@ee.duth.gr
Professor at Electrical and Computer Engineering Department
Democritus University of Thrace
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Nikolaos Detsikas, Nikolaos Mitianoudis, and Nikolaos Papamarkos
Elsevier BV
Vasileios Arampatzakis, George Pavlidis, Nikolaos Mitianoudis, and Nikos Papamarkos
Institute of Electrical and Electronics Engineers (IEEE)
Estimation of depth in two-dimensional images is among the challenging topics in Computer Vision. This is a well-studied but also an ill-posed problem, which has long been the focus of intense research. This paper is an in-depth review of the topic, presenting two aspects, one that considers the mechanisms of human depth perception, and another that includes the various Deep Learning approaches. The methods are presented in a compact and structured way that outlines the topic and categorizes the approaches according to the line of research followed in the recent decade. Although there has been significant advancement in the topic, it was without any connection with human depth perception and the potential benefits from this sector.
I. Vourkas, A. Abusleme, N. Vasileiadis, G. Ch. Sirakoulis, and N. Papamarkos
IEEE
Research progress in neuromorphic hardware, capable of biological perception and cognitive information processing, is leading the way towards a revolution in computing technology. Current research efforts have focused mainly on resistive switching devices, the electronic analog of synapses in artificial neural networks (ANNs), and the crossbar nanoarchitecture, for its huge connectivity and maximum integration density. In this context, this work presents the design and simulation of a memristive crossbar-based ANN for text recognition tasks, implementing a novel computing algorithm. In such case study, important issues during the application mapping process are identified and properly addressed at device and circuit level. The computing capabilities of the proposed system are highlighted through SPICE-level circuit simulations, which show excellent agreement with theoretical simulation results.
Maria Ntonti and Nikos Papamarkos
ACTAPRESS
This paper describes a new technique for document retrieval using a web camera in an office environment. The architecture of the aforementioned method consists of three main stages: segmentation, restoration and retrieval. Firstly, the document image is taken with a web camera and the segmentation process is applied to locate the four corners of the document and isolate it. Then we proceed to document restoration by applying filtering, skew and curvature correction as well as removal of any redundant object that does not belong to the document. In the third and final stage, a feature vector is extracted and is compared with the documents of the database.
George Ioannakis, Christodoulos Chamzas, Anestis Koutsoudis, Nikolaos Papamarkos, Ioannis Pratikakis, Fotis Arnaoutoglou, Nikolaos Mitianoudis, and Thomas Sgouros
IEEE
The aim of this research is to achieve spatial consistency of the UV map. We present an approach to produce a fully spatially consistent UV mapping based on the planar parameterisation of the mesh. We apply our method on a 3D digital replica of an ancient Greek Lekythos vessel. We parameterise the mesh of a 3D model onto a unit square 2D plane using computational conformal geometry techniques. The proposed method is genus independent, due to an iterative 3D mesh cutting procedure. Having now the texture of a 3D model depicted on a spatially continuous two dimensional structure enables us to efficiently apply a vast range of image processing based techniques and algorithms.
P. Zafeiridis, , N. Papamarkos, S. Goumas, I. Seimenis, , , and
International Hellenic University
In this work a new image sharpening technique based on multiscale analysis and wavelet fusion is presented. The proposed technique is suitable for visibility optimization of biomedical images obtained from MRI sensors. The proposed approach combines, with a wavelet based fusion algorithm, the sharpening results accrued from a number of independent image sharpening techniques. Initially, the input image is preprocessed by a denoising filter based on a complex Two Dimensional Dual-Tree Discrete Wavelet Transform. Then, the denoised image is passed through a cluster of five sharpening filters and subsequently, the final image is obtained with the help of a wavelet fusion technique. The main novelty of the proposed technique lies on using only one input image for sharpening and that the fusion is performed on images extracted in different frequency bands. This technique could be used as a preprocessing step in many applications. In this paper we focus on the application of the proposed technique in brain MR images. Specific image sharpening and quality indices are employed for the quantitative assessment of the proposed technique.
Nikolaos Mitianoudis and Nikolaos Papamarkos
Elsevier BV
Nikolaos Mitianoudis and Nikolaos Papamarkos
IEEE
Document Image Binarization refers to the task of transforming a scanned image of a handwritten or printed document into a bi-level representation containing only characters and background. Here, we address the historic document image binarization problem using a three-stage methodology. Firstly, we remove possible stains and noise from the document image by estimating the document background image. The remaining background and character pixels are separated using a Local Co-occurrence Mapping, local contrast and a two-state Gaussian Mixture Model. In the last stage, possible isolated misclassified blobs are removed by a morphology operator. The proposed scheme offers robust and fast performance, especially for handwritten documents.
Lazaros Tsochatzidis, Konstantinos Zagoris, Michalis Savelonas, Nikos Papamarkos, Ioannis Pratikakis, Nikolaos Arikidis, and Lena Costaridou
IEEE
Microcalcifications (MCs) provide a significant early indication of breast malignancy. This work introduces a supervised scheme for malignancy risk assessment of mammograms containing MCs. The proposed scheme employs shape and textural features as input to a support vector machine (SVM) ensemble, in order to perform content-based image retrieval (CBIR) of mammograms. The retrieval performance of the proposed scheme has been evaluated by taking into account the variation of MCs morphology as defined in BI-RADS. In our experiments, we use a set of 87 mammograms containing MCs, obtained from the widely adopted DDSM database for screening mammography. The experimental results demonstrate that the proposed supervised CBIR scheme addresses effective retrieval of MCs mammograms outperforming relevant unsupervised schemes.
Kyriakos Sgouropoulos, Ekaterini Stergiopoulou, and Nikos Papamarkos
Springer Science and Business Media LLC
Konstantinos Zagoris, Ioannis Pratikakis, Apostolos Antonacopoulos, Basilis Gatos, and Nikos Papamarkos
Elsevier BV
Nikolaos Mitianoudis and Nikolaos Papamarkos
IEEE
In this paper, the authors exploit a multispectral image representation to perform more accurate document image binarisation compared to previous color representations. In the first stage, image fusion is employed to create a “document” and a “background” image. In the second stage, the FastICA algorithm is used to perform background subtraction. In the third stage, a spatial kernel K-harmonic means classifier binarizes the FastICA output. The proposed system outperforms previous efforts on document image binarization.
Ekaterini Stergiopoulou, Kyriakos Sgouropoulos, Nikos Nikolaou, Nikos Papamarkos, and Nikos Mitianoudis
Elsevier BV
Iliana Papamarkou and Nikos Papamarkos
IEEE
In this paper, a novel method to convert color documents to grayscale is proposed. This approach takes as criteria that a suitable form of a grayscale document must have locally uniform background, well separated characters from the background and reduced noise. The main stages of the proposed technique are color reduction to a limited number of dominant colors and transformation of the gray classes obtained 3-D to a more compact form. The resultant grayscale document gives better OCR results and better compression ratio.
Kilsoo Kim, Young-Ki Lee, Sehwan Oh, David Moroniti, Dimitri Mavris, George J. Vachtsevanos, Nikos Papamarkos, and George Georgoulas
IEEE
This paper introduces a simulation and evaluation of guidance, navigation, and control algorithms applied to an autonomous hovercraft. A line-of-sight guidance law is adopted in conjunction with a neural network based adaptive dynamic inversion control scheme for the underactuated hovercraft following a prescribed path. The simulation result demonstrates that the guidance and control scheme can be effective in waypoint following of the underactuated hovercraft, especially, when external disturbances exist. It is also shown that the error signals are bounded using Lyapunov's direct method.
Dim P. Papadopoulos, Vicky S. Kalogeiton, Savvas A. Chatzichristofis, and Nikos Papamarkos
Elsevier BV
Konstantinos Zagoris, Ioannis Pratikakis, Apostolos Antonacopoulos, Basilis Gatos, and Nikos Papamarkos
IEEE
In a number of types of documents, ranging from forms to archive documents and books with annotations, machine printed and handwritten text may be present in the same document image, giving rise to significant issues within a digitisation and recognition pipeline. It is therefore necessary to separate the two types of text before applying different recognition methodologies to each. In this paper, a new approach is proposed which strives towards identifying and separating handwritten from machine printed text using the Bag of Visual Words paradigm (BoVW). Initially, blocks of interest are detected in the document image. For each block, a descriptor is calculated based on the BoVW. The final characterization of the blocks as Handwritten, Machine Printed or Noise is made by a Support Vector Machine classifier. The promising performance of the proposed approach is shown by using a consistent evaluation methodology which couples meaningful measures along with a new dataset.
Dim P. Papadopoulos, Savvas A. Chatzichristofis, and Nikos Papamarkos
Springer Berlin Heidelberg
Konstantinos Zagoris, Savvas A Chatzichristofis, and Nikos Papamarkos
Springer Science and Business Media LLC
V. Vonikakis, I. Andreadis, and N. Papamarkos
Springer Science and Business Media LLC
Konstantinos Zagoris, Kavallieratou Ergina, and Nikos Papamarkos
Elsevier BV
Michael Makridis, Nikolaos E. Mitrakis, Nikolaos Nikolaou, and Nikolaos Papamarkos
Springer Berlin Heidelberg
Konstantinos Zagoris, Savvas A. Chatzichristofis, Nikos Papamarkos, and Yiannis S. Boutalis
IEEE
Capable tools are needed in order to successfully search and retrieve a suitable image from large image collections. Many content-based image retrieval systems employ low-level image features such as color, texture and shape in order to locate the image. Although the above approaches are successful, they lack the ability to include human perception in the query for retrieval because the query must be an image. In this paper a new image annotation technique and a keyword-based image retrieval system are presented, which map the low-level features of the Joint Composite Descriptor to the high-level features constituted by a set of keywords. One set consists of colors-keywords and the other set consists of words. Experiments were performed to demonstrate the effectiveness of the proposed technique.
Konstantinos Zagoris, Kavallieratou Ergina, and Nikos Papamarkos
Elsevier BV