Earticle

The performance of image coding can be improved upon by using a special class of multiplierless discrete cosine transform using Ramanujan numbers termed as Ramanujan DCT (RDCT). Ramanujan ordered numbers are those which approximate 2π/N by 2 2 −l + −m , where l and m are integers. The cosine angles can then be computed using Chebyshev type of recursion using only shifters and adders. Fast forward and backward transformation may be achieved. Analysis and simulations show that the proposed RDCT maintains good de-correlation and energy compaction properties of the DCT and the error due to approximation is almost zero at lower spectral components and relatively low at higher spectral components. Simulation experiments are provided to justify that the proposed algorithm is best suited for image compression.

Selecting appropriate feature extraction method is absolutely one of the most important factors to archive high classification performance in pattern recognition systems. Among different feature extraction methods proposed for pattern recognition, statistical moments seem to be so promising. Whereas theoretical comparison of the moments is too complicated, in this paper, an experimental evaluation on four well known statistical moments namely Hu invariant moments, Affine invariant moments, Zernike moments, and Pseudo-Zernike moments is presented. Set of different experiments on a binary images dataset consisting of regular, translated, rotated, and scaled Persian printed numerical characters using a nearest neighbor rule classifier has been done and variety of interesting results have been presented. Finally, the results show that Pseudo-Zernike moments outperform the other introduced moments.

Ethernet has gained popularity for deploying in Metropolitan Area Networks (MANs) due to its ease of management and highly cost effective. While the flat addressing scheme (i.e., nonhierarchical MAC addresses) and the broadcast based address resolution scheme simplify many aspects of configuration, they also bring poor scalability. This paper aims at developing an efficient and scalable Metro-Ethernet architecture. To achieve this goal, we propose a Distributed Registration based Address Resolution Protocol (DRARP) and an End user enabled Mac-in-Mac (EMiM) encapsulation scheme. DRARP solves an unknown address through unicast, and hence eliminates the broadcast messages. EMiM does Mac-in-Mac (MiM) encapsulation by end users instead of the Provider Edge (PE) nodes, thus significantly reducing the PE node’s forwarding table size. The proposed architecture sustains the Ethernet’s plug-and-play feature and provides high scalability. The simulation results show that the proposed schemes can save more than 60% communication messages for address resolution and up to 80% forwarding table size in PE nodes.

In this paper we have proposed novel hardware for an adaptive encrypted watermarking method based on fuzzy logic. Fuzzy logic is used for data fusion, and it builds a human visual system (HVS) model for spatial masking in a wavelet domain. Encryption and digital watermarking both techniques must be incorporated to give best solution for digital rights management. It is obvious that these two technologies complement each other, and are both responsible for complete security of the digital information. Encryption transforms the original content into an unreadable format and watermarking leaves the digital object intact and recognizable. The aim of hardware assisted watermarking is to achieve low power usage, real-time performance, reliability, and ease of integration with existing consumer electronic devices. The experimental results demonstrate the high robustness of the proposed algorithm against the geometric distortion such as rotation and scaling.

In this paper, a new median filter switcher is presented for suppression of impulsive noise in gray-level images. The proposed filter is Modified Adaptive Center Weighted Median (MACWM) filter with an adjustable central weight obtained by partitioning the observation vector space. Dominant points of the proposed approach are partitioning of observation vector space using fuzzy c-means clustering method, training procedure using LMS algorithm and then applying the freezing weights of each block to test image. The exprimental results show better performance in the impulse noise reduction over standard images relative the median (MED) filter, the switching scheme I (SWM-I) filter, the signal dependent rank order mean (SD-ROM) filter, the tristate median (TSM) filter, the fast peer group filter (FPGF), the fuzzy median (FM) filter, the PFM filter and the adaptive center weighted median (ACWM) filter.

This paper presents three techniques of plants classification based on their leaf shape the SVM-BDT, PNN and Fourier moment technique for solving multiclass problems. All the three techniques have been applied to a database of 1600 leaf shapes from 32 different classes, where most of the classes have 50 leaf samples of similar kind. In the proposed work three techniques are used for comparing the performance of classification of leaves. Probabilistic Neural Network with principal component analysis, Support Vector Machine utilizing Binary Decision Tree and Fourier Moment. The proposed SVM based Binary Decision Tree architecture takes advantage of both the efficient computation of the decision tree architecture and the high classification accuracy of SVMs. This can lead to a dramatic improvement in recognition speed when addressing problems with large number of classes. Classification results from all the three techniques were compared and it was observed that SVM-BDT performs better than Fourier and PNN technique.