Change search
Link to record
Permanent link

Direct link
BETA
Kusetogullari, HüseyinORCID iD iconorcid.org/0000-0001-7536-3349
Alternative names
Publications (10 of 10) Show all publications
Kusetogullari, H., Yavariabdi, A., Cheddad, A., Grahn, H. & Johan, H. (2019). ARDIS: A Swedish Historical Handwritten Digit Dataset. Neural computing & applications (Print)
Open this publication in new window or tab >>ARDIS: A Swedish Historical Handwritten Digit Dataset
Show others...
2019 (English)In: Neural computing & applications (Print), ISSN 0941-0643, E-ISSN 1433-3058Article in journal (Refereed) Epub ahead of print
Abstract [en]

This paper introduces a new image-based handwrittenhistorical digit dataset named ARDIS (Arkiv DigitalSweden). The images in ARDIS dataset are extractedfrom 15,000 Swedish church records which were writtenby different priests with various handwriting styles in thenineteenth and twentieth centuries. The constructed datasetconsists of three single digit datasets and one digit stringsdataset. The digit strings dataset includes 10,000 samplesin Red-Green-Blue (RGB) color space, whereas, the otherdatasets contain 7,600 single digit images in different colorspaces. An extensive analysis of machine learning methodson several digit datasets is examined. Additionally, correlationbetween ARDIS and existing digit datasets ModifiedNational Institute of Standards and Technology (MNIST)and United States Postal Service (USPS) is investigated. Experimental results show that machine learning algorithms,including deep learning methods, provide low recognitionaccuracy as they face difficulties when trained on existingdatasets and tested on ARDIS dataset. Accordingly, ConvolutionalNeural Network (CNN) trained on MNIST andUSPS and tested on ARDIS provide the highest accuracies 58.80% and 35.44%, respectively. Consequently, the resultsreveal that machine learning methods trained on existingdatasets can have difficulties to recognize digits effectivelyon our dataset which proves that ARDIS dataset hasunique characteristics. This dataset is publicly available forthe research community to further advance handwritten digitrecognition algorithms.

Place, publisher, year, edition, pages
Springer Nature Switzerland, 2019
Keywords
Handwritten digit recognition, ARDIS dataset, Machine learning methods, Benchmark
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:bth-17741 (URN)10.1007/s00521-019-04163-3 (DOI)
Funder
Knowledge Foundation, 20140032
Available from: 2019-03-27 Created: 2019-03-27 Last updated: 2019-05-02Bibliographically approved
Kusetogullari, H. & Yavariabdi, A. (2018). Evolutionary multiobjective multiple description wavelet based image coding in the presence of mixed noise in images. Applied Soft Computing, 73, 1039-1052
Open this publication in new window or tab >>Evolutionary multiobjective multiple description wavelet based image coding in the presence of mixed noise in images
2018 (English)In: Applied Soft Computing, ISSN 1568-4946, E-ISSN 1872-9681, Vol. 73, p. 1039-1052Article in journal (Refereed) Published
Abstract [en]

In this paper, a novel method for generation of multiple description (MD) wavelet based image coding is proposed by using Multi-Objective Evolutionary Algorithms (MOEAs). Complexity of the multimedia transmission problem has been increased for MD coders if an input image is affected by any type of noise. In this case, it is necessary to solve two different problems which are designing the optimal side quantizers and estimating optimal parameters of the denoising filter. Existing MD coding (MDC) generation methods are capable of solving only one problem which is to design side quantizers from the given noise-free image but they can fail reducing any type of noise on the descriptions if they applied to the given noisy image and this will cause bad quality of multimedia transmission in networks. Proposed method is used to overcome these difficulties to provide effective multimedia transmission in lossy networks. To achieve it, Dual Tree-Complex Wavelet Transform (DT-CWT) is first applied to the noisy image to obtain the subbands or set of coefficients which are used as a search space in the optimization problem. After that, two different objective functions are simultaneously employed in the MOEA to find pareto optimal solutions with the minimum costs by evolving the initial individuals through generations. Thus, optimal quantizers are created for MDCs generation and obtained optimum parameters are used in the image filter to remove the mixed Gaussian impulse noise on the descriptions effectively. The results demonstrate that proposed method is robust to the mixed Gaussian impulse noise, and offers a significant improvement of optimal side quantizers for balanced MDCs generation at different bitrates. © 2018 Elsevier B.V.

Place, publisher, year, edition, pages
Elsevier Ltd, 2018
Keywords
Adaptive and optimal quantizer design, Mixed Gaussian impulse noise reduction, Multi-objective formulation and optimization, Multiple description coding (MDC) for multimedia communication, Wavelets, Codes (symbols), Complex networks, Evolutionary algorithms, Gaussian distribution, Image segmentation, Impulse noise, Multimedia systems, Noise abatement, Pareto principle, Problem solving, Wavelet transforms, Dual tree complex wavelet transform (DT-CWT), Multi objective evolutionary algorithms, Multi-media communications, Multi-objective formulation, Multimedia transmissions, Quantizer design, Wavelet-based image coding, Image coding
National Category
Other Computer and Information Science
Identifiers
urn:nbn:se:bth-17199 (URN)10.1016/j.asoc.2018.10.015 (DOI)000450124900072 ()
Available from: 2018-11-01 Created: 2018-11-01 Last updated: 2018-12-13Bibliographically approved
Demir, M. F., Cankirli, A., Karabatak, B., Yavariabdi, A., Mendi, E. & Kusetogullari, H. (2018). Real-Time Resistor Color Code Recognition using Image Processing in Mobile Devices. In: JardimGoncalves, R; Mendonca, JP; Jotsov, V; Marques, M; Martins, J; Bierwolf, R (Ed.), 9th International Conference on Intelligent Systems 2018: Theory, Research and Innovation in Applications, IS 2018 - Proceedings: . Paper presented at 9th International Conference on Intelligent Systems, IS 2018; Funchal - Madeira; Portugal; 25 September 2018 through 27 September (pp. 26-30). Institute of Electrical and Electronics Engineers Inc.
Open this publication in new window or tab >>Real-Time Resistor Color Code Recognition using Image Processing in Mobile Devices
Show others...
2018 (English)In: 9th International Conference on Intelligent Systems 2018: Theory, Research and Innovation in Applications, IS 2018 - Proceedings / [ed] JardimGoncalves, R; Mendonca, JP; Jotsov, V; Marques, M; Martins, J; Bierwolf, R, Institute of Electrical and Electronics Engineers Inc. , 2018, p. 26-30Conference paper, Published paper (Refereed)
Abstract [en]

This paper proposes a real-time video analysis algorithm to read the resistance value of a resistor using a color recognition technique. To achieve this, firstly, a nonlinear filtering is applied to input video frame to smooth intensity variations and remove impulse noises. After that, a photometric invariants technique is employed to transfer the video frame from RGB color space to Hue-Saturation-Value (HSV) color space, which decreases sensitivity of the proposed method to illumination changes. Next, a region of interest is defined to automatically detect resistor's colors and then an Euclidean distance based clustering strategy is employed to recognize the color bars. The proposed method provides a wide range of color classification which includes twelve colors. In addition, it utilizes relatively low computational time which makes it suitable for real-time mobile video applications. The experiments are performed on a variety of test videos and results show that the proposed method has low error rate compared to the other resistor color code recognition mobile applications. © 2018 IEEE.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2018
Keywords
Android platform, Color recognition, Decision making, Image and video processing, Resistor classification, Bar codes, Color, Color codes, Computation theory, Image segmentation, Impulse noise, Intelligent systems, Resistors, Video signal processing, Android platforms, Hue saturation values, Intensity variations, Photometric invariants, Real-time mobile video, Real-time video analysis, Color image processing
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-18025 (URN)10.1109/IS.2018.8710533 (DOI)000469337900005 ()9781538670972 (ISBN)
Conference
9th International Conference on Intelligent Systems, IS 2018; Funchal - Madeira; Portugal; 25 September 2018 through 27 September
Available from: 2019-06-14 Created: 2019-06-14 Last updated: 2019-07-01Bibliographically approved
Yasar, F. G. & Kusetogullari, H. (2018). Underwater human body detection using computer vision algorithms. In: 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018: . Paper presented at 26th IEEE Signal Processing and Communications Applications Conference, SIU, Altin Yunus Resort ve Thermal HotelIzmir; Turkey (pp. 1-4). Institute of Electrical and Electronics Engineers Inc.
Open this publication in new window or tab >>Underwater human body detection using computer vision algorithms
2018 (English)In: 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018, Institute of Electrical and Electronics Engineers Inc. , 2018, p. 1-4Conference paper, Published paper (Refereed)
Abstract [en]

The number of studies to ensure the security when life-threatening unexpected events are encountered increases. Increasing of time spent under the water can cause the death of people. Thus, people who are in a risk of suffocation in the water must be found for early intervention and this process must be quick. The main contribution of this study is to detect and to track the people under the water quickly. Thresholding, Background Subtraction, Interframe Difference and Foreground Detection methods have been applied to create the silhouette of the people under the water. These methods have been demonstrated on videos which are found from internet. © 2018 IEEE.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2018
Keywords
Computer vision, Human detection, Image processing, Electrical engineering, Signal processing, Background subtraction, Computer vision algorithms, Early intervention, Foreground detection, Human body detections, Inter-frame differences, Unexpected events
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-16919 (URN)10.1109/SIU.2018.8404305 (DOI)2-s2.0-85050803229 (Scopus ID)9781538615010 (ISBN)
Conference
26th IEEE Signal Processing and Communications Applications Conference, SIU, Altin Yunus Resort ve Thermal HotelIzmir; Turkey
Available from: 2018-08-21 Created: 2018-08-21 Last updated: 2018-08-21Bibliographically approved
Yavariabdi, A., Kusetogullari, H., Mendi, E. & Karabatak, B. (2018). Unsupervised Change Detection using Thin Cloud-Contaminated Landsat Images. In: JardimGoncalves, R; Mendonca, JP; Jotsov, V; Marques, M; Martins, J; Bierwolf, R (Ed.), 9th International Conference on Intelligent Systems 2018: Theory, Research and Innovation in Applications, IS 2018 - Proceedings: . Paper presented at 9th International Conference on Intelligent Systems, IS 2018; Funchal - Madeira; Portugal; 25 September 2018 through 27 September (pp. 21-25). Institute of Electrical and Electronics Engineers Inc.
Open this publication in new window or tab >>Unsupervised Change Detection using Thin Cloud-Contaminated Landsat Images
2018 (English)In: 9th International Conference on Intelligent Systems 2018: Theory, Research and Innovation in Applications, IS 2018 - Proceedings / [ed] JardimGoncalves, R; Mendonca, JP; Jotsov, V; Marques, M; Martins, J; Bierwolf, R, Institute of Electrical and Electronics Engineers Inc. , 2018, p. 21-25Conference paper, Published paper (Refereed)
Abstract [en]

In this paper, a novel unsupervised change detection method is proposed to automatically detect changes between two cloud-contaminated Landsat images. To achieve this, firstly, a photometric invariants technique with Stationary Wavelet Transform (SWT) are applied to input images to decrease the influence of cloud and noise artifacts in the change detection process. Then, mean shift image filtering is employed on the sub-band difference images, generated via image differencing technique, to smooth the images. Next, multiple binary change detection masks are obtained by partitioning the pixels in each of the smoothed sub-band difference images into two clusters using Fuzzy c-means (FCM). Finally, the binary masks are fused using Markov Random Field (MRF) to generate the final solution. Experiments on both semi-simulated and real data sets show the effectiveness and robustness of the proposed change detection method in noisy and cloud-contaminated Landsat images. © 2018 IEEE.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2018
Keywords
Change detection, Fuzzy c-means, Landsat images, Mean-shift, Wavelet, Fuzzy systems, Image segmentation, Intelligent systems, Magnetorheological fluids, Markov processes, Fuzzy C mean, Mean shift, Wavelet transforms
National Category
Computer Engineering
Identifiers
urn:nbn:se:bth-18024 (URN)10.1109/IS.2018.8710473 (DOI)000469337900004 ()2-s2.0-85065972639 (Scopus ID)9781538670972 (ISBN)
Conference
9th International Conference on Intelligent Systems, IS 2018; Funchal - Madeira; Portugal; 25 September 2018 through 27 September
Available from: 2019-06-14 Created: 2019-06-14 Last updated: 2019-07-01Bibliographically approved
Kusetogullari, H. (2018). Unsupervised Text Binarization in Handwritten Historical Documents Using k-Means Clustering. In: Bi, Y Kapoor, S Bhatia, R (Ed.), PROCEEDINGS OF SAI INTELLIGENT SYSTEMS CONFERENCE (INTELLISYS) 2016, VOL 2: . Paper presented at SAI Annual Conference on Areas of Intelligent Systems and Artificial Intelligence and their Applications to the Real World (IntelliSys), SEP 21-22, 2016, London, ENGLAND (pp. 23-32). SPRINGER INTERNATIONAL PUBLISHING AG
Open this publication in new window or tab >>Unsupervised Text Binarization in Handwritten Historical Documents Using k-Means Clustering
2018 (English)In: PROCEEDINGS OF SAI INTELLIGENT SYSTEMS CONFERENCE (INTELLISYS) 2016, VOL 2 / [ed] Bi, Y Kapoor, S Bhatia, R, SPRINGER INTERNATIONAL PUBLISHING AG , 2018, p. 23-32Conference paper, Published paper (Refereed)
Abstract [en]

In this paper, we propose a novel technique for unsupervised text binarization in handwritten historical documents using k-means clustering. In the text binarization problem, there are many challenges such as noise, faint characters and bleed-through and it is necessary to overcome these tasks to increase the correct detection rate. To overcome these problems, preprocessing strategy is first used to enhance the contrast to improve faint characters and Gaussian Mixture Model (GMM) is used to ignore the noise and other artifacts in the handwritten historical documents. After that, the enhanced image is normalized which will be used in the postprocessing part of the proposed method. The handwritten binarization image is achieved by partitioning the normalized pixel values of the handwritten image into two clusters using k-means clustering with k = 2 and then assigning each normalized pixel to the one of the two clusters by using the minimum Euclidean distance between the normalized pixels intensity and mean normalized pixel value of the clusters. Experimental results verify the effectiveness of the proposed approach.

Place, publisher, year, edition, pages
SPRINGER INTERNATIONAL PUBLISHING AG, 2018
Series
Lecture Notes in Networks and Systems, ISSN 2367-3370 ; 16
Keywords
Handwritten text binarization, Image processing, k-means clustering, Document images
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-17280 (URN)10.1007/978-3-319-56991-8_3 (DOI)000448662500003 ()978-3-319-56991-8 (ISBN)
Conference
SAI Annual Conference on Areas of Intelligent Systems and Artificial Intelligence and their Applications to the Real World (IntelliSys), SEP 21-22, 2016, London, ENGLAND
Available from: 2018-11-15 Created: 2018-11-15 Last updated: 2019-04-05
Kusetogullari, H. & Yavariabdi, A. (2017). Change Detection in Multispectral Landsat Images Using Multiobjective Evolutionary Algorithm. IEEE Geoscience and Remote Sensing Letters, 14(3), 414-418, Article ID 10.1109/LGRS.2016.2645742.
Open this publication in new window or tab >>Change Detection in Multispectral Landsat Images Using Multiobjective Evolutionary Algorithm
2017 (English)In: IEEE Geoscience and Remote Sensing Letters, ISSN 1545-598X, E-ISSN 1558-0571, Vol. 14, no 3, p. 414-418, article id 10.1109/LGRS.2016.2645742Article in journal (Refereed) Published
Abstract [en]

In this letter, we propose a novel method for unsupervised change detection in multitemporal multispectral Landsat images using multiobjective evolutionary algorithm (MOEA). The proposed method minimizes two different objective functions using MOEA to provide tradeoff between each other. The objective functions are used for evaluating changed and unchanged regions of the difference image separately. The difference image is obtained by using the structural similarity index measure method, which provides combination of the comparisons of luminance, contrast, and structure between two images. By evolving a population of solutions in the MOEA, a set of Pareto optimal solution is estimated in a single run. To find the best solution, a Markov random field fusion approach is used. Experiments on semisynthetic and real-world data sets show the efficiency and effectiveness of the proposed method.

Place, publisher, year, edition, pages
IEEE, 2017
Keywords
remote sensing, Change detection, image processing, Landsat images, multiobjective evolutionary algorithms (MOEAs)
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:bth-13978 (URN)10.1109/LGRS.2016.2645742 (DOI)000395908600028 ()
Available from: 2017-03-02 Created: 2017-03-02 Last updated: 2017-11-29Bibliographically approved
Cheddad, A., Kusetogullari, H. & Grahn, H. (2017). Object recognition using shape growth pattern. In: Proceedings of the 10th International Symposium on Image and Signal Processing and Analysis, ISPA: . Paper presented at 10th International Symposium on Image and Signal Processing and Analysis (ISPA), Ljubljana (pp. 47-52). IEEE Computer Society Digital Library, Article ID 8073567.
Open this publication in new window or tab >>Object recognition using shape growth pattern
2017 (English)In: Proceedings of the 10th International Symposium on Image and Signal Processing and Analysis, ISPA, IEEE Computer Society Digital Library, 2017, p. 47-52, article id 8073567Conference paper, Published paper (Refereed)
Abstract [en]

This paper proposes a preprocessing stage to augment the bank of features that one can retrieve from binary images to help increase the accuracy of pattern recognition algorithms. To this end, by applying successive dilations to a given shape, we can capture a new dimension of its vital characteristics which we term hereafter: the shape growth pattern (SGP). This work investigates the feasibility of such a notion and also builds upon our prior work on structure preserving dilation using Delaunay triangulation. Experiments on two public data sets are conducted, including comparisons to existing algorithms. We deployed two renowned machine learning methods into the classification process (i.e., convolutional neural network-CNN- and random forests-RF-) since they perform well in pattern recognition tasks. The results show a clear improvement of the proposed approach's classification accuracy (especially for data sets with limited training samples) as well as robustness against noise when compared to existing methods.

Place, publisher, year, edition, pages
IEEE Computer Society Digital Library, 2017
Keywords
Binary image dilations, convolutional neural network, machine learning, pattern recognition, shape growth pattern
National Category
Computer Systems Signal Processing
Identifiers
urn:nbn:se:bth-15416 (URN)10.1109/ISPA.2017.8073567 (DOI)000442428600009 ()978-1-5090-4011-7 (ISBN)
Conference
10th International Symposium on Image and Signal Processing and Analysis (ISPA), Ljubljana
Projects
Scalable resource efficient systems for big data analytics
Available from: 2017-11-01 Created: 2017-11-01 Last updated: 2018-09-06Bibliographically approved
Kusetogullari, H., Grahn, H. & Lavesson, N. (2016). Handwriting image enhancement using local learning windowing, Gaussian Mixture Model and k-means clustering. In: 2016 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2016: . Paper presented at 2016 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2016, Limassol (pp. 305-310). Institute of Electrical and Electronics Engineers Inc., Article ID 7886054.
Open this publication in new window or tab >>Handwriting image enhancement using local learning windowing, Gaussian Mixture Model and k-means clustering
2016 (English)In: 2016 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2016, Institute of Electrical and Electronics Engineers Inc. , 2016, p. 305-310, article id 7886054Conference paper, Published paper (Refereed)
Abstract [en]

In this paper, a new approach is proposed to enhance the handwriting image by using learning-based windowing contrast enhancement and Gaussian Mixture Model (GMM). A fixed size window moves over the handwriting image and two quantitative methods which are discrete entropy (DE) and edge-based contrast measure (EBCM) are used to estimate the quality of each patch. The obtained results are used in the unsupervised learning method by using k-means clustering to assign the quality of handwriting as bad (if it is low contrast) or good (if it is high contrast). After that, if the corresponding patch is estimated as low contrast, a contrast enhancement method is applied to the window to enhance the handwriting. GMM is used as a final step to smoothly exchange information between original and enhanced images to discard the artifacts to represent the final image. The proposed method has been compared with the other contrast enhancement methods for different datasets which are Swedish historical documents, DIBCO2010, DIBCO2012 and DIBCO2013. Results illustrate that proposed method performs well to enhance the handwriting comparing to the existing contrast enhancement methods. © 2016 IEEE.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2016
Keywords
contrast enhancement, Gaussian mixture modeling, Handwriting image enhancement, k-means clustering, learning-based windowing, Gaussian distribution, Image enhancement, Image segmentation, Unsupervised learning, Discrete entropy, Gaussian Mixture Model, Historical documents, Quantitative method, Unsupervised learning method, Signal processing
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-14146 (URN)10.1109/ISSPIT.2016.7886054 (DOI)000406122500056 ()2-s2.0-85017608194 (Scopus ID)9781509058440 (ISBN)
Conference
2016 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2016, Limassol
Funder
Knowledge Foundation, 20140032
Available from: 2017-05-04 Created: 2017-05-04 Last updated: 2018-02-02Bibliographically approved
Kusetogullari, H. & Yavariabdi, A. (2016). Self-Adaptive Hybrid PSO-GA Method for Change Detection Under Varying Contrast Conditions in Satellite Images. In: Proceedings of the 2016 SAI Computing Conference (SAI): . Paper presented at SAI Computing Conference (SAI), JUL 13-15, 2016, London, ENGLAND (pp. 361-368). IEEE
Open this publication in new window or tab >>Self-Adaptive Hybrid PSO-GA Method for Change Detection Under Varying Contrast Conditions in Satellite Images
2016 (English)In: Proceedings of the 2016 SAI Computing Conference (SAI), IEEE, 2016, p. 361-368Conference paper, Published paper (Refereed)
Abstract [en]

This paper proposes a new unsupervised satellite change detection method, which is robust to illumination changes. To achieve this, firstly, a preprocessing strategy is used to remove illumination artifacts and results in less false detection than traditional threshold-based algorithms. Then, we use the corrected input data to define a new fitness function based on the difference image. The purpose of using Self-Adaptive Hybrid Particle Swarm Optimization-Genetic Algorithm (SAPSOGA) is to combine two meta-heuristic optimization algorithms to search and find the feasible solution in the NP-hard change detection problem rapidly and efficiently. The hybrid algorithm is employed by letting the GA and PSO run simultaneously and similarities of GA and PSO have been considered to implement the algorithm, i.e. the population. In the SAPSOGA employed, in each iteration/generation the two population based algorithms share different amount of information or individual(s) between themselves. Thus, each algorithm informs each other about their best optimum results (fitness values and solution representations) which are obtained in their own population. The fitness function is minimized by using binary based SAPSOGA approach to produce binary change detection masks in each iteration to obtain the optimal change detection mask between two multi temporal multi spectral landsat images. The proposed approach effectively optimizes the change detection problem and finds the final change detection mask.

Place, publisher, year, edition, pages
IEEE, 2016
Keywords
Remote sensing; Image processing; Optimization; Self-adaptive hybrid algorithm; Genetic algorithm; Binary particle swarm optimization
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:bth-13683 (URN)000389451900050 ()978-1-4673-8460-5 (ISBN)
Conference
SAI Computing Conference (SAI), JUL 13-15, 2016, London, ENGLAND
Available from: 2016-12-30 Created: 2016-12-30 Last updated: 2018-01-13Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-7536-3349

Search in DiVA

Show all publications