{"title":"Digital image watermarking technique for big size watermarks and high-resolution images using discrete cosine transform","authors":"A. Al-Gindy","doi":"10.1504/ijsise.2017.10008792","DOIUrl":"https://doi.org/10.1504/ijsise.2017.10008792","url":null,"abstract":"The capability of any watermarking system to hide large or small amounts of data while maintaining the robustness and quality is an important challenge in watermarking. The proposed algorithm can store hidden watermarking information up to 25% of the host image size. This means that it can also be an extremely robust technique when working with high-resolution images. The green channel of the RGB model has been used to host the watermark by modifying the very low-frequency coefficients of the discrete cosine transform transformation. The used frequency coefficients are predefined after a process of zigzag patterns. The new technique can resist classical attacks such as JPEG compression, low-pass filtering, median filtering and geometric attacks such as, cropping, rotation, affine and scaling. The method has been applied to high-resolution images that have been found to be extremely robust against attacks. The recovery method is blind because it does not need the original host image for extraction. The simulation results show that the proposed watermarking technique outperforms many other existing techniques.","PeriodicalId":56359,"journal":{"name":"International Journal of Signal and Imaging Systems Engineering","volume":"1 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2017-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49628062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nour-eddine Joudar, Fidae Harchli, Es-Safi Abdelatif, M. Ettaouil
{"title":"New adaptive switching scheme for impulse noise removal: modelling and resolution by genetic optimisation","authors":"Nour-eddine Joudar, Fidae Harchli, Es-Safi Abdelatif, M. Ettaouil","doi":"10.1504/IJSISE.2017.10008793","DOIUrl":"https://doi.org/10.1504/IJSISE.2017.10008793","url":null,"abstract":"Nowadays, the optimisation is one of the techniques which has proved its efficiency in many areas. In this paper, we propose a novel optimisation-based technique for impulse noise removal. Based on the classical image restoration model, we build a new objective function by introducing a new binary vector that indicates the pixels categories. We combine each pixel with the median of its neighbours in a decision rule so that one of them generates the optimal solution. The resolution of the proposed model is carried out by the genetic algorithm. Once noisy pixels are detected, a median based filter is performed only for these pixels. Experiments show that the results are satisfactory in term of both visual quality and quantitative measurement.","PeriodicalId":56359,"journal":{"name":"International Journal of Signal and Imaging Systems Engineering","volume":"10 1","pages":"316"},"PeriodicalIF":0.6,"publicationDate":"2017-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42047964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A high-gain adaptive observer for discrete-time nonlinear systems","authors":"A. Ghanmi, S. Hajji, S. Kamoun","doi":"10.1504/IJSISE.2017.10008789","DOIUrl":"https://doi.org/10.1504/IJSISE.2017.10008789","url":null,"abstract":"This paper focuses on the development of adaptive observer for a class of nonlinear discrete-time systems. A high-gain observer is used to estimate the unknown parameters and state variables. The problem formulation is achieved based on the Euler approximation method. The proposed algorithm is developed to guarantees the convergence of parameters and state variables to their true values. Based on a new formulation of the high-gain observer, sufficient conditions and assumptions to ensure asymptotic convergence are established. An example involving a typical bioreactor illustrates some results of the proposed observer.","PeriodicalId":56359,"journal":{"name":"International Journal of Signal and Imaging Systems Engineering","volume":"10 1","pages":"279"},"PeriodicalIF":0.6,"publicationDate":"2017-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47730599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Mathematical analysis of RF imaging techniques and signal processing using wavelets","authors":"M. Khulbe, H. Parthasarathy, M. Tripathy","doi":"10.1504/IJSISE.2017.10008790","DOIUrl":"https://doi.org/10.1504/IJSISE.2017.10008790","url":null,"abstract":"Non-linear optics plays an important role in the imaging. In this paper using non-linearity, we have derived three different techniques for imaging. In the first technique, an algorithm is developed for the scattering of electromagnetic waves from the medium, which gives higher-order harmonics of the EM wave. Here, the linear and non-linear interactions of molecules with the applied electromagnetic waves play an important role in target detection. We assume the material is inhomogeneous and represented by its susceptibility tensor. Second technique for detection of non-linearity or higher-order harmonic is using anharmonic oscillator model where the perturbation due to non-linearity in the electron moment is derived and mapped to the second harmonic generation of electromagnetic waves. Third technique is applied using Gaussian monopulse where the non-linear interaction of wave with the matter makes the phase change of the wave. When wavelet transforms with dilations and translation are applied to these non-linear waveforms, we get the details of region of interest in terms of wavelet coefficients. The region of interest may be 1-dimensional, 2-dimensional or 3-dimensional. These methods can be used in biomedical applications and other areas where target is in the near-field range.","PeriodicalId":56359,"journal":{"name":"International Journal of Signal and Imaging Systems Engineering","volume":"10 1","pages":"286"},"PeriodicalIF":0.6,"publicationDate":"2017-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45757758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. C. Dinis, T. Moraes, P. Amorim, O.H.J. Amorim, Jorge Silva, R. Ruben
{"title":"An open-source GUI application for segment foetal ultrasound images","authors":"J. C. Dinis, T. Moraes, P. Amorim, O.H.J. Amorim, Jorge Silva, R. Ruben","doi":"10.1504/IJSISE.2017.10008718","DOIUrl":"https://doi.org/10.1504/IJSISE.2017.10008718","url":null,"abstract":"There are several commercial software for medical image dataset segmentation. However, most of them are expensive and not user-friendly. With our proposal of a new open-source software with a simple and specific graphical user interface (GUI), it is easy to segment a foetus from a 3D ultrasound medical image dataset. The segmented portion of images can be converted into a stereolithography (STL) file format for 3D print technologies in order to obtain an accurate physical reproduction of the model segmented. Despite the large number of segmentation algorithms available, this new GUI has three specific possibilities (threshold, region growing and Chan-Vese) in order to keep it simple and efficient. For the same reason, the GUI has just three noise filters available in order to reduce speckle. Besides GUI simplicity, a good segmentation quality was achieved. The main purpose of our proposal is to segment foetal 3D ultrasound images and to make this task quick, easy and efficient.","PeriodicalId":56359,"journal":{"name":"International Journal of Signal and Imaging Systems Engineering","volume":"10 1","pages":"271"},"PeriodicalIF":0.6,"publicationDate":"2017-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48709849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Telugu character recognition for degraded palm leaf documents using optimal feature selection techniques - a 3D approach","authors":"T. Lakshmi, P. N. Sastry, T. Rajinikanth","doi":"10.1504/IJSISE.2017.10008711","DOIUrl":"https://doi.org/10.1504/IJSISE.2017.10008711","url":null,"abstract":"Palm leaves were used as a medium of recording information about 700 years ago. This work deals with the recognition of Telugu palm leaf characters by acquiring 3D data using a contact-type profiler. A novel concept of using a 3D inherent feature, i.e. depth of incision is proposed to eliminate noise. With the help of this 3D feature, improved recognition accuracy is also reported for various features extracted from the palm leaf characters. Experiments are conducted by implementing optimisation techniques, such as differential evolution and particle swarm optimisation, to find the optimum number of features to reduce the memory needed. With varying feature dimensions, average classification accuracies are reported for combination of feature extraction methods and optimisation techniques.","PeriodicalId":56359,"journal":{"name":"International Journal of Signal and Imaging Systems Engineering","volume":"10 1","pages":"223"},"PeriodicalIF":0.6,"publicationDate":"2017-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41414109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Adaptive-scale convolutional neural networks for texture image analysis","authors":"Bachir Kaddar, H. Fizazi","doi":"10.1504/IJSISE.2017.10008716","DOIUrl":"https://doi.org/10.1504/IJSISE.2017.10008716","url":null,"abstract":"This paper proposes an effective adaptive-scale convolutional neural networks (A-SCNN) for texture image analysis. We combine the multi-scale texture image analysis with the efficient feature space of a convolutional neural network to extract characteristic texture features. These latter encode regions of adaptive sizes centered on each pixel according to different optimal scales reflecting the local structure pattern content. To fix the scale-space values accurately, the Hessian-Laplacian operator is used. Experimental results demonstrate a good performance of the proposed A-SCNN in texture classification. Particularly, the CNN based on the adaptive scale shows promising for irregular texture pattern classification, and the selective sizes of both feature maps and receptive fields can further improve the performance of the classical CNN texture discrimination ability.","PeriodicalId":56359,"journal":{"name":"International Journal of Signal and Imaging Systems Engineering","volume":"10 1","pages":"248"},"PeriodicalIF":0.6,"publicationDate":"2017-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46582832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An efficient hybrid PC-SIFT-based feature extraction technique for face recognition","authors":"Deepti Ahlawat, Vijay Nehra","doi":"10.1504/IJSISE.2017.10008715","DOIUrl":"https://doi.org/10.1504/IJSISE.2017.10008715","url":null,"abstract":"In this investigation, an efficient hybrid approach involving phase congruency (PC) and shift invariant feature transform (SIFT) for face recognition is presented. The present study exploits the advantages of PC and SIFT together for the purpose of efficient feature extraction for the facial images. The effectiveness of the present work is analysed and compared using other classifiers, i.e. K-means and self-organizing map. The results of this study demonstrate that phase congruency - shift invariant feature transform is robust to expression variations and shows better performance than other comparative methods and achieves good recognition accuracy. Studies are conducted on Japanese female facial expression and Yale databases. The proposed technique has been compared with the existing techniques, and from the experiments, it is observed that the results of the proposed technique are better than the existing techniques.","PeriodicalId":56359,"journal":{"name":"International Journal of Signal and Imaging Systems Engineering","volume":"10 1","pages":"237"},"PeriodicalIF":0.6,"publicationDate":"2017-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41494419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Makeup-invariant face identification and verification using fisher linear discriminant analysis-based Gabor filter bank and histogram of oriented gradients","authors":"I. Kamil, Aliu S. Are","doi":"10.1504/IJSISE.2017.10008717","DOIUrl":"https://doi.org/10.1504/IJSISE.2017.10008717","url":null,"abstract":"Non-permanent facial makeup is one of the most difficult problems inhibiting face recognition systems in security applications. In this paper, a new method is proposed for makeup-invariant face identification and verification. Face images from the virtual makeup (VMU) and YouTubemakeup (YMU) datasets were subjected to the Gabor filtering and histogram of oriented gradients (HOG) methods for feature extraction. The Gabor and HOG features were concatenated to generate the final feature vectors and subsequently reduced using the fisher linear discriminant analysis subspace. The reduced features were classified using the city block distance (CBD), Euclidean distance (EUC), cosine similarity measure (CSM) and whitened cosine similarity measure (WCSM). The CSM achieved the best recognition rates out of the four metrics used. Performance evaluation of these metrics produced identification and verification rates of 100% and 100% for the VMU database, and 72.52% and 79.47% for the YMU database, respectively. The developed method outperformed several state-of-the-art methods initially exploited.","PeriodicalId":56359,"journal":{"name":"International Journal of Signal and Imaging Systems Engineering","volume":"10 1","pages":"257"},"PeriodicalIF":0.6,"publicationDate":"2017-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42067138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"QOS enabled data dissemination in hierarchical VANET using machine learning approach","authors":"K. KrishnaKumar, E. J. T. Fredrik","doi":"10.1504/IJSISE.2017.10008714","DOIUrl":"https://doi.org/10.1504/IJSISE.2017.10008714","url":null,"abstract":"Vehicular ad hoc networks (VANETs) are a collection of vehicular nodes that perform as a mobile hosts form a temporary network without the aid of any centralised infrastructure, so it is a sub-class of ad hoc network. It ensures the quality of service (QoS) for different VANET applications. Although it provides the QoS services to the process, mobility and routing play an important challenge in the VANET environment. So, different researches have revealed that the hierarchical routing schemes have numerous benefits over the traditional ones. Stable cluster formation and maintenance with the guarantying QoS in intra-cluster communications has always remained as a great challenge. For overcoming this issue, this paper proposes a QoS enabled data dissemination using an improved Kruskal's algorithm to provide efficient data dissemination and QoS in hierarchical VANET. This approach constructs the minimum spanning trees using Kruskal's algorithm in every road segment, where the vehicle has been clustered using the fuzzy c-means clustering method by considering the intra-cluster QoS. Each spanning tree will have a cluster head that is responsible to collect the data from the leaf nodes and disseminates the data to other coordinator nodes and vice versa. The simulation results show that the proposed approach performs better than the existing routing approach in terms of delay, throughput and packet loss.","PeriodicalId":56359,"journal":{"name":"International Journal of Signal and Imaging Systems Engineering","volume":"10 1","pages":"231"},"PeriodicalIF":0.6,"publicationDate":"2017-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66731627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}