Change search
Refine search result
1 - 25 of 25
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1. Aibinu, A.M.
    et al.
    Iqbal, Muhammad Imran
    Shafie, A.A.
    Salami, M.J.E.
    Nilsson, Mikael
    Vascular intersection detection in retina fundus images using a new hybrid approach2010In: Computers in Biology and Medicine, ISSN 0010-4825, E-ISSN 1879-0534, Vol. 40, no 1, p. 81-89Article in journal (Refereed)
    Abstract [en]

    The use of vascular intersection aberration as one of the signs when monitoring and diagnosing diabetic retinopathy from retina fundus images (FIs) has been widely reported in the literature. In this paper, a new hybrid approach called the combined cross-point number (CCN) method able to detect the vascular bifurcation and intersection points in FIs is proposed. The CCN method makes use of two vascular intersection detection techniques, namely the modified cross-point number (MCN) method and the simple cross-point number (SCN) method. Our proposed approach was tested on images obtained from two different and publicly available fundus image databases. The results show a very high precision, accuracy, sensitivity and low false rate in detecting both bifurcation and crossover points compared with both the MCN and the SCN methods.

  • 2. Bartunek, Josef Ström
    et al.
    Nilsson, Mikael
    Nordberg, Jörgen
    Claesson, Ingvar
    Adaptive Fingerprint Binarization by Frequency Domain Analysis2006Conference paper (Other academic)
    Abstract [en]

    This paper presents a new approach for fingerprint enhancement by using directional filters and binarization. A straightforward method for automatically tuning the size of local area is obtained by analyzing entire fingerprint image in the frequency domain. Hence, the algorithm will adjust adaptively to the local area of the fingerprint image, independent on the characteristics of the fingerprint sensor or the physical appearance of the fingerprints. Frequency analysis is carried out in the local areas to design directional filters. Experimental results are presented.

  • 3. Bartunek, Josef Ström
    et al.
    Nilsson, Mikael
    Nordberg, Jörgen
    Claesson, Ingvar
    Improved Adaptive Fingerprint Binarization2008Conference paper (Refereed)
    Abstract [en]

    In this paper improvements to a previous work are presented. Removing the redundant artifacts in the fingerprint mask is introduced enhancing the final result. The proposed method is entirely adaptive process adjusting to each fingerprint without any further supervision of the user. Hence, the algorithm is insensitive to the characteristics of the fingerprint sensor and the various physical appearances of the fingerprints. Further, a detailed description of fingerprint mask generation not fully described in the previous work is presented. The improved experimental results are presented.

  • 4. Bartunek, Josef Ström
    et al.
    Nilsson, Mikael
    Nordberg, Jörgen
    Claesson, Ingvar
    Neural Network based Minutiae Extraction from Skeletonized Fingerprints2006Conference paper (Other academic)
    Abstract [en]

    Human fingerprints are rich in details denoted minutiae. In this paper a method of minutiae extraction from fingerprint skeletons is described. To identify the different shapes and types of minutiae a neural network is trained to work as a classifier. The proposed neural network is applied throughout the fingerprint skeleton to locate various minutiae. A scheme to speed up the process is also presented. Extracted minutiae can then be used as identification marks for automatic fingerprint matching.

  • 5. Butt, Naveed R.
    et al.
    Nilsson, Mikael
    Jakobsson, Andreas
    Nordberg, Magnus
    Pettersson, Anna
    Wallin, Sara
    Östmark, Henric
    An Improved Classification Scheme for Standoff Detection of Explosives via Raman Spectroscopy2010Conference paper (Refereed)
    Abstract [en]

    Raman spectroscopy is a laser-based vibrational tech- nique that can provide spectral signatures unique to a multitude of compounds. The technique is gaining widespread interest as a method for detecting hidden explosives due to its sensitivity and ease of use. In this work, we present a computationally e±cient clas- si¯cation scheme for accurate stando® identi¯cation of several common explosives using visible-range Raman spectroscopy. Using real measurements, we evaluate and modify a recent correlation-based approach to classify Raman spectra from various both harmful and commonplace substances. The results show that the proposed approach can, at a distance of 30 me- ters, or more, successfully classify measured Raman spectra from several explosive substances, including Nitromethane, TNT, DNT, Hydrogen Peroxide, TATP and Ammonium Nitrate.

  • 6. Butt, Naveed R.
    et al.
    Nilsson, Mikael
    Jakobsson, Andreas
    Nordberg, Markus
    Pettersson, Anna
    Wallin, Sara
    Östmark, Henric
    Classification of Raman Spectra to Detect Hidden Explosives2011In: IEEE GEOSCIENCE AND REMOTE SENSING LETTERS , ISSN 1545-598X , Vol. 8, no 3, p. 517-521Article in journal (Refereed)
    Abstract [en]

    Raman spectroscopy is a laser-based vibrational technique that can provide spectral signatures unique to a multitude of compounds. The technique is gaining widespread interest as a method for detecting hidden explosives due to its sensitivity and ease of use. In this letter, we present a computationally efficient classification scheme for accurate standoff identification of several common explosives using visible-range Raman spectroscopy. Using real measurements, we evaluate and modify a recent correlation-based approach to classify Raman spectra from various harmful and commonplace substances. The results show that the proposed approach can, at a distance of 30 m, or more, successfully classify measured Raman spectra from several explosive substances, including nitromethane, trinitrotoluene, dinitrotoluene, hydrogen peroxide, triacetone triperoxide, and ammonium nitrate.

  • 7. Iqbal, Muhammad Imran
    et al.
    Aibinu, A.M.
    Nilsson, Mikael
    Tijani, I. B.
    Salami, M.J.E.
    Detection of Vascular Intersection in Retina Fundus Image Using Modified Cross Point Number and Neural Network Technique2008Conference paper (Refereed)
    Abstract [en]

    Vascular intersection can be used as one of the symptoms for monitoring and diagnosis of diabetic retinopathy from fundus images. In this work we apply the knowledge of digital image processing, fuzzy logic and neural network technique to detect bifurcation and vein-artery cross-over points in fundus images. The acquired images undergo preprocessing stage for illumination equalization and noise removal. Segmentation stage clusters the image into two distinct classes by the use of fuzzy c-means technique, neural network technique and modified cross-point number (MCN) methods were employed for the detection of bifurcation and cross-over points. MCN uses a 5x5 window with 16 neighboring pixels for efficient detection of bifurcation and cross over points in fundus images. Result obtained from applying this hybrid method on both real and simulated vascular points shows that this method perform better than the existing simple cross-point number (SCN) method, thus an improvement to the vascular point detection and a good tool in the monitoring and diagnosis of diabetic retinopathy. ©2008 IEEE.

  • 8. Maddala, Sainath
    et al.
    Bartunek, Josef Ström
    Blekinge Institute of Technology, School of Engineering, Department of Signal Processing.
    Nilsson, Mikael
    Blekinge Institute of Technology, School of Engineering, Department of Signal Processing.
    Implementation and evaluation of NIST biometric image software for fingerprint recognition2010Conference paper (Refereed)
    Abstract [en]

    Fingerprints are rich in details which are in the form of discontinuities in ridges known as minutiae and are unique for each person. This paper describes implementation and evaluation of an existing fingerprint recognition system in MATLAB environment. The selected system is developed by National Institute of Standards and Technology (NIST) denoted as Biometric Image Software (NBIS). The NBIS source code is written in ANSI C programming language. To be able to evaluate the algorithm in MATLAB a C language MEX-files has been used. The NBIS support both minutiae extraction and minutiae matching functions that have been employed in the evaluation. The implemented system has been tested on a Fingerprint Verification Competition (FVC) database. The results are presented as Receiver Operating Characteristics (ROC) graphs

  • 9.
    Maddala, Sainath
    et al.
    Blekinge Institute of Technology, School of Engineering, Department of Signal Processing.
    Tangellapally, Sreekanth Rao
    Blekinge Institute of Technology, School of Engineering, Department of Signal Processing.
    Bartunek, Josef Ström
    Blekinge Institute of Technology, School of Engineering, Department of Signal Processing.
    Nilsson, Mikael
    Blekinge Institute of Technology, School of Engineering, Department of Signal Processing.
    Implementation and evaluation of NIST Biometric Image Software for fingerprint recognition2011Conference paper (Refereed)
    Abstract [en]

    Fingerprints are rich in details which are in the form of discontinuities in ridges known as minutiae and are unique for each person. This paper describes implementation and evaluation of an existing fingerprint recognition system in MATLAB environment. The selected system is developed by National Institute of Standards and Technology (NIST) denoted as Biometric Image Software (NBIS). The NBIS source code is written in ANSI C programming language. To be able to evaluate the algorithm in MATLAB a C language MEX-files has been used. The NBIS support both minutiae extraction and minutiae matching functions that have been employed in the evaluation. The implemented system has been tested on a Fingerprint Verification Competition (FVC) database. The results are presented as Receiver Operating Characteristics (ROC) graphs.

  • 10. Muhammad, Azam Sheikh
    et al.
    Lavesson, Niklas
    Davidsson, Paul
    Nilsson, Mikael
    Analysis of Speed Sign Classification Algorithms Using Shape Based Segmentation of Binary Images2009Conference paper (Refereed)
    Abstract [en]

    Traffic Sign Recognition is a widely studied problem and its dynamic nature calls for the application of a broad range of preprocessing, segmentation, and recognition techniques but few databases are available for evaluation. We have produced a database consisting of 1,300 images captured by a video camera. On this database we have conducted a systematic experimental study. We used four different preprocessing techniques and designed a generic speed sign segmentation algorithm. Then we selected a range of contemporary speed sign classification algorithms using shape based segmented binary images for training and evaluated their results using four metrics, including accuracy and processing speed. The results indicate that Naive Bayes and Random Forest seem particularly well suited for this recognition task. Moreover, we show that two specific preprocessing techniques appear to provide a better basis for concept learning than the others.

  • 11.
    Nilsson, Mikael
    Blekinge Institute of Technology, School of Engineering, Department of Signal Processing.
    First Order Hidden Markov Model: Theory and Implementation Issues2005Report (Refereed)
    Abstract [en]

    This report explains the theory of Hidden Markov Models (HMMs). The emphasis is on the theory aspects in conjunction with the implementation issues that are encountered in a floating point processor. The main theory and implementation issues are based on the use of a Gaussian Mixture Model (GMM) as the state density in the HMM, and a Continuous Density Hidden Markov Model (CDHMM) is assumed. Suggestions and advice related to the implementation are given for a typical pattern recognition task.

  • 12. Nilsson, Mikael
    On Feature Extraction and Classification in Speech and Image Processing2007Doctoral thesis, comprehensive summary (Other academic)
    Abstract [en]

    The natural world is home to innumerable patterns in various forms, which humans are able to locate and interpret by means of the senses. This thesis presents and explores different techniques that mimic such behavior through the use of artificial sensors and computational power, i.e. aspects of machine learning with particular emphasis on pattern recognition. Theory and practical issues are explored with respect to two main operations; feature extraction and classification. On the topic of feature extraction, this thesis introduces a new signal processing transform, denoted the Successive Mean Quantization Transform (SMQT). The relevant theory, extensions and numerical transformations are presented, along with possible usage of this transform in various situations. Two different classifiers are investigated; the hidden Markov model and the sparse network of winnows. The hidden Markov model is a stochastic model which has been used successfully in the context of various pattern recognition applications. During the implementation of a complete system using the hidden Markov model, a number of possible numerical issues can arise. The relevant theory behind these numerical issues is presented, as are a number of possible solutions. The sparse network of winnows is a general purpose classifier. In the context of this thesis, it is tailored for the task of fast binary classification using lookup tables. Further, a scheme is proposed to split up this classifier in order to perform faster classification. This scheme is denoted the split up sparse network of winnows. The sections of this thesis dedicated to feature extraction and classification present a number of tools which are utilized further in three applications. The first application is concerned with the enhancement of noise degraded speech. Specifically, this application addresses the task of reducing non-stationary noise from speech using the hidden Markov model. The second application addresses the task of automatic image enhancement. For this task, the Successive Mean Quantization Transform is investigated. The final application is concerned with face detection. For this task, illumination problems and speed issues are discussed, along with proposed solutions.

  • 13. Nilsson, Mikael
    et al.
    Bartunek, Josef Ström
    Nordberg, Jörgen
    Claesson, Ingvar
    Human Whistle Detection and Frequency Estimation2008Conference paper (Refereed)
    Abstract [en]

    Human whistle could be a way to perform activation of different kind of devices, for example turn on and off a light in a smart room. Therefore, in this paper a human whistle detection and frequency estimation system is presented. Further, an investigation of human whistling and a robust non-linear feature extraction is presented. A system for robust performance due to sensor change and various noise situations is proposed using these features. Experiments in various noise situations are conducted.

  • 14. Nilsson, Mikael
    et al.
    Bartunek, Josef Ström
    Nordberg, Jörgen
    Claesson, Ingvar
    On Histograms and Spatiograms: Introduction of the Mapogram2008Conference paper (Refereed)
    Abstract [en]

    This paper introduces the concept of a mapogram. A mapogram may be viewed as a special form of spatiogram,which is a histogram containing additional spatial information. Additionally, this paper presents theory relevant to the creation of a proposed mapogram. A similarity measure derived from the Bhattacharyya coefficient is obtained in order to make comparisons between mapograms. Examples using a mapogram are given.

  • 15. Nilsson, Mikael
    et al.
    Dahl, Mattias
    Claesson, Ingvar
    A cepstrum domain HMM-based speech enhancement method applied to nonstationary noise2005Conference paper (Refereed)
    Abstract [en]

    This paper presents a Hidden Markov Model (HMM)-based speech enhancement method, aiming at reducing non-stationary noise from speech signals. The system is based on the assumption that the speech and the noise are additive and uncorrelated. Cepstral features are used to extract statistical information from both the speech and the noise. A-priori statistical information is collected from long training sequences into ergodic hidden Markov models. Given the ergodic models for the speech and the noise, a compensated speech-noise model is created by means of parallel model combination, using a log-normal approximation. During the compensation. the mean of every mixture in the speech and noise model is stored. The stored means are then used in the enhancement process to create the most likely speech and noise power spectral distributions using the forward algorithm combined with mixture probability. The distributions are used to generate a Wiener filter for every observation. The paper includes a performance evaluation of the speech enhancer for stationary as well as non-stationary noise environment.

  • 16. Nilsson, Mikael
    et al.
    Dahl, Mattias
    Claesson, Ingvar
    Digital Filter Design of IIR Filters using Real Valued Genetic Algorithm2003Conference paper (Refereed)
    Abstract [en]

    This paper presents a new paradigm for infinite impulse response (IIR) filter design using genetic algorithms (GA). By encode or transform the filter design problem into the z-plane the GA optimization procedure will be simplified. Additionally, given the z-plane encoding new mutation techniques are introduced, with the intention to locate promising regions in the search space. With proper design of the fitness function, the proposed algorithm can be used to evolve both full precision or quantized filter structures.

  • 17. Nilsson, Mikael
    et al.
    Dahl, Mattias
    Claesson, Ingvar
    Gray-Scale Image Enhancement using the SMQT2005Conference paper (Refereed)
    Abstract [en]

    This paper explores the Successive Mean Quantization Transform (SMQT) for automatic enhancement of gray-scale images. The transform is in the paper presented using set theory. The image enhancement capabilities and properties of the transform are analyzed. The transform is capable to perform both a nonlinear and a shape preserving stretch of the image histogram. Experiments and comparisons to histogram equalization are conducted.

  • 18. Nilsson, Mikael
    et al.
    Dahl, Mattias
    Claesson, Ingvar
    HMM-based speech enhancement applied in non-stationary noise using cepstral features and log-normal approximation2003Conference paper (Refereed)
    Abstract [en]

    This paper proposes a hidden Markov model (HMM)-based speech enhancement method, aiming at reducing non-stationary noise from speech signals. The system is based on the assumption that the speech and the noise are additive and uncorrelated. Cepstral features are used to extract statistical information from both the speech and the noise. A priori statistical information is collected from long training sequences into ergodic hidden Markov models. Given the ergodic models for the speech and the noise a compensated model is created by means of parallel model combination, using a log-normal approximation. During compensation, the mean of every mixture in the speech and noise model is stored. The stored means are then used in the enhancement process to create the most likely speech and noise power spectral distributions using the forward algorithm combined with mixture probability. The distributions are used to generate an optimal linear Wiener filter for every observation. An evaluation of the speech enhancer working in a non-stationary noise environment is performed.

  • 19. Nilsson, Mikael
    et al.
    Dahl, Mattias
    Claesson, Ingvar
    The Successive Mean Quantization Transform2005Conference paper (Refereed)
    Abstract [en]

    This paper presents the Successive Mean Quantization Transform (SMQT). The transform reveals the organization or structure of the data and removes properties such as gain and bias. The transform is described and applied in speech processing and image processing. The SMQT is considered as an extra processing step for the mel frequency cepstral coefficients commonly used in speech recognition. In image processing the transform is applied in automatic image enhancement and dynamic range compression.

  • 20. Nilsson, Mikael
    et al.
    Gertsovich, Irina
    Bartunek, Josef Ström
    Mouth Open or Closed Decision for Frontal Face Images with Given Eye Locations2010Conference paper (Refereed)
    Abstract [en]

    Abstract—Determination of the open/closed state of a mouth is a desired feature considering the face ISO standard. In this paper a simple score is proposed for automatic mouth open/closed decision. Landmarks around the mouth are explored in order to calculate the score. Analysis of mouth location, scale and rotation introduced by nonreflective similarity transformations utilizing prior knowledge regarding the eye locations with the accompanied Jesorsky error is presented. Further, a novel system is proposed in which a search in the four dimensions; position, scale, rotation and shape variation is combined with a discriminative classifier in order to perform alignment of the landmarks. The system is evaluated on the XM2VTS and IMM face databases indicating the feasibility of the proposed system. The evaluation is presented utilizing a cumulative distribution of the mouth open/closed score error.

  • 21. Nilsson, Mikael
    et al.
    Nordberg, Jörgen
    Claesson, Ingvar
    Face Detection using Local SMQT Features and Split Up SNoW Classifier2007Conference paper (Refereed)
    Abstract [en]

    The purpose of this paper is threefold: firstly, the local Successive Mean Quantization Transform features are proposed for illumination and sensor insensitive operation in object recognition. Secondly, a split up Sparse Network of Winnows is presented to speed up the original classifier. Finally, the features and classifier are combined for the task of frontal face detection. Detection results are presented for the MIT+CMU and the BioID databases. With regard to this face detector, the Receiver Operation Characteristics curve for the BioID database yields the best published result. The result for the CMU+MIT database is comparable to state-of-the-art face detectors. A Matlab version of the face detection algorithm can be downloaded from http://www.mathworks.com/matlabcentral/fileexchange/loadFile.do?objectId=13701&o bjectType=FILE

  • 22. Nilsson, Mikael
    et al.
    Nordberg, Jörgen
    Håkansson, Lars
    Claesson, Ingvar
    Feature Extraction and Classification Approaches in Condition Based Monitoring2007Conference paper (Refereed)
    Abstract [en]

    Creating a supervision tool in Condition Based Monitoring (CBM) for manufacturing processes by means of a pattern recognition approach, with emphasis on the feature extraction and classification is usually a difficult task. In particular manufacturing methods like drilling, turning, milling, boring and grinding are of concern for the discussion. The issue of machine tool downtime and degraded productivity and production costs continues to plague the industry and thus urge for reliable CBM systems enabling to predict or detect vibration, estimating tool wear and detect tool breakage. Extracting relevant information and choosing a suitable classifier is far from trivial for a given CBM scenario and requires knowledge of the process involved. This paper will discuss some common techniques used and also aim to indicate possible new approaches utilizing emerging techniques from other disciplines. In particular, nonlinear techniques such as Local Binary Pattern (LBP) and variants thereof are investigated as possible techniques for feature extraction. Generative as well as discriminative classifiers are also discussed.

  • 23. Nilsson, Mikael
    et al.
    Sattar, Farook
    Chngt, Hui Kheng
    Claesson, Ingvar
    Automatic Enhancement and Subjective Evaluation of Dental X-ray Images Using the SMQT2005Conference paper (Refereed)
    Abstract [en]

    This paper investigates the Successive Mean Quantization Transform (SMQT) for enhancement of dental X-ray images. The aim is to provide an automatic tool for enhancing the dental X-rays that would aid an interpreter, who is typically a specialist in dentistry. The evaluation is performed based on a subjective test by a clinical expert/endodontist who has vast experience in dental X-ray analysis and diagnosis. Based on the subjective test for a number of dental images, this SMQT based enhancement method is found to provide a useful tool for enhancing the diagnostic value of dental X-ray images. © 2005 IEEE.

  • 24. Swartling, Mikael
    et al.
    Nilsson, Mikael
    Grbic, Nedelko
    Detection of Vehicle Mounted Auditory Reverse Alarm using Hidden Markov Model2007Conference paper (Refereed)
    Abstract [en]

    This paper presents a method for automatically detecting vehicle mounted auditory reverse alarms, or other similar warning signals, based on hidden Markov model and pattern matching techniques. The method is designed for embedded realtime platforms. The purpose of the method is to embed it with active hearing protection devices, aiding the user in detecting warning signals in low SNR environments. Real recordings are used to evaluate the performance, and the results are presented.

  • 25. Swartling, Mikael
    et al.
    Nilsson, Mikael
    Grbic, Nedelko
    Distinguishing True and False Source Locations when Localizing Multiple Concurrent Speech Sources2008Conference paper (Refereed)
    Abstract [en]

    A permutation problem arises in the case of locating multiple speech sources using several sensor arrays in the far field. The intersection of different direction of arrival (DOA) estimates between sensor arrays leads to a set of real source locations as well as a set of false intersections. This paper presents a novel method for pairing DOA estimates from different sensor arrays, resulting in the corresponding real intersection points. The algorithm presented is numerically efficient and suitable for real time implementations. Real room recordings are used to evaluate the method.

1 - 25 of 25
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf