Lecture

Automatic Vectorization: Principles and Applications

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Description

This lecture introduces automatic vectorization, focusing on the potential and limits of digitizing vector objects from scanned documents or images. It covers general principles, such as automatic detection of structures and polygonization, as well as specific techniques like edge detection and automatic tracing.

In MOOC

Geographical Information Systems 1

In this first part of the course, we will focus on the digitization and the storage of geodata. In particular, you will learn:

To characterize spatial objects and/or phenomena (territory modeling) with respect to their position in space (through coordinate systems, projections, and spatial relationships) and according to their intrinsic nature (object/vector mode vs. Image/raster mode);
About the different means used to acquire spatial data; including direct measurement, georeferencing images, digitiza

Official source

Quiz

Related concepts (32)

Polygon

In geometry, a polygon (ˈpɒlɪɡɒn) is a plane figure made up of line segments connected to form a closed polygonal chain. The segments of a closed polygonal chain are called its edges or sides. The points where two edges meet are the polygon's vertices or corners. An n-gon is a polygon with n sides; for example, a triangle is a 3-gon. A simple polygon is one which does not intersect itself. More precisely, the only allowed intersections among the line segments that make up the polygon are the shared endpoints of consecutive segments in the polygonal chain.

Corner detection

Corner detection is an approach used within computer vision systems to extract certain kinds of features and infer the contents of an image. Corner detection is frequently used in motion detection, , video tracking, image mosaicing, panorama stitching, 3D reconstruction and object recognition. Corner detection overlaps with the topic of interest point detection. A corner can be defined as the intersection of two edges. A corner can also be defined as a point for which there are two dominant and different edge directions in a local neighbourhood of the point.

Regular polygon

In Euclidean geometry, a regular polygon is a polygon that is direct equiangular (all angles are equal in measure) and equilateral (all sides have the same length). Regular polygons may be either convex, star or skew. In the limit, a sequence of regular polygons with an increasing number of sides approximates a circle, if the perimeter or area is fixed, or a regular apeirogon (effectively a straight line), if the edge length is fixed. These properties apply to all regular polygons, whether convex or star.

Star polygon

In geometry, a star polygon is a type of non-convex polygon. Regular star polygons have been studied in depth; while star polygons in general appear not to have been formally defined, certain notable ones can arise through truncation operations on regular simple and star polygons. Branko Grünbaum identified two primary definitions used by Johannes Kepler, one being the regular star polygons with intersecting edges that don't generate new vertices, and the second being simple isotoxal concave polygons.

Edge detection

Edge detection includes a variety of mathematical methods that aim at identifying edges, curves in a at which the image brightness changes sharply or, more formally, has discontinuities. The same problem of finding discontinuities in one-dimensional signals is known as step detection and the problem of finding signal discontinuities over time is known as change detection. Edge detection is a fundamental tool in , machine vision and computer vision, particularly in the areas of feature detection and feature extraction.

Related lectures (64)

Automatic Vectorization MOOC: Geographical Information Systems 1

Covers automatic vectorization in geographic information systems, including structure detection, polygonization, and automatic tracing.

Discrete Variables: Geometric Properties

Covers the geometric properties of discrete variables in geographic information systems, focusing on shape, location, and size indices.

Automatic Vectorization Techniques MOOC: Geographical Information Systems 1

Explores automation techniques for vectorizing objects using polygonization, edge detection, segment detection, and automatic tracing.

Deep Learning: Edge Detection and Neural Networks

Discusses edge detection techniques and the evolution of deep learning in neural networks.

Automatic Vectorization: Summary MOOC: Geographical Information Systems 1