Search results

Palmprint recognition is a very interesting and promising area of research. Much work has already been done in this area, but much more needs to be done to make the systems more efficient. In this paper, a multimodal biometrics system based on fusion of left and right palmprints of a person is proposed to overcome limitations of unimodal systems.

Features are extracted using some proposed multi-block local descriptors in addition to MBLBP. Fusion of extracted features is done at feature level by a simple concatenation of feature vectors. Then, feature selection is performed on the resulting global feature vector using evolutionary algorithms such as genetic algorithms and backtracking search algorithm for a comparison purpose. The benefits of such step selecting the relevant features are known in the literature, such as increasing the recognition accuracy and reducing the feature set size, which results in runtime saving. In matching step, Chi-square similarity measure is used.

The resulting feature vector length representing a person is compact and the runtime is reduced.

Intensive experiments were done on the publicly available IITD database. Experimental results show a recognition accuracy of 99.17 which prove the effectiveness and robustness of the proposed multimodal biometrics system than other unimodal and multimodal biometrics systems.

An accurate detection of overhead ground wire under open surroundings with varying illumination is the premise of reliable line grasping with the off-line arm when the inspection robot cross obstacle automatically. This paper aims to propose an improved approach which is called adaptive homomorphic filter and supervised learning (AHSL) for overhead ground wire detection.

First, to decrease the influence of the varying illumination caused by the open work environment of the inspection robot, the adaptive homomorphic filter is introduced to compensation the changing illumination. Second, to represent ground wire more effectively and to extract more powerful and discriminative information for building a binary classifier, the global and local features fusion method followed by supervised learning method support vector machine is proposed.

Experiment results on two self-built testing data sets A and B which contain relative older ground wires and relative newer ground wire and on the field ground wires show that the use of the adaptive homomorphic filter and global and local feature fusion method can improve the detection accuracy of the ground wire effectively. The result of the proposed method lays a solid foundation for inspection robot grasping the ground wire by visual servo.

This method AHSL has achieved 80.8 per cent detection accuracy on data set A which contains relative older ground wires and 85.3 per cent detection accuracy on data set B which contains relative newer ground wires, and the field experiment shows that the robot can detect the ground wire accurately. The performance achieved by proposed method is the state of the art under open environment with varying illumination.

The purpose of this study is to solve the problem of an unknown initial position in a multi-robot raster map fusion. The method includes two-dimensional (2D) raster maps and three-dimensional (3D) point cloud maps.

A fusion method using multiple algorithms was proposed. For 2D raster maps, this method uses accelerated robust feature detection to extract feature points of multi-raster maps, and then feature points are matched using a two-step algorithm of minimum Euclidean distance and adjacent feature relation. Finally, the random sample consensus algorithm was used for redundant feature fusion. On the basis of 2D raster map fusion, the method of coordinate alignment is used for 3D point cloud map fusion.

To verify the effectiveness of the algorithm, the segmentation mapping method (2D raster map) and the actual robot mapping method (2D raster map and 3D point cloud map) were used for experimental verification. The experiments demonstrated the stability and reliability of the proposed algorithm.

This algorithm uses a new visual method with coordinate alignment to process the raster map, which can effectively solve the problem of the demand for the initial relative position of robots in traditional methods and be more adaptable to the fusion of 3D maps. In addition, the original data of the map can come from different types of robots, which greatly improves the universality of the algorithm.

Although numerous signal modalities are available for emotion recognition, audio and visual modalities are the most common and predominant forms for human beings to express their emotional states in daily communication. Therefore, how to achieve automatic and accurate audiovisual emotion recognition is significantly important for developing engaging and empathetic human–computer interaction environment. However, two major challenges exist in the field of audiovisual emotion recognition: (1) how to effectively capture representations of each single modality and eliminate redundant features and (2) how to efficiently integrate information from these two modalities to generate discriminative representations.

A novel key-frame extraction-based attention fusion network (KE-AFN) is proposed for audiovisual emotion recognition. KE-AFN attempts to integrate key-frame extraction with multimodal interaction and fusion to enhance audiovisual representations and reduce redundant computation, filling the research gaps of existing approaches. Specifically, the local maximum–based content analysis is designed to extract key-frames from videos for the purpose of eliminating data redundancy. Two modules, including “Multi-head Attention-based Intra-modality Interaction Module” and “Multi-head Attention-based Cross-modality Interaction Module”, are proposed to mine and capture intra- and cross-modality interactions for further reducing data redundancy and producing more powerful multimodal representations.

Extensive experiments on two benchmark datasets (i.e. RAVDESS and CMU-MOSEI) demonstrate the effectiveness and rationality of KE-AFN. Specifically, (1) KE-AFN is superior to state-of-the-art baselines for audiovisual emotion recognition. (2) Exploring the supplementary and complementary information of different modalities can provide more emotional clues for better emotion recognition. (3) The proposed key-frame extraction strategy can enhance the performance by more than 2.79 per cent on accuracy. (4) Both exploring intra- and cross-modality interactions and employing attention-based audiovisual fusion can lead to better prediction performance.

The proposed KE-AFN can support the development of engaging and empathetic human–computer interaction environment.

Current practices in data classification and retrieval have experienced a surge in the use of multimedia content. Identification of desired information from the huge image databases has been facing increased complexities for designing an efficient feature extraction process. Conventional approaches of image classification with text-based image annotation have faced assorted limitations due to erroneous interpretation of vocabulary and huge time consumption involved due to manual annotation. Content-based image recognition has emerged as an alternative to combat the aforesaid limitations. However, exploring rich feature content in an image with a single technique has lesser probability of extract meaningful signatures compared to multi-technique feature extraction. Therefore, the purpose of this paper is to explore the possibilities of enhanced content-based image recognition by fusion of classification decision obtained using diverse feature extraction techniques.

Three novel techniques of feature extraction have been introduced in this paper and have been tested with four different classifiers individually. The four classifiers used for performance testing were K nearest neighbor (KNN) classifier, RIDOR classifier, artificial neural network classifier and support vector machine classifier. Thereafter, classification decisions obtained using KNN classifier for different feature extraction techniques have been integrated by Z-score normalization and feature scaling to create fusion-based framework of image recognition. It has been followed by the introduction of a fusion-based retrieval model to validate the retrieval performance with classified query. Earlier works on content-based image identification have adopted fusion-based approach. However, to the best of the authors’ knowledge, fusion-based query classification has been addressed for the first time as a precursor of retrieval in this work.

The proposed fusion techniques have successfully outclassed the state-of-the-art techniques in classification and retrieval performances. Four public data sets, namely, Wang data set, Oliva and Torralba (OT-scene) data set, Corel data set and Caltech data set comprising of 22,615 images on the whole are used for the evaluation purpose.

To the best of the authors’ knowledge, fusion-based query classification has been addressed for the first time as a precursor of retrieval in this work. The novel idea of exploring rich image features by fusion of multiple feature extraction techniques has also encouraged further research on dimensionality reduction of feature vectors for enhanced classification results.

The purpose of this paper is to examine the effect of the interpretation strategy of cultural mixing on consumers’ evaluations of global brands that incorporate local cultural elements. Specifically, this paper examines whether a property interpretation and a relational interpretation have different influences on consumers’ evaluations of global brands that incorporate local cultural elements.

Two experiments were conducted as part of this research. Experiment 1 adopted a two (interpretation strategy: property interpretation vs relational interpretation) single-factor between-subjects design. Experiment 2 adopted a 2 (interpretation strategy: property interpretation vs relational interpretation) × 2 (polyculturalist beliefs: high vs low) between-subjects design. The data were analyzed using ANOVA and PROCESS 213.

A property interpretation (emphasizing that some features of a global brand transfer to local cultural elements) leads to a less favorable evaluation of global brands that incorporate local cultural elements than a relational interpretation (emphasizing a relation between global brands and local cultural elements). This effect is fully mediated by perceived cultural intrusion, and it exists only when consumers have a low level of polyculturalist beliefs.

This paper reveals that the phenomenon of cultural mixing occurs when global brands incorporate local cultural elements. In addition, the way that consumers perceive the relationship between global brands and local cultural elements will determine their reactions to global brands that incorporate local cultural elements.

This paper reports a qualitative research study of comparative analysis of global citizenship education (GCE) in two primary schools, one international school in Singapore (Stamford International) and an independent school in Australia (Coastal College). The research focussed on how these two schools implemented GCE through the adoption of international education models, utilising the International Primary Curriculum (IPC) or the International Baccalaureate Programme (IB), creating hybrid curricula. Central to this research is the examination of educational practices, which address global citizenship education in each of the two schools.

Qualitative data from interview transcripts, document analysis, website analysis as well as field notes were analysed both inductively and deductively, teasing out the key themes from interviews, various documents such as policy papers, curriculum materials, syllabuses, the websites and other forms of documents that shed more light on the issues presented. The analysis of each case study began with a brief overview of the global citizenship education policies in the two schools and of their international curricula models, followed by a separate interpretation and juxtaposition of interview data (Phillips and Schweisfurth, 2014).

The key focus is examining the interplay between the global and national, which both schools have acknowledged in their design of the curricula. It is integral to note that globalization differs within different communities around the world with a unique and multifaceted interplay of global and national factors termed as a “global-local nexus”. A key overarching finding relates to the tensions between educational domains and neo-liberal market rationales, which had affected the schools' decisions in curricula and GCE enactment within both schools. Despite their commitment to GCE ideals, schools were mindful about being distinctive and remaining competitive within their educational markets.

In the study, the ideas of hybridity and “mixture and fusion” of curricula elements to generate new practices in local contexts against global influences have been explored. These ideas form the key features of the curriculum design in both schools and of the contexts in which the schools were situated. Even though the selected case study schools were international and independent and were not expected to fully adhere to government guidelines from their respective country’s policies, they were staged against these policies, which in turn influenced the curriculum initiatives and pedagogical approaches of these schools. Thus studying the landscape in which these two schools are situated provided a better understanding of the various influences – geo-political, formal policy, school-specific factors – which contributed to the knowledge base of global citizenship education studies for multi-ethnic nations such as Singapore and Australia.

As more national school systems embrace diversity, an international education approach has been adopted. This study affirms the idea proposed by Hayden, Thompson and Bunnell (2016), that the use of “international” is less relevant in categorising schools that seek to embrace GCE. It is more appropriate to use “cosmopolitan,” as proposed by Rizvi (2008), where the focus is more broadly on acquiring knowledge about cultural trajectories and social identities and reinforcing the idea of global connectivity as is evident in both case study schools. The focus is on understanding and acting on local issues within the “broader context of the global shifts that are reshaping the very nature of localities” (Rizvi, 2008, p. 21). One of the key things to note is that the global and international approaches are seldom enacted in their pure form. Schools that have adopted international education are usually unique and heterogeneous in nature, and what they have done is very much dependent on their histories, their geographical locations and the economic and political statuses. This is evident in both case study schools.

This study has added to the existing literature by providing a rich comparative investigation of global citizenship education in two countries, Australia and Singapore. The research provided the opportunity to study different models of internationally minded schools, with similar GCE ambitions. As the study explored two types of schools in two different countries, there is no claim of generalisability of findings to all the schools in these two countries. However, educators and researchers who are interested in this field could reflect on the themes that have emerged from this study and make an informed decision on the possible transferability to their own contexts.

Besides its contribution to existing literature, the study has also shown that for effective integration of GCE in schools, either in a national or international education system, it is necessary for a comprehensive understanding of the GCE principles. The results drawn from the study indicate that the ambiguity of the concept of GCE can result in different interpretations by school leaders, teachers and students, thus affecting its enactment in schools. In order to better understand and apply GCE, an effective conceptual model would provide a critical understanding of the multi-faceted nature of global citizenship education. A critical GCE requires schools to reflect on the entire curriculum, ensuring a seamless integration of GCE into curricula and practices.

High-resolution remote sensing images possess a wealth of semantic information. However, these images often contain objects of different sizes and distributions, which make the semantic segmentation task challenging. In this paper, a bidirectional feature fusion network (BFFNet) is designed to address this challenge, which aims at increasing the accurate recognition of surface objects in order to effectively classify special features.

There are two main crucial elements in BFFNet. Firstly, the mean-weighted module (MWM) is used to obtain the key features in the main network. Secondly, the proposed polarization enhanced branch network performs feature extraction simultaneously with the main network to obtain different feature information. The authors then fuse these two features in both directions while applying a cross-entropy loss function to monitor the network training process. Finally, BFFNet is validated on two publicly available datasets, Potsdam and Vaihingen.

In this paper, a quantitative analysis method is used to illustrate that the proposed network achieves superior performance of 2–6%, respectively, compared to other mainstream segmentation networks from experimental results on two datasets. Complete ablation experiments are also conducted to demonstrate the effectiveness of the elements in the network. In summary, BFFNet has proven to be effective in achieving accurate identification of small objects and in reducing the effect of shadows on the segmentation process.

The originality of the paper is the proposal of a BFFNet based on multi-scale and multi-attention strategies to improve the ability to accurately segment high-resolution and complex remote sensing images, especially for small objects and shadow-obscured objects.

To describe the architecture of iPOS (short for iPAQ positioning system), a novel fault‐tolerant and adaptive self‐positioning system with quality‐of‐service (QoS) guarantees for resource‐limited mobile devices.

The iPOS architecture is based on a novel sensor modelling technique in combination with a probabilistic data‐fusion engine, which is capable of efficiently combining the location information obtained from an arbitrary number of heterogeneous location sensors. As a proof of concept, the paper present a prototypical implementation for handheld devices, which was evaluated by means of practical experiments.

A major advantage of the iPOS positioning system is its extensibility and flexibility, which is achieved by means of an open plugin architecture and the support of global positioning coordinates according to the WGS‐84 standard. The iPOS system scales very well with respect to the number of sensor plugins that can be operated in parallel. The main limiting factor for the number of supported active plugins is the amount of available system resources on the MoD. With regard to recognition, the experimental results indicate a good accuracy of the fusion‐based positioning system in comparison to the accuracy of the individual sensing technologies. Thanks to the explicit modelling of reliable sensor events, the iPOS system is capable of providing QoS guarantees to applications with regard to the achieved positioning accuracy.

During the experiments, the author recognized time synchronisation as an important challenge that should be addressed as part of future work.

The system enables resource‐restricted mobile devices and computerised objects to exploit computing resources found in their immediate physical vicinity (locality).

The paper presents a novel lightweight sensor‐fusion architecture for fault‐tolerant and adaptive self‐positioning that performs well on resource‐limited mobile devices. A special feature of the developed data‐fusion architecture is the application of a novel event modelling technique that enables the positioning system to give QoS guarantees under certain conditions.

Diagnosing pain in neonates is difficult but critical. Although approximately thirty manual pain instruments have been developed for neonatal pain diagnosis, most are complex, multifactorial, and geared toward research. The goals of this work are twofold: 1) to develop a new video dataset for automatic neonatal pain detection called iCOPEvid (infant Classification Of Pain Expressions videos), and 2) to present a classification system that sets a challenging comparison performance on this dataset. The iCOPEvid dataset contains 234 videos of 49 neonates experiencing a set of noxious stimuli, a period of rest, and an acute pain stimulus. From these videos 20 s segments are extracted and grouped into two classes: pain (49) and nopain (185), with the nopain video segments handpicked to produce a highly challenging dataset. An ensemble of twelve global and local descriptors with a Bag-of-Features approach is utilized to improve the performance of some new descriptors based on Gaussian of Local Descriptors (GOLD). The basic classifier used in the ensembles is the Support Vector Machine, and decisions are combined by sum rule. These results are compared with standard methods, some deep learning approaches, and 185 human assessments. Our best machine learning methods are shown to outperform the human judges.