Search results

This paper aims to introduce an unsupervised modular approach for eye centre localisation in images and videos following a coarse-to-fine, global-to-regional scheme. The design of the algorithm aims at excellent accuracy, robustness and real-time performance for use in real-world applications.

A modular approach has been designed that makes use of isophote and gradient features to estimate eye centre locations. This approach embraces two main modalities that progressively reduce global facial features to local levels for more precise inspections. A novel selective oriented gradient (SOG) filter has been specifically designed to remove strong gradients from eyebrows, eye corners and self-shadows, which sabotage most eye centre localisation methods. The proposed algorithm, tested on the BioID database, has shown superior accuracy.

The eye centre localisation algorithm has been compared with 11 other methods on the BioID database and six other methods on the GI4E database. The proposed algorithm has outperformed all the other algorithms in comparison in terms of localisation accuracy while exhibiting excellent real-time performance. This method is also inherently robust against head poses, partial eye occlusions and shadows.

The eye centre localisation method uses two mutually complementary modalities as a novel, fast, accurate and robust approach. In addition, other than assisting eye centre localisation, the SOG filter is able to resolve general tasks regarding the detection of curved shapes. From an applied point of view, the proposed method has great potentials in benefiting a wide range of real-world human-computer interaction (HCI) applications.

The purpose of this study is to design a robotic inline measurement system for spot welding quality control to achieve process requirement without any operator during the manufacturing flow.

A robot manipulator carries a stereo-camera and an ultrasonic control probe. The center position of the spot welding point is determined by evaluating the results of the edge, gradient and symmetry approaches from the methods proposed up to now in the literature to increase reliability. The center position of the spot welding point, determined in the camera reference plane, is transferred to the robot base plane coordinates with the hand–eye calibration proposed in this manuscript. Weld quality is checked by the ultrasonic test probe located at the spot welding point.

While operators can only control welding quality, the developed station can also evaluate the quality based on geometric accuracy by processing the deviation of the position of the spot welding points. The proposed calibration method and the results of other methods in the literature are presented in this study by comparing it with synthetic data in simulations and in practical application.

The quality control is performed not only for the spot welding made with robots but also for the manual welds as well. Because of vision configuration, and reliability issues, maximum allowable offset by the correct spot position is limited to 20 mm to position the manipulator for testing. The installation and pretest works of the developed robotic welding quality control station are completed in the Body Shop Area of Ford Otosan factory in Kocaeli/Turkey. The results of the robotic control process are monitored by the quality assurance team. Integration of automation with the production line will be completed and an inline measurement will be done.

In this paper, a new hand–eye calibration method based on simple and closed-form analytical solutions has been presented. The objective function is defined as reducing the deviation in the point projection, rather than reducing the error in the calibration equation. To increase reliability, combining the results of existing centering algorithms for the detection of the strongly deformed spot welding spot center, although it is normally in a circular form, has been suggested.

This paper primarily aims to focus on a review of convolutional neural network (CNN)-based eye control systems. The performance of CNNs in big data has led to the development of eye control systems. Therefore, a review of eye control systems based on CNNs is helpful for future research.

In this paper, first, it covers the fundamentals of the eye control system as well as the fundamentals of CNNs. Second, the standard CNN model and the target detection model are summarized. The eye control system’s CNN gaze estimation approach and model are next described and summarized. Finally, the progress of the gaze estimation of the eye control system is discussed and anticipated.

The eye control system accomplishes the control effect using gaze estimation technology, which focuses on the features and information of the eyeball, eye movement and gaze, among other things. The traditional eye control system adopts pupil monitoring, pupil positioning, Hough algorithm and other methods. This study will focus on a CNN-based eye control system. First of all, the authors present the CNN model, which is effective in image identification, target detection and tracking. Furthermore, the CNN-based eye control system is separated into three categories: semantic information, monocular/binocular and full-face. Finally, three challenges linked to the development of an eye control system based on a CNN are discussed, along with possible solutions.

This research can provide theoretical and engineering basis for the eye control system platform. In addition, it also summarizes the ideas of predecessors to support the development of future research.

Free Open Source Softwares (FOSS) witnessed the development of many very good alternatives to proprietary softwares. These free softwares can be localized in several local languages. This paper aims to illustrate a very interesting empirical investigation on FOSS. Several significant benefits of localization are described in introduction and subsequent sections.

Although the localization process is standard and well documented for most of the FOSS, it is a more complex task as it involves coordination among developers, linguists and domain experts. Hence, a very few open source softwares are successfully localized in Indian languages. In this paper, the authors present an approach that they have used for GIMP (GNU Image Manipulation Program) software Marathikaran (localization in Marathi language) project of by Rajya Marathi Vikas Sanstha of Maharashtra Government (RMVS), India.

This localization project has been described by RMVS as a pilot project that would guide such similar localizations in many other Indian languages for other popular open source softwares.

The localization work overcomes the general misconception that regional languages are good only for communication (Boli Bhasha) but cannot be used for dissemination of knowledge (Gyan Bhasha). This work is notably contributing to language preservation, language revitalization and Digital India Initiative.

This work is the pioneering work in this domain for Marathi language with respect to GIMP. The authors presented systematic steps used to localize the GIMP software in Marathi language (from 2% to 100%).

Globalisation as a competitive marketing strategy can only offer a limited explanation for the behaviour of organisations. This is particularly applicable in the case of business and marketing strategies for small and medium‐sized organisations in the retail sector. Terms such as “localisation” have been coined by researchers but the concept is yet to receive a valid interpretation as a marketing strategy from the perspective of the small retailer. This paper seeks first, to understand how “localisation” impacts on the business practices and marketing strategy of small retailers in Spain and Scotland. Second, the results should help lessen the gap between the concepts of globalisation and the localisation.

This explorative, comparative qualitative paper explores business practices and marketing strategies by small retail business owners in Seville (Spain) and Perth (UK) and the role of localisation, using three key themes – place, people and promotion.

This paper suggests that place attractiveness, word‐of‐mouth customer‐to‐customer marketing, customer service beyond simple product advice, community embeddedness and informal but meaningful interpersonal relations between shop owner and customers are some of the key pillars of the “localisation” strategic marketing approach pursued by small retailers in Perth and Seville. This indicates a counterbalance to globalisation.

The pursuit of a deliberate localisation approach by small retailers may be key to their sustainable competitiveness in the knowledge that these elements would not be easily replicated by larger or global retailers.

To solve problems of low intelligence and poor robustness of traditional navigation systems, the purpose of this paper is to propose a brain-inspired localization method of the unmanned aerial vehicle (UAV).

First, the yaw angle of the UAV is obtained by modeling head direction cells with one-dimension continuous attractor neural network (1 D-CANN) and then inputs into 3D grid cells. After that, the motion information of the UAV is encoded as the firing of 3 D grid cells using 3 D-CANN. Finally, the current position of the UAV can be decoded from the neuron firing through the period-adic method.

Simulation results suggest that continuous yaw and position information can be generated from the conjunctive model of head direction cells and grid cells.

The proposed period-adic cell decoding method can provide a UAV with the 3 D position, which is more intelligent and robust than traditional navigation methods.

The purpose of this paper is to discuss the integration of information technology (IT) systems and the strengthening of customer service to raise business competitive advantage.

The case company uses IT systems to integrate customers and suppliers. In this paper, both are interviewed about how they work together for the development and operation of IT systems. A grounded theory approach is followed to develop the theoretical framework from the empirical evidence.

This research regards the whole machine industry as having the following influence, beginning with the related innovation business model. Previously, most machine tool companies played the role of product manufacturer, making high‐quality products the goal. This research indicated that not only can Taiwan manufacture high‐quality products but also that it can create product design and support a global localization service to the world.

In this paper, information architecture planning is designed to strengthen the bonds between the clients and the company.

This paper may help global companies concerned with the development, support, and operation of IT systems to look beyond the systems of their collaborative working to consider the effect of supporting a localization service in their systems.

Successful localization policies are critical to the resolution of difficult social problems in the Gulf States relating to rising populations and youth unemployment. Successful localization is proving difficult, however, and this paper aims to look specifically at Omanization in an effort to contribute to a better understanding of a complex socio‐economic arena.

The paper is based on 25 interviews with Ministerial officials and senior private sector managers with human resource management responsibilities in Oman. Interviews were open‐coded to allow factors specific to Oman to emerge from the data.

Key findings are that the perceptions of the employability of locals remains a difficult supply side problem and employers' preferences for foreign labour remains a difficult demand side problem.

The paper is strengthened by the involvement of senior managers yet it is difficult to separate stereotypes of local labour from stereotypes of foreign workers.

The insights reported in the paper identify key areas for further development of localization policy.

The paper provides a new perspective on the difficulties of localization in the Gulf States.

The study aims to examine the effect of inclusions and inherent microstructure on fatigue behavior of 34Cr2Ni2Mo steel.

Fatigue behavior of 34Cr2Ni2Mo steel was investigated for up to 1E10 cycles.

Results showed that both inclusion and inherent microstructure have an influence on the crack initiation mechanism. Fatigue cracks mostly initiated from inclusions, whereas substrate-induced crack initiations were also observed. Fatigue life of inclusion-induced failures is mostly determined by the location of inclusions rather than the loading stress. The inherent microstructure seems to tolerate inclusions at a lower stress level in very high-cycle regime owing to the absence of internal inclusion-induced failure. For the substrate-induced crack initiations, high-density dislocations are found to be accumulated around the carbide particle-matrix interface, which may be the cause of crack initiation in the inherent structure due to strain localization.

The effect of inclusions and inherent microstructure on fatigue behavior of 34Cr2Ni2Mo steel up to 1E10 cycles.

Highlights

• Fatigue failure occurs even at a lifetime of 5.76E9 cycles.

• Surface inclusion induced premature failures.

• Inherent microstructure tolerates inclusions at lower stress level.

• Internal carbides promote substrate-induced crack initiations.

Fatigue failure occurs even at a lifetime of 5.76E9 cycles.

Surface inclusion induced premature failures.

Inherent microstructure tolerates inclusions at lower stress level.

Internal carbides promote substrate-induced crack initiations.

To improve the operational efficiency and intelligence of live operation robots in dynamic-unstructured operation environments, this paper aims to propose a fuzzy logic-based method for the autonomous search and visual localization control of a manipulator end effector applied to a drainage plate bolt on a high-voltage transmission line. The proposed approach is based on a four-way video image information output from a dual-operation manipulator.

First, based on the structural characteristics of the drainage line, an autonomous search method for the drainage plate bolt and a mapping relationship between the autonomous search control parameters and the relative posture of the operation manipulator-drainage line are proposed. The posture control parameters of the dual manipulators can then be obtained, and a two-dimensional fuzzy controller is designed with the posture offset distance and the posture offset angle as its input signals. This enables the localization control of the bolt and nut alignment to be realized through a visual process.

The proposed fuzzy control algorithm is used for bolt location control, and its performance is compared with that of the conventional approach. The simulation results indicate that the fuzzy control algorithm greatly improves the localization accuracy and operational efficiency of live operation robots.

Field operation experiments on actual transmission lines verify that the fuzzy control-based visual localization control of the robot manipulator has great engineering practicality. Therefore, the proposed method further improves operational intelligence compared with conventional algorithms.