DIA Research

horizontal rule

Short CV
DIA Research

Document Image Analysis (DIA) Research:

bulletDocument Image Pre-processing: Adaptive  binarization and enhancement of degraded documents, remove degradations due to shadows, non-uniform illumination, low contrast and smear [,], recovery of arbitrarily warped documents [,], skew correction [,], noisy border removal [].    


Machine-printed OCR: Extracting curvature features from characters [],  binary tree based OCR [], multi-classifier OCR [], Neural Network, SVM  & KNN classifiers for typewritten OCR [], text line position determination [], segmentation, recognition and article tracking for old newspapers [], distinction between handwritten and machine-printed text [], Segmentation of historical machine-printed documents [].


Handwritten OCR: Handwritten character representation, segmentation-free OCR [], feature extraction based on the skeletonized character body, topological description of the character skeleton for old Greek handwritten manuscript recognition [], recognition of isolated Handwritten Greek characters [], cursive handwritten word recognition [], text line detection in handwritten documents [], database of Greek handwritten characters [], handwritten character recognition through two-stage foreground sub-sampling [].



Word spotting: A survey of document image word spotting techniques [], keyword search in historical typewritten documents, word retrieval optimized by user's feedback [],  segmentation-free word spotting [], a word spotting framework for historical machine-printed documents [].



Page Segmentation: Automatic extraction of the main document image components (text, titles, images, captions, graphics, lines, special symbols) [], segmentation area location using isothetic polygons [], newspaper page segmentation into specific items (main titles, head-lines, over-titles, sub-titles, references), article identification and reconstruction [], combining complementary techniques for document image segmentation [].



  1. First International Newspaper Segmentation Contest []

  2. ICDAR 2003 Page Segmentation Competition []

  3. ICDAR2005 Page Segmentation Competition []

  4. ICDAR2007 Page Segmentation Competition []

  5. ICDAR2007 Handwriting Segmentation Contest []

  6. ICDAR2009 Handwriting Segmentation Contest [ ]

  7. ICDAR 2009 Document Image Binarization Contest (DIBCO 2009) [ ]

  8. ICFHR 2010 Handwriting Segmentation Contest []

  9. H-DIBCO 2010 Handwritten Document Image Binarization Competition []

  10. ICDAR 2011 Document Image Binarization Contest (DIBCO 2011) []

  11. ICDAR 2011 Writer Identification Contest []

  12. ICFHR 2012 Competition on Handwritten Document Image Binarization (H-DIBCO 2012) []

  13. ICFHR2012 Competition on Writer Identification - Challenge 1: Latin/Greek Documents []

  14. ICDAR 2013 Competition on Writer Identification Document Analysis and Recognition []

  15. ICDAR 2013 document image binarization contest (DIBCO 2013) []

  16. ICDAR 2013 Document Image Skew Estimation Contest (DISEC 2013) []

  17. ICDAR 2013 Handwriting Segmentation Contest []

  18. ICFHR2014 Competition on Handwritten Document Image Binarization (H-DIBCO 2014) []

  19. ICFHR 2014 Competition on Handwritten KeyWord Spotting (H-KWS 2014) []

  20. ICFHR2016 Handwritten Keyword Spotting Competition (H-KWS 2016) []

  21. ICFHR2016 Handwritten Document Image Binarization Contest (H-DIBCO 2016) []

  22. ICDAR2017 Competition on Document Image Binarization (DIBCO 2017)

  23. cBAD: ICDAR2017 Competition on Baseline Detection

  24. ICDAR2017 Competition on Historical Document Writer Identification (Historical-WI)


Line and Table Detection: Automatic table detection in document images, morphological operations in order to connect line breaks and to enhance line segments, horizontal and vertical line detection, image/text areas removal, detection of line intersections, table reconstruction. []


Camera Based Document Analysis & Recognition: Text detection in indoor/outdoor scene images and video frames, efficient binarization and enhancement of camera images, connected component analysis in order to detect text regions, help camera images to be successfully processed and recognized by commercial OCR engines, text detection in video images. [ ]


Text Identification in Web images: Web image processing for text area identification, prepare Web images for OCR procedure with best results, conditional dilation technique in order to detect text and inverted text areas, process Web images of low resolution, consisting mainly of graphic objects and having the anti-aliasing property.  [ ]

horizontal rule

Home | Short CV | Publications | DIA Research | Projects | Teaching | Links | Demos/Data | News

 Last updated: 15-02-2018.