Search results

21 – 30 of 202
Article
Publication date: 31 July 2020

Zainab Akhtar, Jong Weon Lee, Muhammad Attique Khan, Muhammad Sharif, Sajid Ali Khan and Naveed Riaz

In artificial intelligence, the optical character recognition (OCR) is an active research area based on famous applications such as automation and transformation of printed…

Abstract

Purpose

In artificial intelligence, the optical character recognition (OCR) is an active research area based on famous applications such as automation and transformation of printed documents into machine-readable text document. The major purpose of OCR in academia and banks is to achieve a significant performance to save storage space.

Design/methodology/approach

A novel technique is proposed for automated OCR based on multi-properties features fusion and selection. The features are fused using serially formulation and output passed to partial least square (PLS) based selection method. The selection is done based on the entropy fitness function. The final features are classified by an ensemble classifier.

Findings

The presented method was extensively tested on two datasets such as the authors proposed and Chars74k benchmark and achieved an accuracy of 91.2 and 99.9%. Comparing the results with existing techniques, it is found that the proposed method gives improved performance.

Originality/value

The technique presented in this work will help for license plate recognition and text conversion from a printed document to machine-readable.

Details

Journal of Enterprise Information Management, vol. 36 no. 3
Type: Research Article
ISSN: 1741-0398

Keywords

Article
Publication date: 28 October 2014

Long-Jyi Yeh, Tsung Han Lee and Kuei-Shu Hsu

The purpose of this paper is to use vision stereo to simultaneously acquire image pairs under a normal environment. Then the methods of moving edges detection and moving target…

Abstract

Purpose

The purpose of this paper is to use vision stereo to simultaneously acquire image pairs under a normal environment. Then the methods of moving edges detection and moving target shifting are applied to reduce noise error in order to position a target efficiently. The target is then double confirmed via image merge and alignment. After positioning, the visual difference between the target and the image created by the stereo vision system is measured for alignment. Finally, the image depth of the target is calculated followed by real-time target tracking.

Design/methodology/approach

This study mainly applies Sobel image principle. In addition, moving edges detection and moving target shifting are also used to work with system multi-threading for improving image identification efficiency.

Findings

The results of the experiment suggest that real-time image tracking and positioning under a pre-set environment can be effectively improved. On the other hand, tracking and positioning are slightly affected under a normal environment. Errors of distance measurements occur because there is more noise existing.

Research limitations/implications

This study mainly determines the movements and positioning of an object or a target via image. However, the stability of moving edges detection executed by the stereo vision system can be affected if the light sources in an environment are too strong or extreme.

Practical implications

So far the method of tracking and positioning a moving object has been applied to surveillance systems or the application which requires measuring and positioning under a normal environment. The method proposed by this study can also be used to construct a 3D environment.

Originality/value

The method proposed by this study can also be used to construct a 3D environment or tracking moving object to measure the distance.

Details

Engineering Computations, vol. 31 no. 8
Type: Research Article
ISSN: 0264-4401

Keywords

Article
Publication date: 15 June 2012

Xi‐Zhang Chen, Yu‐Ming Huang and Shan‐ben Chen

Stereo vision technique simulates the function of the human eyes to observe the world, which can be used to compute the spatial information of weld seam in the robot welding…

Abstract

Purpose

Stereo vision technique simulates the function of the human eyes to observe the world, which can be used to compute the spatial information of weld seam in the robot welding field. It is a typical kind of application to fix two cameras on the end effector of robot when stereo vision is used in intelligent robot welding. In order to analyse the effect of vision system configuration on vision computing, an accuracy analysis model of vision computing is constructed, which is a good guide for the construction and application of stereo vision system in welding robot field.

Design/methodology/approach

A typical stereo vision system fixed on welding robot is designed and constructed to compute the position information of spatial seam. A simplified error analysis model of the two arbitrary putting cameras is built to analyze the effect of sensors' structural parameter on vision computing accuracy. The methodology of model analysis and experimental verification are used in the research. And experiments related with image extraction, robot movement accuracy is also designed to analyze the effect of equipment accuracy and related processed procedure in vision technology.

Findings

Effect of repeatability positioning accuracy and TCP calibration error of welding robot for visual computing are also analyzed and tested. The results show that effect of the repeatability on computing accuracy is not bigger than 0.3 mm. However, TCP affected the computing accuracy greatly, when the calibrated error of TCP is bigger than 0.5, the re‐calibration is very necessary. The accuracy analysis and experimental technique in this paper can guide the research of three‐dimensional information computing by stereo vision and improve the computed accuracy.

Originality/value

The accuracy of seam position information is affected by many interactional factors, the systematic experiments and a simplified error analysis model are designed and established, the main factors such as the sensor's configurable parameters, the accuracy of arc welding robot and the accuracy of image recognition, are included in the model and experiments. The model and experimental method are significant for design of visual sensor and improvement of computing accuracy.

Details

Industrial Robot: An International Journal, vol. 39 no. 4
Type: Research Article
ISSN: 0143-991X

Keywords

Article
Publication date: 10 July 2007

Pingyuan Cui and Fuzhan Yue

To provide an autonomous navigation system to endow lunar rovers with increased autonomy both for exploration achievement of scientific goals and for safe navigation.

2631

Abstract

Purpose

To provide an autonomous navigation system to endow lunar rovers with increased autonomy both for exploration achievement of scientific goals and for safe navigation.

Design/methodology/approach

First, algorithm and technique of initial position determination of lunar rovers are introduced. Then, matched‐features set is build by multi steps of image processing such as feature detection, feature tracking and feature matching. Based on the analysis of the image processing error, a two‐stage estimation algorithm is used to estimate the motion, robust linear motion estimation is executed to estimate the motion initially and to reject the outliers, and Levenberg‐Marquardt non‐linear estimation is used to estimate the motion precisely. Next, a weighted ZSSD algorithm is presented to estimate the image disparities by analyzing the traditional ZSSD. Finally, a virtual simulation system is constructed using the development tool of open inventor, this simulation system can provide stereo images for simulations of stereo vision and motion estimation techniques, simulation results are provided and future research work is addressed in the end.

Findings

An autonomous navigation system is build based on stereo vision, the motion estimation algorithm and disparity estimation algorithm are developed.

Research limitations/implications

The field test will be done in the near future to valid the autonomous navigation algorithm presented in this paper.

Practical implications

A very useful source of information for graduate students and technical reference for researchers who work on lunar rovers.

Originality/value

In this paper, stereo vision‐based autonomous navigation techniques for lunar rovers are discussed, and an autonomous navigation scheme which based on stereo vision is presented, and the validity of all the algorithms involved is confirmed by simulations.

Details

Aircraft Engineering and Aerospace Technology, vol. 79 no. 4
Type: Research Article
ISSN: 0002-2667

Keywords

Article
Publication date: 1 February 2005

Binjie XIN and Jinlian HU

Cloth has the nature of three-dimensional, flexible and non-rigid, some traditional methods based on 2D imaging and contact-type 3D surface measurement methods can not work for…

Abstract

Cloth has the nature of three-dimensional, flexible and non-rigid, some traditional methods based on 2D imaging and contact-type 3D surface measurement methods can not work for this kind of material. In this paper we present a study of digitalization of three dimensional cloth appearances based on stereo vision method. The 3D stereo system includes a set of mirror group (3D lens) and a digital camera with high resolution. Based on the camera geometry and stereo matching techniques, the depth map of cloth could be calculated so as to evaluate the 3D appearance of fabrics and related objects. The results show it is effective and workable to use this system to study the cloth/garment's 3D deformation or draping profile.

Details

Research Journal of Textile and Apparel, vol. 9 no. 1
Type: Research Article
ISSN: 1560-6074

Article
Publication date: 23 October 2007

Jie Zhao, Shuchun Yu and Hegao Cai

The paper seeks to develop a stereo vision system based on a new binocular device. It aims to present an explicit‐implicit correction method to correct radial and tangential…

Abstract

Purpose

The paper seeks to develop a stereo vision system based on a new binocular device. It aims to present an explicit‐implicit correction method to correct radial and tangential distortion of image synchronously. It also aims to propose a step‐rotation rectification method to rectify epipolar error between stereo pairs.

Design/methodology/approach

Least squares technique was used in solving the explicit‐implicit correction model. When the step‐rotation rectification method was implemented, the technology of rotating image space was used.

Findings

The paper finds that the stereo vision system based on a new binocular device can be used in different circumstances, and it can obtain more eyeshot of cameras. The explicit‐implicit correction method can eliminate radial and tangential distortion of images, and the solution to this method is so easy that it can be solved by least squares technique. The theory of step‐rotation rectification is simple, and it is effective for rectifying epipolar error.

Practical implications

The explicit‐implicit correction method and step‐rotation rectification method can be used in correcting image distortion and epipolar error in stereo pairs collected by a stereo vision system. The new binocular device can be used in building a stereo vision system.

Originality/value

A new binocular device is developed in the paper. Explicit distortion method and implicit distortion method are united to correct image distortion. A step‐rotation rectification method is proposed to rectify epipolar error.

Details

Industrial Robot: An International Journal, vol. 34 no. 6
Type: Research Article
ISSN: 0143-991X

Keywords

Article
Publication date: 1 September 2005

Matthias Rüther, Mahmood Saleem, Horst Bischof and Gernot Krammer

The goal is to perform an in‐situ measurement of dust layer thickness on bag filters.

Abstract

Purpose

The goal is to perform an in‐situ measurement of dust layer thickness on bag filters.

Design/methodology/approach

Presents a machine vision system in terms of hard‐ and software which is capable of obtaining the relative height difference of a cloth filter surface in different states of operation. The measurement process starts with a stereo reconstruction of filter surface patches. The patches are aligned to form a continuous model using the iterative closest point algorithm. Models acquired at different states of operation are registered using thin plate spline interpolation and afterwards subtracted from each other to obtain the relative height difference.

Findings

Relative thickness measurement is possible with an accuracy ranging from 50 to 300 μm, depending on the operational states.

Research limitations/implications

In‐situ measurement of dust deposition is a new tool for examining the behaviour of commercial bag filters.

Practical implications

Provides the foundation for a system measuring both thickness and density of dust deposition.

Originality/value

Applies findings in the field of machine vision to a problem in process engineering and filter design.

Details

Assembly Automation, vol. 25 no. 3
Type: Research Article
ISSN: 0144-5154

Keywords

Article
Publication date: 30 January 2020

Guoyang Wan, Fudong Li, Wenjun Zhu and Guofeng Wang

The positioning and grasping of large-size objects have always had problems of low positioning accuracy, slow grasping speed and high application cost compared with ordinary small…

Abstract

Purpose

The positioning and grasping of large-size objects have always had problems of low positioning accuracy, slow grasping speed and high application cost compared with ordinary small parts tasks. This paper aims to propose and implement a binocular vision-guided grasping system for large-size object with industrial robot.

Design/methodology/approach

To guide the industrial robot to grasp the object with high position and pose accuracy, this study measures the pose of the object by extracting and reconstructing three non-collinear feature points on it. To improve the precision and the robustness of the pose measuring, a coarse-to-fine positioning strategy is proposed. First, a coarse but stable feature is chosen to locate the object in the image and provide initial regions for the fine features. Second, three circular holes are chosen to be the fine features whose centers are extracted with a robust ellipse fitting strategy and thus determine the precise pose and position of the object.

Findings

Experimental results show that the proposed system has achieved high robustness and high positioning accuracy of −1 mm and pose accuracy of −0.5 degree.

Originality/value

It is a high accuracy method that can be used for industrial robot vision-guided and grasp location.

Details

Sensor Review, vol. 40 no. 1
Type: Research Article
ISSN: 0260-2288

Keywords

Article
Publication date: 1 October 2006

Christine Connolly

To explore the phenomenon of stereoscopic vision and its exploitation in engineering and other professional applications, and in entertainment.

Abstract

Purpose

To explore the phenomenon of stereoscopic vision and its exploitation in engineering and other professional applications, and in entertainment.

Design/methodology/approach

Starts with a review of how stereo vision works, and the techniques used in 3D movies to present the illusion of depth and movement at right angles to the screen. Looks at some engineering products that build on these techniques, and then at the development of 3D television, based on a different image separation method. Finally looks at developments in stereo machine vision.

Findings

A variety of techniques exist to present left and right views of a scene to the correct eyes and stimulate 3D perception: for example, light‐filtering, alternate‐frame sequencing and optical separation. Fatigue occurs when there is crosstalk between those images, or when the images are presented at too low a frame rate. Many computer modelling software providers produce programs with 3D‐viewing capability for professional engineers. There are some exciting recent developments, such as add‐on PC stereo systems, and 3D TV.

Originality/value

Makes the general scientist aware of the wide range of professional uses of stereo vision, and of the engineering challenges behind 3D film and television.

Details

Sensor Review, vol. 26 no. 4
Type: Research Article
ISSN: 0260-2288

Keywords

Article
Publication date: 30 August 2013

Rainhard Dieter Findling and Rene Mayrhofer

Personal mobile devices currently have access to a significant portion of their user's private sensitive data and are increasingly used for processing mobile payments…

Abstract

Purpose

Personal mobile devices currently have access to a significant portion of their user's private sensitive data and are increasingly used for processing mobile payments. Consequently, securing access to these mobile devices is a requirement for securing access to the sensitive data and potentially costly services. The authors propose and evaluate a first version of a pan shot face unlock method: a mobile device unlock mechanism using all information available from a 180° pan shot of the device around the user's head – utilizing biometric face information as well as sensor data of built‐in sensors of the device. The paper aims to discuss these issues.

Design/methodology/approach

This approach uses grayscale 2D images, on which the authors perform frontal and profile face detection. For face recognition, the authors evaluate different support vector machines and neural networks. To reproducibly evaluate this pan shot face unlock toolchain, the authors assembled the 2013 Hagenberg stereo vision pan shot face database, which the authors describe in detail in this article.

Findings

Current results indicate that the approach to face recognition is sufficient for further usage in this research. However, face detection is still error prone for the mobile use case, which consequently decreases the face recognition performance as well.

Originality/value

The contributions of this paper include: introducing pan shot face unlock as an approach to increase security and usability during mobile device authentication; introducing the 2013 Hagenberg stereo vision pan shot face database; evaluating this current pan shot face unlock toolchain using the newly created face database.

Details

International Journal of Pervasive Computing and Communications, vol. 9 no. 3
Type: Research Article
ISSN: 1742-7371

Keywords

21 – 30 of 202