About my PHD (Jul 18, 2007 at 11:21 PM) - Contributed by Romain Raveaux - Last Updated (Dec 09, 2013 at 02:39 PM)
Graph Mining and Graph Classification : Application to cadastral map analysis. This thesis tackles the problem of technical document interpretation applied to ancient and colored cadastral maps. This subject is on the crossroad of different fields like signal or image processing, pattern recognition, artificial intelligence, man-machine interaction and knowledge engineering. Indeed, each of these different fields can contribute to build a reliable and efficient document interpretation device. This thesis points out the necessities and importance of dedicated services oriented to historical documents and a related project named ALPAGE. Subsequently, the main focus of this work: Content-Based Map Retrieval within an ancient collection of color cadastral maps is introduced. The organization of this thesis paper is in five chapters.
My Phd thesis presentation (Video)
PhD defense. The presentation slides (PDF file)
My Phd thesis in short (PDF file)
Draft version of my manuscrit (PDF file)
Abstract: ALPAGE Project
Technical documents have a strategic role in numerous organisations, composing somehow a graphic representation of their heritage. In the context of a project named “ALPAGE―, a closer look is given to ancient French cadastral maps related to the Parisian urban space during the 19th century. Hence, the data collection is made up of 1100 images issued from the digitalization of Atlas books. Each image contains a vast number of domain dependent objects, ie. parcels, water collection points, stairs, windows/doors… From a computer sciences point of view, the challenge consists in the extraction of information from colour images in the objective of providing a vector layer to be inserted in a Geographical Information System (GIS). This raster to vector conversion requires a priori knowledge to control the quality of the vectorization and to adjust algorithm parameters. The constraints given by historians are translated into a computer sciences paradigm called Attributed Relational Graphs (ARG). From a raw colour image segmentation, the system iterates to fit at best a semantic graph. Such a minimization process involves three types of algorithms: a classification stage where image regions are categorized into nominal variables; a graph matching method in order to compare a user-defined model and computer generated graphs; and finally, a relevancy feedback scheme to infer local changes into the segmentation process. Our contribution can be easily identified as a model driven image segmentation.
Alpage Project : http://alpageproject.free.fr http://romain.raveaux.free.fr - The Home of Romain Raveaux
Nov 21, 2010 - The performance evaluation (PE) tool is available and can be downloaded at PE.jar. ... If you cannot run this PE tool, you can send me your ground truth file and detected file and I can run the tool on your ... [PDF Presentation] ... h
Aug 25, 2010 - Next, we focus on coloured cadastral maps and define the scope and objectives of .... nition, pages 1128â-1132, Washington, DC, USA, 2007.
My CV in English - last update 2006 -. - Researcher Form. - - Google Me - http://romain.raveaux.free.fr - The Home of Romain Raveaux. Powered by Mambo.
Problem Encoding. Cross-Over function ... Vectors of prototypes : V = {v1 1, .., vn m} with M prototypes per class et .... A vector V containing M Ã N graphs. 15 / 25 ...
In this paper, we propose and explain the use of anytime algorithms in graph matching (GM). ... conclusion brings into question the usual evidence that claims that it is impossible to ..... sum assignment problem which can be solved in O(n3) where ..
Oct 13, 2016 - Summary: The objective of the Quadratic Assignment Problem. (QAP) is to assign ... The constraints in the above equation require that a vertex.
Page 78. International Master of Research in Computer Science: Computer Aided Decision Support. Integer Linear Programming. Function to minimize. Page 79 ...
Oct 13, 2016 - Communication and Image Representation, Volume 24, Issue. 8, November .... structures, e.g. molecular graphs where the structural formula is.
Implicit graph embedding. Explicit graph embedding. Conclusion .... Let Ï(x) and Ï(y) be two functions projecting x and y into. R m. with n ⤠m k(x,y) = ãÏ(x) ...
Oct 17, 2007 - Graph classification. Application to Symbol Recognition. (Aug 12, 2007 at 10:40 PM) - Contributed by Administrator - Last Updated (Oct 17, ...
Page 2 ... 2.1.4 Attributed Graphs ... Simple Graph A simple graph is a graph that does not contain self-loops or multi-edges. (i.e., two ... for solving an exact GM problem, a yes or no answer is outputted. ..... 2.1.11.8 Modeling Graph Matching by
nitude based on convolutional neural networks. Signal,. Image and Video Processing, 10(4):609â616, 2016. 14. H. Liu, U. Engelke, W. Junle, P. Le Callet, and I.
evaluation â Polygon detection quality â Graphics recog- nition â Machine ... auto-vectorization capability of the products was still re- quired. Responding to this ...
Page 55 .... 5062. | Validation |. 14101. 56. 3200. 1688. Average number of nodes. 12.03. 5.56 ..... Performance evaluation of vectorization and line detection has.
Oct 24, 2009 - method and a distance between attributed graphs are defined. ..... ing graphs require the use of a fast but yet effective graph distance.
Devoted, black and blind. So different since, my love, you lied. I walked the line ... At the right place at the right moment. Whatever they think I'm not a coward.
