Graphics Recognition Algorithms Research Articles

Creating Accessible Online Floor Plans for Visually Impaired Readers

We present a generic model for providing blind and severely vision-impaired readers with access to online information graphics. The model supports fully and semi-automatic transcription and allows the reader a choice of presentation mediums. We evaluate the model through a case study: online house floor plans. To do so, we conducted a formative user study with severely vision impaired users to determine what information they would like from an online floor plan and how to present the floor plan as a text-only description, tactile graphic, and on a touchscreen with audio feedback. We then built an automatic transcription tool using specialized graphics recognition algorithms. Finally, we measured the quality of system recognition as well as conducted a second user study to evaluate the usefulness of the accessible graphics produced by the tool for each of the three formats. The results generally support the design of the generic model and the usefulness of the tool we have produced. However, they also reveal the inability of current graphics recognition algorithms to handle unforeseen graphical conventions. This highlights the need for automatic transcription systems to return a level of confidence in the recognized components and to present this to the end-user so they can have an appropriate level of trust.

Detecting figures and part labels in patents: competition-based development of graphics recognition algorithms

We report the findings of a month-long online competition in which participants developed algorithms for augmenting the digital version of patent documents published by the United States Patent and Trademark Office (USPTO). The goal was to detect figures and part labels in U.S. patent drawing pages. The challenge drew 232 teams of two, of which 70 teams (30%) submitted solutions. Collectively, teams submitted 1,797 solutions that were compiled on the competition servers. Participants reported spending an average of 63 hours developing their solutions, resulting in a total of 5,591 hours of development time. A manually labeled dataset of 306 patents was used for training, online system tests, and evaluation. The design and performance of the top-5 systems are presented, along with a system developed after the competition which illustrates that winning teams produced near state-of-the-art results under strict time and computation constraints. For the 1st place system, the harmonic mean of recall and precision (f-measure) was 88.57% for figure region detection, 78.81% for figure regions with correctly recognized figure titles, and 70.98% for part label detection and character recognition. Data and software from the competition are available through the online UCI Machine Learning repository to inspire follow-on work by the image processing community.

A complete system for the analysis of architectural drawings

In this paper, we present a complete system for the analysis of architectural drawings, with the aim of reconstructing in 3D the represented buildings. We successively describe the graphics recognition algorithms used for image processing and feature extraction, the 2D modeling step, which includes symbol recognition and converts the drawing into a description in terms of basic architectural entities, and a proposed 3D modeling process which matches reconstructed floors. The system also includes a powerful and flexible user interface.

Object-process based graphics recognition class library: principles and applications

We have developed a Graphics Class Library (GCL) for graphics recognition using the object-process methodology and object-oriented implementation. The purpose of the library is to supply generic code for graphics recognition algorithms to be used as ready made and easily extendible components in future systems. The library consists of reusable classes of graphic objects that appear in engineering drawings as well as in other classes of line drawings. A generic integrated graphics recognition algorithm is at the basis of the library, serving useful standard operations required for graphics recognition applications. Copyright © 1999 John Wiley & Sons, Ltd.

Object‐process based graphics recognition class library: principles and applications

We have developed a Graphics Class Library (GCL) for graphics recognition using the object-process methodology and object-oriented implementation. The purpose of the library is to supply generic code for graphics recognition algorithms to be used as ready made and easily extendible components in future systems. The library consists of reusable classes of graphic objects that appear in engineering drawings as well as in other classes of line drawings. A generic integrated graphics recognition algorithm is at the basis of the library, serving useful standard operations required for graphics recognition applications.