Search

Image denoising is one of the preliminary steps in image processing methods in which the presence of noise can deteriorate image quality. This paper presents an improved two-stage fuzzy filter for filtering salt and pepper noise from the images to enhance the image quality. In the first stage, the pixels in the image are categorized as good or noisy based on adaptive thresholding using type-2 fuzzy logic with exclusively two different membership functions in the filter window. In the second stage, the noisy pixels are denoised using modified ordinary fuzzy logic in the respective filter window. The proposed filter is validated on standard images with various noise levels. The proposed filter removes the noise and preserves beneficial image characteristics, i.e., edges and corners at higher noise levels. The performance of the proposed filter is compared with the various state-of-the-art methods in terms of peak signal-to-noise ratio and computation time. The average PSNR values for the noise percentage 20%, 50% and 80% are the 37%, 31% and 27%. To show the effectiveness of statistical filter tests, i.e., the Friedman test and Bonferroni−Dunn (BD) test are also carried out, which ascertain that the proposed filter outperforms in comparison to various filtering approaches. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks (CNN) are being widely practised in computer vision applications, where pooling indicates as an integral part. Pooling significantly reduces the training time and computational cost of any network. The pooling operations generally being used are max, average, or stochastic. The performance of the CNN architecture can be increased by using more than one pooling operations. Herein, a novel mixed fuzzy pooling is proposed for image classification in the CNN architecture. In the proposed mixed fuzzy pooling, max pooling and fuzzy pooling are combined together to boost the classification accuracy. The proposed mixed fuzzy pooling is designed as a function of max pooling, fuzzy pooling, and α parameter where the learning of the proposed pooling function takes place with the value of α. In fuzzy pooling, Type-2 fuzzy logic is used to get the convolved dominant features. This is obtained by the estimation of a threshold for image region to be pooled. Thereafter, Type-1 fuzzy logic is used to get the pooling output by a weighted average of convolved dominant features. The performance of various pooling strategies on MNIST dataset for handwritten digits classification and CIFAR-10 dataset for RGB images classification have been compared and analysed. The experimental results show better image classification accuracy for the proposed mixed fuzzy pooling than conventional pooling operations. [ABSTRACT FROM AUTHOR]

Adaptability of an effective access network in optical code division multiple access domain requires an efficient coding scheme which has the abilitiy to provide required communication capacity in terms of cardinality, reach, and data rates. In this paper, an extensive study and investigation has been carried out for adaptability study of a well-known coding scheme diagonal eigenvalue unity (DEU) code at various date rates in passive optical network (PON) environment. DEU code design is based on Jordan block matrix with ideal in-phase cross correlation (IPCC) properties. The numerical and simulation results show the ability of DEU code in supporting synchronized transmissions at different data rates that suits triple play services of video, audio and data (VAD). An algorithm is developed to determine the required chip duration that matches a particular service. It shows that data rate is more influential than code length on pulse duration especially for video applications. In support of the proposed algorithm, 5 Gb/s, 2.5 Gb/s, and 1.25 Gb/s data rate transmissions have been validated for various simultaneous users. In addition, a Poisson's distribution analysis is carried out aiming to study different bit rate scenarios with ad hoc population network. Results have concluded that higher value of average rate of simultaneous users (σ) is preferable for low data rate whereas the lower value of σ is suitable to the higher data rates in accordance with network population. In particular, for video streaming, the traffic running in a continuous fashion requires the highest transmission priority and small value of σ. [ABSTRACT FROM AUTHOR]

One dimensional encoding in optical communications has limitations in terms of the number of supported users and large bandwidth consumption. This study presents a new algorithm to generate two-dimensional (2D) encoding utilizing permutation vectors (PV) theory for incoherent multiple access network to suppress multiple access interference (MAI) and system complexity. The proposed code design approach is based on spectral/spatial techniques for code generation. All possible combinations of PV code-sets are obtained by utilizing all permutations of the vectors with the repetition of each vector weight (W) times. Furthermore, the 2D-PV code-set is constructed by combining two code sequences of the 1D-PV code. Furthermore, the transmitter–receiver architecture of the 2D-PV spectral/spatial (S/S) code based OCDMA system is presented. The Gaussian approximation is used to analyze the performance of the proposed OCDMA system with 2D- PV code by considering various noise sources (shot, thermal, and PIIN). Results indicate that the 2D-PV code provides increased cardinality by eliminating phase induced intensity noise (PIIN) effects with a minimum likelihood of interference between multiple user data. Simulation implementations validate the proposed system performance for an agreeable bit error rate (BER) of 10–9 [ABSTRACT FROM AUTHOR]

Single-image dehazing is an extensively studied field and an ill-posed problem faced by vision-based systems in an outdoor environment. This paper proposes a dark channel network to estimate the transmission map of an input hazy scene for single-image dehazing. The architecture constitutes two major components—feature extraction layer and convolutional neural network layer. The former extracts the haze relevant features, while latter convolve these features with filter kernels to estimate the true scene transmission. Finally, the estimated transmission map is used to obtain the dehazed image using atmospheric scattering model. The experiments have been performed on synthetic hazy images and benchmark hazy dataset available in the literature. The performance of the proposed architecture outperforms the existing models in terms of standard quantitative metrics—mean square error, structural similarity index, and peak signal-to-noise ratio. [ABSTRACT FROM AUTHOR]

This paper undertakes the ancillary topic of relation between the transmission capacity of two dimensional optical code division multiple (2D-OCDMA) systems and its economic aspects. A new code called 2D double weight zero cross-correlation (2D-DZCC) is developed and implemented in both spectral-spatial and spectral-temporal 2D-OCDMA systems for a comprehensive techno-economic analysis. In order to determine the most efficient network architecture in terms of system capacity and cost, both models are evaluated for allowed bandwidth in terms of data, and reach. The technological analysis is followed by investigation of capital expenditure (CAPEX) for both architectures in terms of the cost incurred on network components between the transmitter and receiver modules. Evaluation of both models demonstrates that spectral-temporal OCDMA system tends to provide relatively same transmission capacity with ≈ 70 % reduced cost of implementation in comparison with the spectral-spatial system. Consequently, making spectral-spatial systems most suitable for the deployment of passive optical network (PON) at the low cost access domain. [ABSTRACT FROM AUTHOR]

This paper proposes a novel deep learning-based single image dehazing network named as Compact Single Image Dehazing Network (CSIDNet) for outdoor scene enhancement. CSIDNet directly outputs a haze-free image from the given hazy input. The remarkable features of CSIDNet are that it has been designed only with three convolutional layers and it requires lesser number of images for training without diminishing the performance in comparison to the other commonly observed deep learning-based dehazing models. The performance of CSIDNet has been analyzed on natural hazy scene images and REalistic Single Image DEhazing (RESIDE) dataset. RESIDE dataset consists of Outdoor Training Set (OTS), Synthetic Objective Testing Set (SOTS), and real-world synthetic hazy images from Hybrid Subjective Testing Set (HSTS). The performance metrics used for comparison are Peak Signal to Noise Ratio (PSNR) and Structural SIMilarity (SSIM) index. The experimental results obtained using CSIDNet outperform several well known state-of-the-art dehazing methods in terms of PSNR and SSIM on images of SOTS and HSTS from RESIDE dataset. Additionally, the visual comparison shows that the dehazed images obtained using CSIDNet are more appealing with better edge preservation. Since the proposed network requires minimal resources and is faster to train along with lesser run-time, it is more practical and feasible for real-time applications. [ABSTRACT FROM AUTHOR]

Spectral Amplitude Coding Optical Code Division Multiple Access (SAC–OCDMA) is an auspicious advancement in an asynchronous environments. In this paper, we have presented an effective Enhanced Quantum Logic Gate (EQLG) code for SAC–OCDMA to improve the code construction, cross-correlation and minimize the noises. The EQLG code contains unitary matrices with minimum overlaps in code spectral wavelengths of various clients. This drops the Multiple Access Interference (MAI) and furthermore EQLG code, provides high data-rate transmission in networks. The development of the proposed EQLG code is depicted in following strides as; at first build a matrix utilizing the estimation of the weight value and the number of subscribers. Based upon that, the number of rows and columns are located in the matrix. Second, each diagonal sequences are computed by using the QLG method. The execution of the recommended EQLG code will be analysed with existing SAC–OCDMA systems in response to Bit Error Rate (BER). The simulations of encoding with 10–60 users with 622 Mb/s data transmission at a BER of 10−9 have been successfully achieved. [ABSTRACT FROM AUTHOR]