Papers by Florence Cloppet
2016 International Image Processing, Applications and Systems (IPAS), 2016
This paper focuses on breast masses analysis from two different modalities: Magnetic Resonance Im... more This paper focuses on breast masses analysis from two different modalities: Magnetic Resonance Imaging (MRI) and Dual-Energy Contrast Enhanced Digital Mammography (DECEDM). After the segmentation step, a set of texture and shape features are extracted from both MRI and DECEDM. Then textural and morphological information extracted from the two modalities are combined in order to improve breast cancer detection. Achieved results show that features combination extracted from two different breast images modalities can give a better characterization of breast cancer with a CCR of 96%.
Tables are complex elements that can disturb the automatic analysis of the structure of an image ... more Tables are complex elements that can disturb the automatic analysis of the structure of an image of a document. In this article, we present a method based on the alternation of the color of lines to extract color tables that are not materialized by physical rulings. Experimental results, obtained on a dataset of document images with various layouts, enable to validate the interest of this approach. MOTS-CLES : Analyse d'images de documents, extraction de tableaux, detection de couleurs dominantes, segmentation d'images, croissance de regions.
2008 19th International Conference on Pattern Recognition, 2008
This paper presents a fast method using simple genetic algorithms (GAs) for features selection. U... more This paper presents a fast method using simple genetic algorithms (GAs) for features selection. Unlike traditional approaches using GAs, we have used the combination of Adaboost classifiers to evaluate an individual of the population. So, the fitness function we have used is defined by the error rate of this combination. This approach has been implemented and tested on the MNIST database and the results confirm the effectiveness and the robustness of the proposed approach.
Proceedings of the 14th …, 2009
Abstract. This paper presents an effective system for the classification of ancient handwritten d... more Abstract. This paper presents an effective system for the classification of ancient handwritten documents according to the writing style. We have employed a set of features that are extracted from the contours of the handwritten images. These features are based on the ...
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
One of the major goals of Computer vislon is the research and the development of flexible methods... more One of the major goals of Computer vislon is the research and the development of flexible methods for shape description. A large group of shape description techniques is given by heuristic approaches. which yield acceptable resulls in the ciescrlptlon of slmple shapes and regions. In this case, objects are ropresontod by a planar graph with nodes SymbDlizlng subreglons from reQion decomposition, and region shape is then described by Ihe graph properties. In this paper, the Angular Bisector Network (ABN), a descriptor of polygonal shape, Is used to automatically detect intersections between neuritss of col1 structures. Somo properties of the ABN, such as llnear algebraic complexity, easy extraction of characteristic points, etc., are very useful and experimental results are promising.
Extraction et Gestion des Connaissances, 2012
Turkish Journal of Electrical Engineering and Computer Sciences, 1998
This study is concerned with the segmentation of cytological images and extraction of cellular en... more This study is concerned with the segmentation of cytological images and extraction of cellular entities in order to provide quantitative data about the number of cells in culture (statistical tests, morphology, model of evolution, etc). This quantitative supply is useful in biology to evaluate the consequences of the application of active substances on morphological changes and cellular viability. It is related to the conception of a system dedicated to automatic analysis of cell images, in order to evaluate the eects of drugs on the morphology of neuronal cells. We use a cooperative region/contour segmentation, which gives closed polygonal contours. As the neurites can cross over, the obtained closed polygonal contours can contain several cells. In order to extract each cell contour, a method of entity extraction has been developed. It is based on a vectorial shape descriptor: the bisector network, which is a simplied generalized Vorono diagram.
RÉSUMÉ. Le but de cet article est de proposer une méthode pour la séparation entre manuscrit et i... more RÉSUMÉ. Le but de cet article est de proposer une méthode pour la séparation entre manuscrit et imprimé dans des documents. La méthode proposée repose sur des descripteurs originaux appartenant à deux catégories différentes, la linéarité et la régularité, invariants à la translation et à l’échelle. Plus précisément, nous dérivons une mesure de linéarité à partir de l’histogramme des longueurs des segments. Le cadre résultant est indépendant de la forme du document et du type de langage latin utilisé, et fournit une approche numériquement efficace. Ses performances, évaluées sur des documents réels, atteignent un taux de reconnaissance qui dépasse 90%.
Tables are one of the best ways to synthesize information such as statistical results, key figure... more Tables are one of the best ways to synthesize information such as statistical results, key figures in documents. In this article we focus on the extraction of materialized tables in document images, in the particular case where acquisition noise can disrupt the recovering of the table structures. The sequential printings/scannings of a document and its deterioration can lead to “broken” lines among the materialized segments of the tables. We propose a method based on the search for straight line segments in documents, relying on a new image transform that locally defines primitives well suited for pattern recognition and on a proposed theoretical model of lines in order to confirm their presence among a set of confident potential line parts. The extracted straight line segments are then used to reconstruct the table structures. Our approach has been evaluated both from quality and stability points of view.
The handwritten/printed text discrimination problem is a decision problem usually solved after a ... more The handwritten/printed text discrimination problem is a decision problem usually solved after a binarization of grey level or color images. The decision is usually made at the connected component level of a filtered image. These image components are labeled as printed or handwritten. Each component is represented as a point in a n dimensional space based on the use of n different features. In this paper we present the transformation of a (state of the art) traditional system dealing with the handwritten/printed text discrimination problem to an agent-based system. In this system we associate two different agents with the two different points of view (i.e. linearity and regularity) considered in the baseline system for discriminating a text, based on four (two for each agent) different features. We are also using argumentation for modeling the decision making mechanisms of the agents. We then present experimental results that compare the two systems by using images of the IAM handwr...
Tenth International Conference on Machine Vision (ICMV 2017)
2007 Conference Record of the Forty-First Asilomar Conference on Signals, Systems and Computers, 2007
We present a method for detecting linear structures in biological microscopy images. The contribu... more We present a method for detecting linear structures in biological microscopy images. The contribution of this paper is to unify the Beamlet transform with linear filtering techniques and propose a new detector, the feature-adpated beamlet transform. Our detector is able to incorporate knowledge about the desired line-profile lying along curves, like edges or ridges. We propose an efficient implementation in
2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)
Document layout extraction is a difficult step in the image interpretation process due to the hig... more Document layout extraction is a difficult step in the image interpretation process due to the high complexity of documents. The main challenge relies on the huge gap between both the physical and the logical structures of document images. In order to loose as few as possible information, most existing methods are working at pixel level. In this paper, we present a new framework for complex layout extraction based on features of high levels obtained from a document straight line based segmentation. We propose to capture the straight line segments thanks to a new transform integrating the local spatial organization of the segments contained in the document content. Such transform can be applied either on the foreground (related to the document content) or the background pixels, in order to take advantage of the duality of information present in both document parts. Experimental results obtained on the PRImA Layout Analysis dataset illustrate the robustness of our framework for the extraction of specific components of the document including text areas, images and separators.
Big Data and Cognitive Computing
In this work, we build a computer aided diagnosis (CAD) system of breast cancer for high risk pat... more In this work, we build a computer aided diagnosis (CAD) system of breast cancer for high risk patients considering the breast imaging reporting and data system (BIRADS), mapping main expert concepts and rules. Therefore, a bag of words is built based on the ontology of breast cancer analysis. For a more reliable characterization of the lesion, a feature selection based on Choquet integral is applied aiming at discarding the irrelevant descriptors. Then, a set of well-known machine learning tools are used for semantic annotation to fill the gap between low level knowledge and expert concepts involved in the BIRADS classification. Indeed, expert rules are implicitly modeled using a set of classifiers for severity diagnosis. As a result, the feature selection gives a a better assessment of the lesion and the semantic analysis context offers an attractive frame to include external factors and meta-knowledge, as well as exploiting more than one modality. Accordingly, our CAD system is in...
Pattern Recognition Letters
Cloppet, Florence, Véronique Eglin, Marlène Helias-Baron, Van Cuong Kieu, Dominique Stutzmann, et... more Cloppet, Florence, Véronique Eglin, Marlène Helias-Baron, Van Cuong Kieu, Dominique Stutzmann, et Nicole Vincent. « ICDAR 2017 Competition on the Classification of Medieval Handwritings in Latin Script ». In 14th IAPR International Conference on Document Analysis and Recognition. ICDAR 2017, 1371‑76. Kyoto: CPS, 2017. https://doi.org/DOI 10.1109/ICDAR.2017.224.
2016 23rd International Conference on Pattern Recognition (ICPR), 2016
Uploads
Papers by Florence Cloppet