In a society driven by visual information and with the drastic expansion of low-priced cameras, text recognition is nowadays a fast changing field. In particular, natural scene text understanding aiming at extracting text from daily images is the main concern of this text. From text extraction to correction of recognition errors, each sub-step is deeply studied to enhance versatility for handling most images, even the most complex ones. Either in color camera-based images or in low resolution thumbnails, inherent degradations, such as complex backgrounds, artistic fonts, uneven lighting or unsatisfactory resolution, must be taken into account. In order to circumvent or correct them, studies of image formation and degradation sources challengingly led to overcome too constrained definitions of color spaces. Hence the selective metric text extraction attempts to combine magnitude and directional processing of colors in an unsupervised framework. Text extraction from background is simultaneously linked to subsequent steps of character segmentation and recognition. This intermingled chain mainly aims at combining color, intensity and spatial information of pixels for robustness and accuracy. Each of these features addresses different issues; the first one for text extraction and the two latter ones for recovering initial separation between characters through log-Gabor filtering. In order to reach higher quality results, pre- and postprocessing of natural scene text understanding are necessary and deal with Teager-based super-resolution, assuming a simple affine motion between frames with the SURETEXT proposition for the first one and with association of recognition outputs and linguistic information through lightweight finite state machines for the second one. In the final part of each step, results are clearly mentioned to highlight effectiveness of the methods. Moreover, several databases, to be independent of a particular one, and a public and renowned data set, are used to assess results and compare them with recent and competing lgorithms. Finally a large discussion is opened through presented achievements of this text and required future extensions in natural scene text understanding to complete exciting applications, such as reading tool for visually impaired or innovative web images search engines in a life-log context!
Introduction 7
I. Cadre légal de l'étude 11
I.1. Contexte institutionnel et historique du dossier 11
I.2. Processus de révision de plan de secteur et rôle de l’étude d’incidences 14
I.2.1 Révision de plan de secteur : cas particulier de la N54 16
I.2.2 Alternatives de tracé issues de la consultation de la population 17
II. Les matrices origines/destinations comme élément décisionnel du gabarit d’une nouvelle infrastructure 21
II.1. Projet de gabarit en 2002 21
II.2. L’apport des matrices origines/destinations pour valider les options de gabarit 23
II.2.1 Approche méthodologique 23
II.2.2 Données fournies par le MET 24
a. Composantes d’une matrice origines/destinations 24
b. Campagne de comptage de septembre 2002 25
II.2.3 Applicabilité des données fournies 28
II.2.4 Estimation et actualisation de la matrice origines/destinations dans le cadre du choix de gabarit de la N54 29
II.2.5 Trafic capté et gabarit de l’infrastructure projetée 33
II.3. Pertinence de l’utilisation de matrice origines/destinations comme aide à la décision dans le choix du gabarit d’une nouvelle infrastructure routière 38
III. Le paysage comme élément de l’analyse multicritère dans le cadre d’une étude d’incidences 41
III.1. Méthodologie générale de l’analyse multicritère comparative par filtres successifs 41
III.1.1 Premier tri 42
III.1.2. Second tri 52
III.1.3. Evaluation et comparaison environnementale 55
III.2. Méthodologie particulière de l’analyse paysagère 58
III.2.1 Premier tri 59
III.2.2 Second tri 68
III.2.3 Evaluation et comparaison environnementale 79
III.3 Résultats 96
III.3.1. Résultats généraux de l’analyse multicritère 96
Premier tri 96
Second tri 102
Evaluation et comparaison environnementale 104
III.3.2. Résultats de l’analyse paysagère 105
Premier tri 105
Second tri 107
Evaluation et comparaison environnementale 109
III.4. Pertinence de l’utilisation d’une analyse paysagère dans un processus décisionnel de tracé de nouvelle infrastructure routière 111
IV Conclusions et enjeux 113
Bibliographie 117