Mukul S. Sutaone

Bio: Mukul S. Sutaone is an academic researcher from College of Engineering, Pune. The author has contributed to research in topics: Image texture & Telecommunications link. The author has an hindex of 6, co-authored 50 publications receiving 159 citations.

A review on weight initialization strategies for neural networks

Abstract: Over the past few years, neural networks have exhibited remarkable results for various applications in machine learning and computer vision. Weight initialization is a significant step employed before training any neural network. The weights of a network are initialized and then adjusted repeatedly while training the network. This is done till the loss converges to a minimum value and an ideal weight matrix is obtained. Thus weight initialization directly drives the convergence of a network. Therefore, the selection of an appropriate weight initialization scheme becomes necessary for end-to-end training. An appropriate technique initializes the weights such that the training of the network is accelerated and the performance is improved. This paper discusses various advances in weight initialization for neural networks. The weight initialization techniques in the literature adopted for feed-forward neural network, convolutional neural network, recurrent neural network and long short term memory network have been discussed in this paper. These techniques are classified as (1) initialization techniques without pre-training, which are further classified into random initialization and data-driven initialization, (2) initialization techniques with pre-training. The different weight initialization and weight optimization techniques which select optimal weights for non-iterative training mechanism have also been discussed. We provide a close overview of different initialization schemes in these categories. This paper concludes with discussions on existing schemes and the future scope for research.

A combinational logic implementation of S-box of AES

Abstract: This paper presents a combinational logic based Rijndael S-box implementation for the SubByte transformation on ASIC. Combinational implementation of S-box results in low cost, small area occupancy and high throughput as compared to the typical ROM based lookup table implementation with fixed and unbreakable access time. S-box has been implemented using 0.18µm CMOS standard cell library at 1.62V and runs at clock frequency of 71.43MHz. We could achieve throughput of 571.5Mbps with core utilization of 85%, core area occupied is 39.88.4µm2 using only 178 cells. Total power dissipation of the S-box implementation is 0.611mW which is quite lower than other literature available.

Texture representation using autoregressive models

Abstract: Texture is a fundamental characteristic in many natural images that plays an important role in human visual perception and in turn provides information for image understanding and scene interpretation. The textured image can be modeled to describe, analyze and synthesize the texture. The model parameters capture the essential perceived qualities of texture. One of the important characteristics of texture data is the statistical dependence of the gray level at a lattice point on those of its neighbors. The spatial-interaction models characterize this statistical dependency by representing the intensity of a pixel, as a 2-D linear combination of the intensity of its neighbors and an additive noise. One way of specifying this interaction is simultaneous autoregressive (SAR) models. This is one of the most traditional methods used for modeling in the area of image processing. This paper presents the work done by the authors on parameter estimation and synthesis of textured images using Simultaneous Autoregressive (SAR) modeling. Different programs are developed in MATLAB to implement the parameter estimation and synthesis and are tested for their performance. The scope of this work includes the use of causal and noncausal methods for modeling and synthesizing natural textures. Simultaneous or spatial autoregressive models with causal and noncausal neighborhoods are used for parameter estimation and texture pattern generation. Parameter estimation is done by two different methods: The least square error (LSE) and maximum likelihood estimation (MLE). LSE method is preferred for causal models. MLE method is used for noncausal autoregressive models and it uses iterative algorithm. The synthesis procedure is based on generating a two dimensional autoregressive random field driven by a two dimensional zero mean white noise field with unit variance. Two different algorithms are used for synthesis of causal and noncausal AR models. Different image textures are synthesized using a given set of neighborhoods and parameters. Different patterns of synthetic images can be generated using various sets of parameters. A number of images from Brodatz album are tested for parameter estimation and synthesis. The synthesized image retains the pattern in the original image like vertical or horizontal streaks. An interactive graphical user interface (GUI) is developed using MATLAB that allows user to select one image from Brodatz album. The user can choose between causal or noncausal neighborhood and select number of elements in the neighborhood or choose any one set of neighborhood from different sets stored, and find out SAR model parameters by one of the methods of parameter estimation. The user can synthesize the image using these parameters. Both original and synthesized image are displayed side by side on the screen and the user can easily compare the two images. Thus the GUI offers an interactive platform for implementation of parameter estimation using different neighborhoods for the images from Brodatz album and synthesis of the image from these estimated parameters.

Ruggedisation methodologies for GPS based Vehicle Tracking System

Abstract: Main objective of this research proposal is to develop ruggedised strategic GPS based Vehicle Tracking System (VTS). For ruggedisation, system needs to be tested for specifications according to the different standards such as JSS-55555 / MIL-STD-810E (Environmental) and MIL-STD-461E (EMI/EMC). This paper gives brief survey of strategic testing procedures, typical severities of the tests, and probable failures/damages in the electronics / communication systems /circuits. The tests include Environmental, Dynamic, Corrosion, Mould growth, Radiated / Conducted Emission and Susceptibility, ESS and Burn-in, etc. This paper also explains the effect of all these tests on the equipment leading to probable damages/failures in the system for which cognizance must be taken in the design for improvement of reliability of the equipment to make the equipment compatible with stringent requirements. The outcome of these tests may be probable damages like failure of semiconductor devices and components, destruction of electronic circuits, breakage of PCB, damages in the enclosures, drift in the specifications / parameters, functional impairments, malfunctioning of the equipment, etc. The brief methodologies of ruggedisation such as selection of MIL grade components, use of shock mounts, specialized enclosure design, balanced mechanical layout, and use of protective coatings are recommended. These methodologies are useful to ensure the compatibility of GPS based Vehicle Tracking System with different standards like JSS-55555 / MIL-810E (Environmental).

Texture Feature Extraction Methods: A Survey

Abstract: Texture analysis is used in a very broad range of fields and applications, from texture classification (e.g., for remote sensing) to segmentation (e.g., in biomedical imaging), passing through image synthesis or pattern recognition (e.g., for image inpainting). For each of these image processing procedures, first, it is necessary to extract—from raw images—meaningful features that describe the texture properties. Various feature extraction methods have been proposed in the last decades. Each of them has its advantages and limitations: performances of some of them are not modified by translation, rotation, affine, and perspective transform; others have a low computational complexity; others, again, are easy to implement; and so on. This paper provides a comprehensive survey of the texture feature extraction methods. The latter are categorized into seven classes: statistical approaches, structural approaches, transform-based approaches, model-based approaches, graph-based approaches, learning-based approaches, and entropy-based approaches. For each method in these seven classes, we present the concept, the advantages, and the drawbacks and give examples of application. This survey allows us to identify two classes of methods that, particularly, deserve attention in the future, as their performances seem interesting, but their thorough study is not performed yet.

Surface defect detection in tiling Industries using digital image processing methods: analysis and evaluation.

Abstract: Ceramic and tile industries should indispensably include a grading stage to quantify the quality of products. Actually, human control systems are often used for grading purposes. An automatic grading system is essential to enhance the quality control and marketing of the products. Since there generally exist six different types of defects originating from various stages of tile manufacturing lines with distinct textures and morphologies, many image processing techniques have been proposed for defect detection. In this paper, a survey has been made on the pattern recognition and image processing algorithms which have been used to detect surface defects. Each method appears to be limited for detecting some subgroup of defects. The detection techniques may be divided into three main groups: statistical pattern recognition, feature vector extraction and texture/image classification. The methods such as wavelet transform, filtering, morphology and contourlet transform are more effective for pre-processing tasks. Others including statistical methods, neural networks and model-based algorithms can be applied to extract the surface defects. Although, statistical methods are often appropriate for identification of large defects such as Spots, but techniques such as wavelet processing provide an acceptable response for detection of small defects such as Pinhole. A thorough survey is made in this paper on the existing algorithms in each subgroup. Also, the evaluation parameters are discussed including supervised and unsupervised parameters. Using various performance parameters, different defect detection algorithms are compared and evaluated.

Efficient Built-In Redundancy Analysis for Embedded Memories with 2-D Redundancy

Abstract: A novel redundant mechanism is proposed for embedded memories in this paper. Redundant rows and columns are added into the memory array as in the conventional approaches. However, the redundant rows and columns are divided into row blocks and column blocks, respectively. The reconfiguration is performed at the row (column) block level instead of the conventional row (column) level. Based on the proposed redundant mechanism, we first show that the complexity of the redundancy allocation problem is NP-complete. Thereafter, an extended local repair-most (ELRM) algorithm suitable for built-in implementation is proposed. The complexity of the ELRM algorithm is O(N), where N denotes the number of memory cells. According to the simulation results, the hardware overhead for implementing this algorithm is below 0.17% for a 1024/spl times/2048-b SRAM. Due to the efficient usage of the redundant elements, the manufacturing yield, repair rate, and reliability can be improved significantly.