J. R. Caldas Pinto

Camera configurations of a visual servoing setup, for a 2 dof planar robot

Abstract This paper presents a study of three different camera configurations, for a 2 dof planar robot, comparing their behavior based on the singularities of the jacobian used in the control law. The camera configurations used were: eye-to-hand; eye-in-hand with the camera looking respectively in front and down. Two image features, coordinates of a point, from the target were used. Plots representing jacobian singularities, within the joint limits, are presented for a known target position. Some conclusions are also drawn when the target position is unknown. Simulation results for 20 Visual Servoing are presented, to show the behavior of the servoing in the three camera configurations.

Restoration of double-sided ancient music documents with bleed-through

Access to collections of cultural heritage is increasingly becoming a topic of interest for institutions like libraries. With the easy access to information provided by technologies such as the Internet, new ways exist for consulting ancient documents without exposing them to more dangers of degradation. One of those types of documents is written ancient music. These documents suffer from multiple kinds of degradation, where bleed-through outstands as the most damaging. This paper proposes a new method based on the Takagi Sugeno fuzzy classification algorithm to classify the pixels as bleed-through, after performing a general background restoration. This method is applied to a set of double-sided ancient music documents, and the obtained results compared with methods present in the literature.

Dynamic visual servoing of robotic manipulators

This paper proposes a new controller for dynamic visual servoing of robotic manipulators. In this work the image is acquired from a CCD camera mounted on planar robotic manipulator end-effector, and processed in a standard PC based vision system in order to close the visual servoing loop with PD controllers. First, we propose an extension to dynamic visual servoing based on a pose estimation algorithm and then compare it with another Lyapunov stable controller. The proposed dynamic controller uses only information from the image and robot encoders. This approach is inspired on classical 3D visual servoing and the Jacobian transpose controller approach. An experimental setup developed for visual servoing experiments, including software and hardware is presented. Experimental results for a planar robotic manipulator are presented.This paper proposes a new controller for dynamic visual servoing of robotic manipulators. In this work the image is acquired from a CCD camera mounted on planar robotic manipulator end-effector, and processed in a standard PC based vision system in order to close the visual servoing loop with PD controllers. First, we propose an extension to dynamic visual servoing based on a pose estimation algorithm and then compare it with another Lyapunov stable controller. The proposed dynamic controller uses only information from the image and robot encoders. This approach is inspired on classical 3D visual servoing and the Jacobian transpose controller approach. An experimental setup developed for visual servoing experiments, including software and hardware is presented. Experimental results for a planar robotic manipulator are presented.

Uncalibrated visual servoing in 3d workspace

In this paper, inverse fuzzy models for uncalibrated visual servoing, in 3D Workspace, are developed and validated in a six degrees of freedom robotic manipulator. This approach does not require calibrated kinematic and camera models, as needed in classical visual servoing to obtain the Jacobian. Fuzzy modeling is used to identify the inverse Jacobian in the robot workspace. Robot control is achieved by means of using the inverse fuzzy models directly as the controller. Experimental results obtained in a PUMA robot performing eye-to-hand visual servoing demonstrate the validity of the approach.

Old document recognition using fuzzy methods

This paper proposes an expert system based on fuzzy logic for optical character recognition of old printed documents. These documents can have some problems, such as distortion, poor printing quality, faded and misprinted characters, speckles and smudges. The recognition process consists of two stages: training with character image examples and classification of new character images. The proposed OCR builds fuzzy membership functions from oriented features extracted using Gabor filter banks. The proposed methodology is tested on three different books from the 17th century, written in Portuguese. The fuzzy recogniser presents a very high character recognition success rate, which confirms the advantage of using expert systems in image based decision systems.

Automatic Feature Extraction and Recognition for Digital Access of Books of the Renaissance

Antique printed books constitute a heritage that should be preserved and used. With novel digitising techniques is now possible to have these books stored in digital format and accessible to a wider public. However it remains the problem of how to use them. DEBORA (Digital accEss to BOoks of the RenAissance) is a European project that aims to develop a system to interact with these books through world-wide networks. The main issue is to build a database accessible through client computers. That will require to built accompanying metadata that should characterise different components of the books as illuminated letters, banners, figures and key words in order to simplify and speed up the remote access. To solve these problems, digital image analysis algorithms regarding filtering, segmentation, separation of text from non-text, lines and word segmentation and word recognition were developed. Some novel ideas are presented and illustrated through examples.

Methods for written ancient music restoration

Degradation in old documents has been a matter of concern for a long time. With the easy access to information provided by technologies such as the Internet, new ways have arisen for consulting those documents without exposing them to yet more dangers of degradation. While restoration methods are present in the literature in relation to text documents and artworks, little attention has been given to the restoration of ancient music. This paper describes and compares different methods to restore images of ancient music documents degraded over time. Six different methods were tested, including global and adaptive thresholding, color clustering and edge detection. In this paper we conclude that those based on the Sauvolas thresholding algorithm are the better suited for our proposed goal of ancient music restoration.

New Distance Measures Applied to Marble Classification

Automatic marble classification based on their visual appearance is an important industrial issue, but due to the presence of randomly distributed high number of different colors and its subjective evaluation by human experts, the problem remains unsolved. In this paper, several new measures based on similarity tables built by human experts are introduced. They are used to improve the behavior of some clustering algorithms and to quantitatively characterize the results, increasing the correspondence of the measures to the visual appearance of the results. The obtained results show the effectiveness of the proposed methods.

Virtual and Remote Laboratories for Industrial Automation E-Learning

Abstract Nowadays one of the fundamental aspects of industrial automation concerns modeling discrete manufacturing processes and their control through Programmable Logic Controllers (PLC). These subjects, apparently distinct, are indeed related because PLC programming in most cases are based on these models. Another essential topic is the use of SCADA systems and web panels as part of the monitoring process. Teaching these subjects require intensive use of laboratories with dedicated equipment and software. The problem arises when the course has more than one hundred students and the university policy is not to spend too many resources in teaching labs. This paper presents our last solution to the problem based on virtual experimental setups and the use of a remote laboratory with web panels and LabVIEW interfaces. The solution has been tested successfully and very important, using legal software at free cost for the student.

Image Recognition Applied to Robot Control Using Fuzzy Modeling

A new approach to eye-in-hand image-based visual servoing based on fuzzy modeling and control is proposed in this paper. Fuzzy modeling is applied to obtain an inverse model of the mapping between image features errors and joints velocities, avoiding the necessity of inverting the Jacobian. An inverse model is identified for each trajectory using measurements data of a robotic manipulator, and it is directly used as a controller. The control scheme contains an inverse fuzzy model, which is applied to a robotic manipulator performing visual servoing, for a given profile of image features errors. The obtained experimental results show the effectiveness of the proposed control scheme: the fuzzy controller can follow a point-to-point pre-defined trajectory faster (or smoother) than the classic approach.