real-time systems, system-on-chip
National Category
Computer Sciences
Research subject
Computer and Systems Science
Identifiers
urn:nbn:se:oru:diva-4276 (URN)10.1109/.2005.1467192 (DOI)
Conference
2005 IEEE International Symposium on Intelligent Control and 13th Mediterranean Conference on Control and Automation
Available from: 2007-12-14 Created: 2007-12-14 Last updated: 2018-01-13Bibliographically approved
Tolt, G. (2005). Fuzzy similarity-based image processing. (Doctoral dissertation). Örebro: Örebro universitetsbibliotek
Open this publication in new window or tab >>Fuzzy similarity-based image processing
2005 (English)Doctoral thesis, monograph (Other academic)
Abstract [en]

Computer vision problems require low-level operations, e.g. noise reduction and edge detection, as well as high-level operations, e.g. object recognition and image understanding. Letting a PC carry out all computations is convenient but quite inefficient. One approach for improving the performance of the vision system is to bring as much as possible of the computationally intensive low-level operations closer to the camera using dedicated hardware devices, thus letting the PC focus on high-level tasks. In this thesis we present novel fuzzy techniques for reducing noise, determining edgeness and detecting junctions as well as stereo matching measures for color images, as building blocks of complex vision systems, e.g. for robot motion control or other industrial applications.

The noise reduction is achieved by evaluating a number of fuzzy rules, each suggesting a particular filtering output. The firing strengths of the rules correspond to the degrees of similarity found among the pixels in the local processing window. The approach for determining edgeness is based on fuzzy rules that combine the estimated gradient magnitude with information about the homogeneity in different parts of the processing window. In this way the response from false edges is suppressed. In the junction detection approach we let the intersection between fuzzy sets represent the similarity between information obtained with different window sizes. The fuzzy sets represent the possible orientations of line segments in the window and non-zero intersections of the fuzzy sets indicate the presence of line segments in the window. The number of line segments characterize the nature of the junction. For the stereo matching measures, the global similarity betwen two pixels is defined in terms of fuzzy conjunctions of local similarities (color and edgeness). The proposed techniques have been designed for hardware implementation, making use of extensive parallelism and primarily simple numerical operations. The performance is shown in a number of experiments, and the strengths and limitations of the techniques are discussed.

Place, publisher, year, edition, pages
Örebro: Örebro universitetsbibliotek, 2005. p. 136
Series
Örebro Studies in Technology, ISSN 1650-8580 ; 18
Keywords
Image analysis, Bildanalys
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Industrial Measurement Technology
Identifiers
urn:nbn:se:oru:diva-97 (URN)91-7668-432-6 (ISBN)
Public defence
2005-04-07, Hörsal T, Teknikhuset, Örebro universitet, Fakultetsgatan 1, 70182, Örebro, 10:00
Opponent
Supervisors
Available from: 2005-03-17 Created: 2005-03-17 Last updated: 2018-01-13Bibliographically approved
Tolt, G. (2003). Fuzzy-similarity-based low-level image processing: licentiate thesis. (Licentiate dissertation). Örebro: Örebro universitetsbibliotek
Open this publication in new window or tab >>Fuzzy-similarity-based low-level image processing: licentiate thesis
2003 (English)Licentiate thesis, monograph (Other academic)
Place, publisher, year, edition, pages
Örebro: Örebro universitetsbibliotek, 2003. p. 77
Series
Örebro Studies in Technology, ISSN 1650-8580 ; 7
National Category
Control Engineering
Research subject
Automatic Control
Identifiers
urn:nbn:se:oru:diva-4222 (URN)
Available from: 2007-07-25 Created: 2007-07-25 Last updated: 2017-10-18Bibliographically approved
Kalaykov, I. & Tolt, G. (2002). Fast fuzzy signal and image processing hardware. In: Proceedings, NAFIPS 2002: Annual meeting of the North American fuzzy information processing society, 2002. Paper presented at NAFIPS 2002. Annual meeting of the North American fuzzy information processing society (pp. 7-12).
Open this publication in new window or tab >>Fast fuzzy signal and image processing hardware
2002 (English)In: Proceedings, NAFIPS 2002: Annual meeting of the North American fuzzy information processing society, 2002, 2002, p. 7-12Conference paper, Published paper (Refereed)
Abstract [en]

The paper presents the development of fast fuzzy logic based hardware for various applications such as controllers for very fast processes, real-time image processing and pattern recognition. It is based on the fired-rules-hyper-cube (FRHC) concept, characterized by extremely simple way of the fuzzy inference in a layered parallel architecture. The processing time slightly depends on the number of inputs of the fuzzy system and does not depend on the number of rules and fuzzy partitioning of all variables. Most important is the inherent high speed of processing because of the parallelism and pipelining, implemented in all layers.

Keywords
fast fuzzy logic based hardware, fired-rules-hyper-cube concept, fuzzy inference, layered parallel architectures, pipelining, real-time image processing
National Category
Computer Sciences
Research subject
Computer and Systems Science
Identifiers
urn:nbn:se:oru:diva-4284 (URN)10.1109/NAFIPS.2002.1018021 (DOI)0-7803-7461-4 (ISBN)
Conference
NAFIPS 2002. Annual meeting of the North American fuzzy information processing society
Available from: 2007-12-14 Created: 2007-12-14 Last updated: 2018-01-13Bibliographically approved
Tolt, G. & Kalaykov, I. (2001). Fuzzy-similarity-based noise cancellation for real-time image processing. Paper presented at The 10th IEEE International Conference on Fuzzy Systems, 2001.
Open this publication in new window or tab >>Fuzzy-similarity-based noise cancellation for real-time image processing
2001 (English)Conference paper, Published paper (Refereed)
Abstract [en]

We introduce a new algorithm for image noise cancellation based on fuzzy similarity and homogeneity. The proposed method allows simple tuning of fuzzy filter properties and it is very convenient for high-speed real-time image processing. A detailed analysis of the filter properties is presented to support tuning its parameters for a particular application. Test examples and comparisons with other image noise cancellation techniques show the advantages of the method.

Keywords
fuzzy filter property tuning, fuzzy-similarity-based noise cancellation, high-speed real-time image processing, image noise cancellation, real-time image processing
National Category
Computer Sciences
Research subject
Computer and Systems Science
Identifiers
urn:nbn:se:oru:diva-4283 (URN)10.1109/FUZZ.2001.1007233 (DOI)0-7803-7293-X (ISBN)
Conference
The 10th IEEE International Conference on Fuzzy Systems, 2001
Available from: 2007-12-14 Created: 2007-12-14 Last updated: 2018-01-13Bibliographically approved
Organisations

Search in DiVA

Show all publications