scholarly journals A Texture-based Method for Document Segmentation and Classification

2007 ◽  
Vol Volume 6, april 2007, joint... ◽  
Author(s):  
Ming-Wei Lin ◽  
Jules-Raymond Tapamo ◽  
Baird Ndovie
Keyword(s):  
Hybrid Approach ◽  
Document Image ◽  
Document Images ◽  
Heuristic Rules ◽  
Base De Données ◽  
Document Database ◽  
Modèle Hybride ◽  
International Audience ◽  
Occurrence Matrix

International audience In this paper we present a hybrid approach to segment and classify contents of document images. A Document Image is segmented into three types of regions: Graphics, Text and Space. The image of a document is subdivided into blocks and for each block five GLCM (Grey Level Co-occurrence Matrix) features are extracted. Based on these features, blocks are then clustered into three groups using K-Means algorithm; connected blocks that belong to the same group are merged. The classification of groups is done using pre-learned heuristic rules. Experiments were conducted on scanned newspapers and images from MediaTeam Document Database Dans cet article nous présentons un modèle hybride de segmentation et classification du contenu d'images de documents. Chaque image est segmentée en trois types de régions: graphiques, textes et espaces. L'image de chaque document est subdivisée en blocs; pour chacun de ces blocs, cinq caractéristiques sont extraites de leur Matrice de Co-occurrence de leur niveaux de gris. Les blocs sont ensuite regroupés en trois classes en utilisant l'algorithme du K-means. Les blocs connectés sont fusionnés pour former un ensemble de régions homogènes. Des règles heuristiques sont ensuite utilisées pour donner un label à chacune des trois classes. Des expérimentations ont été effectuées avec des images scannées de journaux et des images de la base de données documentaire MediaTeam

scholarly journals ROUGH MORPHOLOGY HYBRID APPROACH FOR MAMMOGRAPHY IMAGE CLASSIFICATION AND PREDICTION

2008 ◽  
Vol 07 (01) ◽  
pp. 17-42 ◽  
Author(s):  
ABOUL ELLA HASSANIEN ◽  
AJITH ABRAHAM
Keyword(s):  
Mathematical Morphology ◽  
Rough Sets ◽  
Attribute Reduction ◽  
Hybrid Approach ◽  
Region Of Interest ◽  
Overall Performance ◽  
Mammography Image ◽  
Occurrence Matrix ◽  
Mammogram Images

The objective of this research is to illustrate how rough sets can be successfully integrated with mathematical morphology and provide a more effective hybrid approach to resolve medical imaging problems. Hybridization of rough sets and mathematical morphology techniques has been applied to depict their ability to improve the classification of breast cancer images into two outcomes: malignant and benign cancer. Algorithms based on mathematical morphology are first applied to enhance the contrast of the whole original image; to extract the region of interest (ROI) and to enhance the edges surrounding that region. Then, features are extracted characterizing the underlying texture of the ROI by using the gray-level co-occurrence matrix. The rough set approach to attribute reduction and rule generation is further presented. Finally, rough morphology is designed for discrimination of different ROI to test whether they represent malignant cancer or benign cancer. To evaluate performance of the presented rough morphology approach, we tested different mammogram images. The experimental results illustrate that the overall performance in locating optimal orientation offered by the proposed approach is high compared with other hybrid systems such as rough-neural and rough-fuzzy systems.

scholarly journals An enhanced binarization framework for degraded historical document images

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Wei Xiong ◽  
Lei Zhou ◽  
Ling Yue ◽  
Lirong Li ◽  
Song Wang
Keyword(s):  
Document Image ◽  
Morphological Operations ◽  
Document Images ◽  
Minimum Entropy ◽  
Stroke Width ◽  
Background Estimation ◽  
Structuring Element ◽  
Document Image Binarization ◽  
Benchmark Datasets ◽  
Stroke Width Transform

AbstractBinarization plays an important role in document analysis and recognition (DAR) systems. In this paper, we present our winning algorithm in ICFHR 2018 competition on handwritten document image binarization (H-DIBCO 2018), which is based on background estimation and energy minimization. First, we adopt mathematical morphological operations to estimate and compensate the document background. It uses a disk-shaped structuring element, whose radius is computed by the minimum entropy-based stroke width transform (SWT). Second, we perform Laplacian energy-based segmentation on the compensated document images. Finally, we implement post-processing to preserve text stroke connectivity and eliminate isolated noise. Experimental results indicate that the proposed method outperforms other state-of-the-art techniques on several public available benchmark datasets.

scholarly journals A Phantom Study to Investigate Robustness and Reproducibility of Grey Level Co-Occurrence Matrix (GLCM)-Based Radiomics Features for PET

2021 ◽  
Vol 11 (2) ◽  
pp. 535
Author(s):  
Mahbubunnabi Tamal
Keyword(s):  
Textural Features ◽  
Strongly Correlated ◽  
Segmentation Method ◽  
Diagnosis And Prognosis ◽  
Radiotracer Uptake ◽  
Positron Emission ◽  
Occurrence Matrix ◽  
The Impact ◽  
Robust To Noise

Quantification and classification of heterogeneous radiotracer uptake in Positron Emission Tomography (PET) using textural features (termed as radiomics) and artificial intelligence (AI) has the potential to be used as a biomarker of diagnosis and prognosis. However, textural features have been predicted to be strongly correlated with volume, segmentation and quantization, while the impact of image contrast and noise has not been assessed systematically. Further continuous investigations are required to update the existing standardization initiatives. This study aimed to investigate the relationships between textural features and these factors with 18F filled torso NEMA phantom to yield different contrasts and reconstructed with different durations to represent varying levels of noise. The phantom was also scanned with heterogeneous spherical inserts fabricated with 3D printing technology. All spheres were delineated using: (1) the exact boundaries based on their known diameters; (2) 40% fixed; and (3) adaptive threshold. Six textural features were derived from the gray level co-occurrence matrix (GLCM) using different quantization levels. The results indicate that homogeneity and dissimilarity are the most suitable for measuring PET tumor heterogeneity with quantization 64 provided that the segmentation method is robust to noise and contrast variations. To use these textural features as prognostic biomarkers, changes in textural features between baseline and treatment scans should always be reported along with the changes in volumes.

scholarly journals Finite Eulerian posets which are binomial or Sheffer

2011 ◽  
Vol DMTCS Proceedings vol. AO,... (Proceedings) ◽  
Author(s):  
Hoda Bidkhori
Keyword(s):  
Generating Functions ◽  
Complete Classification ◽  
International Audience ◽  
Original Question ◽  
Eulerian Posets

International audience In this paper we study finite Eulerian posets which are binomial or Sheffer. These important classes of posets are related to the theory of generating functions and to geometry. The results of this paper are organized as follows: (1) We completely determine the structure of Eulerian binomial posets and, as a conclusion, we are able to classify factorial functions of Eulerian binomial posets; (2) We give an almost complete classification of factorial functions of Eulerian Sheffer posets by dividing the original question into several cases; (3) In most cases above, we completely determine the structure of Eulerian Sheffer posets, a result stronger than just classifying factorial functions of these Eulerian Sheffer posets. We also study Eulerian triangular posets. This paper answers questions posed by R. Ehrenborg and M. Readdy. This research is also motivated by the work of R. Stanley about recognizing the \emphboolean lattice by looking at smaller intervals. Nous étudions les ensembles partiellement ordonnés finis (EPO) qui sont soit binomiaux soit de type Sheffer (deux notions reliées aux séries génératrices et à la géométrie). Nos résultats sont les suivants: (1) nous déterminons la structure des EPO Euleriens et binomiaux; nous classifions ainsi les fonctions factorielles de tous ces EPO; (2) nous donnons une classification presque complète des fonctions factorielles des EPO Euleriens de type Sheffer; (3) dans la plupart de ces cas, nous déterminons complètement la structure des EPO Euleriens et Sheffer, ce qui est plus fort que classifier leurs fonctions factorielles. Nous étudions aussi les EPO Euleriens triangulaires. Cet article répond à des questions de R. Ehrenborg and M. Readdy. Il est aussi motivé par le travail de R. Stanley sur la reconnaissance du treillis booléen via l'étude des petits intervalles.

scholarly journals WRITER IDENTIFICATION BY TEXTURE ANALYSIS BASED ON KANNADA HANDWRITING

2012 ◽  
pp. 80-85
Author(s):  
B.V. DHANDRA ◽  
VIJAYALAXMI.M. B ◽  
GURURAJ MUKARAMBI ◽  
MALLIKARJUN. HANGARGE
Keyword(s):  
Texture Analysis ◽  
Identification Problem ◽  
Document Image ◽  
Independent Method ◽  
Gray Level ◽  
Writer Identification ◽  
Texture Image ◽  
Major Research ◽  
Gabor Filtering ◽  
Occurrence Matrix

Writer identification problem is one of the important area of research due to its various applications and is a challenging task. The major research on writer identification is based on handwritten English documents with text independent and dependent. However, there is no significant work on identification of writers based on Kannada document. Hence, in this paper, we propose a text-independent method for off-line writer identification based on Kannada handwritten scripts. By observing each individual’s handwriting as a different texture image, a set of features based on Discrete Cosine Transform, Gabor filtering and gray level co-occurrence matrix, are extracted from preprocessed document image blocks. Experimental results demonstrate that the Gabor energy features are more potential than the DCTs and GLCMs based features for writer identification from 20 people.

scholarly journals Universal geometric coefficients for the four-punctured sphere (Extended Abstract)

2015 ◽  
Vol DMTCS Proceedings, 27th... (Proceedings) ◽  
Author(s):  
Emily Barnard ◽  
Emily Meehan ◽  
Shira Polster ◽  
Nathan Reading
Keyword(s):  
Cluster Algebra ◽  
Short List ◽  
Nous Permet ◽  
Rational Part ◽  
International Audience

International audience We construct universal geometric coefficients for the cluster algebra associated to the four-punctured sphere and obtain, as a by-product, the $g$ -vectors of cluster variables. We also construct the rational part of the mutation fan. These constructions rely on a classification of the allowable curves (the curves which can appear in quasi-laminations). The classification allows us to prove the Null Tangle Property for the four-punctured sphere, thus adding this surface to a short list of surfaces for which this property is known. The Null Tangle Property then implies that the shear coordinates of allowable curves are the universal coefficients. We compute these shear coordinates to obtain universal geometric coefficients. Nous construisons des coefficients géométriques universels pour l’algèbre amassée associée à la sphère privée de 4 points, et obtenons ce faisant les $g$-vecteurs des variables d’amas. Nous construisons aussi la partie rationnelle de l’éventail de mutation. Ces constructions reposent sur la classification des courbes admissibles (les courbes qui peuvent apparaître dans les quasi-laminations). Cette classification nous permet de prouver la “Null Tangle Property” pour la sphère privée de 4 points, ajoutant ainsi cette surface à la courte liste de surfaces pour lesquelles cette propriété est connue. La “Null Tangle Property” implique alors que les coordonnées de décalage des courbes admissibles sont les coefficients universels. Nous calculons ces coordonnées de décalage pour obtenir les coefficients géométriques universels.

Sign in / Sign up

Export Citation Format

Share Document