This research paper proposes the novel face recognition (FR) descriptor for pose and expression variations so-called multi-scale neighbourhood based-tree binary pattern (MNB-TBP). To produce the entire feature size of the MNB-TBP descriptor, two local descriptors are introduced. These two local descriptors are called as NB-TBP and mean (Mn)NB-TBP. The methodologies adopted for NB-TBP and MnNB-TBP descriptors are totally novel and are based on tree structure. The multi-scale feature extraction and combination of both the proposed descriptors gives the emergence of MNB-TBP descriptor. To produce the compact and robust feature for classification principal component analysis (PCA) is applied further. Finally classification is performed by support vector machines (SVM) and nearest neighbour (NN). The three challenging databases used for the performance evaluation are Olivetti Research Laboratory (ORL), Georgia Technology (GT) and Faces94. The proposed FR approach achieves very effective results which comprehensively outperforms the several state-of-art approaches from the literature.

In order to overcome the problem of low throughput and time-consuming of traditional fingerprint minutiae matching methods, a new convolutional-deep neural network is proposed for parallel fingerprint minutiae matching. This method realises the preprocessing of the initial image through four steps: normalisation, image enhancement, parallel thinning and image segmentation. The convolutional-deep neural network is constructed from convolution kernel, convolution layer, pooling layer and full connection layer to extract minutiae of fingerprint image. Through feature minutiae matching, local matching and global matching, the matching results of fingerprint parallel nodes are obtained. The experimental results show that compared with the traditional matching method, the fingerprint matching throughput of convolutional-deep neural network is increased by 25%, and the matching time is saved by about 8 seconds.

This paper conducts the first experiments applying recurrent neural networks-RNN accompanied with connectionist temporal classification (CTC) to build end-to-end online Uyghur handwriting word recognition system. The traced pen-tip trajectory is fed to network without conducting segmentation and feature extraction. The network is trained to transcribe handwritten word trajectory to a string of characters in alphabet which has total 128 character forms. In order to avoid overfitting during training and improve generalisation of the model, dropout technique is implemented. An online handwritten word dataset has been established and used for model training and evaluation in writer independent manner. Recognition results are evaluated by calculating the Levenshtein-edit distance and 14.73% character error rate CER on test set of 3,600 samples for 900 word classes has been observed without help of any lexicon search and language model.

In this paper, a new transform Gabor filtered Wigner transform (GFWT) has been proposed. In GFWT, Gabor filtering is performed on the Wigner transformed image. Wigner transform gives a simultaneous representation of an image in time and frequency domain which is further processed using Gabor filters. The proposed transform is then used to extract the features from the biometrics to develop different multimodal biometric systems. A detailed study has been carried out in which, different unimodal and multimodal systems such as feature level and score level fusion are analysed. In order to improve the performance of the system, an optimisation technique, particle swarm optimisation (PSO) is used to find the optimal parameters of the Gabor filter and to select the significant GFWT feature vector. The PSO technique not only improves the performance of the system but also able to reduce the dimension of the feature vectors. Numerical experiments are carried out on face and palmprint database to show the effectiveness of the proposed transform for different unimodal and multimodal systems.

Educational informatisation is an important part of national informatisation strategy. The realisation of educational informatisation plays a fundamental, global and lasting role in social development. The advent of the Web 2.0 era has injected new impetus into the development of network education. Web 2.0 has the characteristic of personalisation, decentralisation, openness, interactivity, and sociality. It corresponds to the educational idea advocated by modern educational theory. Through the method of literature analysis, this paper collates and think about the current educational application research under the Web 2.0, and finally through specific case analysis and comparison to verify the views and draw conclusions and provide reference for the future research of Web 2.0 and educational informatisation platform.

AC permanent magnet synchronous motor servo control system is a complex nonlinear, strong coupling and time-varying system. It has strong uncertainty and nonlinearity, and when the system is running, it also will be disturbed to varying degrees, so the conventional control strategy is difficult to meet the control requirements of high accuracy, high speed and high-performance servo system. This paper adopts a direct feedback linearisation control strategy based on sensor technology and uses, as the output of the system to realise the decoupling of the system. In addition, the grey prediction is added to overcome the shortcomings of direct feedback linearisation that is sensitive to parameters. Adjusting the uncertain factors block by grey prediction to adapt to the direct feedback linearisation rule and achieve the desired effect. MATLAB/Simulink is used to complete the simulation of servo control algorithm. The simulation results show that the direct feedback linearisation control is better than the conventional PID control, and the direct feedback linearisation control algorithm with grey prediction can improve the performance of the permanent magnet synchronous motor servo control system and can meet the basic requirements of the high-performance servo control system.

The paper presents a new face recognition system robust to illumination variations and moderate occlusion. Two main contributions are discussed. First, we introduce an approach based on contrast equalisation (CE) to improve the traditional Weber-face (WF) technique and make it more robust. Second, we use the local binary patterns (LBP) and local phase quantisation (LPQ) descriptors to make the Weber-face method more resilient to variations in illumination by exploiting both spatial and frequency domains information. By combining the two descriptors, enhanced facial features are obtained showing more discriminating power for variable lighting conditions as well as occlusion. The concept of complementing the WF model with spatial-frequency descriptors is novel and shown to result in a robust system resilient to changing lighting conditions, variations in pose, and occlusion. The method was compared to a number of existing techniques over three public databases. The proposed algorithm outperformed existing techniques under challenging environments.

Ear is a potential biometric parameter which has drawn the attention due to its structural uniqueness and stability over the age, obesity, disease, expression, etc., unlike other common biometric traits. In this work a geometric retrieval algorithm has been proposed for ear-based biometric analysis with occluded image. First the occlusion problem is countered by an empirical data driven technique and then PSO-based optimal features are extracted for comparison that reveals the authenticity of the subject with respect to a stored database. A search of minima from Euclidian distance-based analysis is used for final decision. The proposed system is tested on 50 subjects collected in multiple sessions in laboratory with a good recognition rate superior to similar reported works as indicated in the result section.

Security on smartphones has become a substantial topic since the amount of security relevant data and information stored on them has been increasing. While the password is commonly used as a traditional approach for user authentication, it suffers from a security-usability trade-off dilemma. Accordingly, the keystroke dynamics authentication approach can provide ease of use to the user as well as robust security. This paper investigates the feasibility of utilising user-typing behaviours on touchscreen keypads for the authentication process via free-text keystroke dynamics. In constructing the timing vectors, three timing features are used: hold time, flight time and digraph duration. Additionally, Euclidian and Manhattan distances were utilised to find the degree of similarity between the user's login data and user's profile. An Android application was developed and evaluated through an experimental study. Thus, we achieved a very encouraging result, as we were able to show that applying the free-text method indeed influences the accuracy of user authentication on a touchscreen device.

With the continuous development of multimedia and speech teaching laboratory in colleges and universities, and the application of digital processing technology, digital voice teaching equipment is ...