Paramartha Dutta

Multilevel image segmentation with adaptive image context based thresholding

Neural network based image segmentation techniques primarily focus on the selection of appropriate thresholding points in the image feature space. Research initiatives in this direction aim at addressing this problem of effective threshold selection for activation functions. Multilevel activation functions resort to fixed and uniform thresholding mechanisms. These functions assume homogeneity of the image information content. In this paper, we propose a collection of adaptive thresholding approaches to multilevel activation functions. The proposed thresholding mechanisms incorporate the image context information in the thresholding process. Applications of these mechanisms are demonstrated on the segmentation of real life multilevel intensity images using a self-supervised multilayer self-organizing neural network (MLSONN) and a supervised pyramidal neural network (PyraNet). We also present a bi-directional self-organizing neural network (BDSONN) architecture suitable for multilevel image segmentation. The architecture uses an embedded adaptive thresholding mechanism to a characteristic multilevel activation function. The segmentation efficiencies of the thresholding mechanisms evaluated using four unsupervised measures of merit, are reported for the three neural network architectures considered.

A study on energy optimized 4 dot 2 electron two dimensional quantum dot cellular automata logical reversible flip-flops

In the present scope, new design methodologies for reversible flip flops are proposed and the results are analyzed by the QCADesigner tool. To the best of our knowledge such methodologies are reported for the first time in the literature. In this paper, we provide few formalisms also. The first one is for the system energy derived using Hamiltonian paradigm and provides internal energy of cell electrons. The second formalism provides the minimum energy requirement for execution of a QCA architecture. This procedure reduces wastage of clock energy. Two very interesting parameters are identified playing crucial role in this context: (i) The electron quantum number n which indicates quantum energy level and (ii) intermediate quantum number for an electron lying between 1 and (n-1). It is established that the incident energy frequency is directly proportional to the number of cells and quadratic function of electron quantum number and intermediate quantum number. The dissipated energy frequency is also directly proportional to the product of number of cells and quadratic function of electron quantum number. This paper, reports some remarkable results. The relaxation time is observed being inversely proportional to the product of number of cells in the architecture and quadratic function of quantum number as well as intermediate quantum number. Apart from these, differential frequency is found directly proportional to the number of cells in the architecture and quadratic function of intermediate quantum number. Few major observations are also indicated: (i) There is always a probability of reflection even if the system energy exceeds barrier energy. (ii) On the contrary, there is always a probability of transmission even though system energy is dominated by the barrier energy.

Binary object extraction using bi-directional self-organizing neural network (BDSONN) architecture with fuzzy context sensitive thresholding

A novel neural network architecture suitable for image processing applications and comprising three interconnected fuzzy layers of neurons and devoid of any back-propagation algorithm for weight adjustment is proposed in this article. The fuzzy layers of neurons represent the fuzzy membership information of the image scene to be processed. One of the fuzzy layers of neurons acts as an input layer of the network. The two remaining layers viz. the intermediate layer and the output layer are counter-propagating fuzzy layers of neurons. These layers are meant for processing the input image information available from the input layer. The constituent neurons within each layer of the network architecture are fully connected to each other. The intermediate layer neurons are also connected to the corresponding neurons and to a set of neighbors in the input layer. The neurons at the intermediate layer and the output layer are also connected to each other and to the respective neighbors of the corresponding other layer following a neighborhood based connectivity. The proposed architecture uses fuzzy membership based weight assignment and subsequent updating procedure. Some fuzzy cardinality based image context sensitive information are used for deciding the thresholding capabilities of the network. The network self organizes the input image information by counter-propagation of the fuzzy network states between the intermediate and the output layers of the network. The attainment of stability of the fuzzy neighborhood hostility measures at the output layer of the network or the corresponding fuzzy entropy measures determine the convergence of the network operation. An application of the proposed architecture for the extraction of binary objects from various degrees of noisy backgrounds is demonstrated using a synthetic and a real life image.

Designing and Implementation of Quantum Cellular Automata 2:1 Multiplexer Circuit

Quantum Cellular Automata is a promising nanotechnology that has been recognized as one of the top six emerging technology in future computers. We have developed a new methodology in design QCA 2:1 MUX having better area efficiency and less input to output delay. We have also shown that using this QCA 2:1 M UX as a unit higher M UX can also be designed. We verified the proposed design using simulation from QCADesigner tool. This simulator is also useful for building complex QCA circuits.

High-speed target tracking by fuzzy hostility-induced segmentation of optical flow field

A time efficient technique for real-time tracking of high-speed objects in a video sequence is presented in this article. The technique is primarily based on the segmentation of the optical flow field computed between the successive image frames of a video sequence, followed by the tracking of a detected point of interest (POI) within the segmented flow field. In the initial phase of the technique, the optical flow field between the first two successive image frames acquired from a video sequence, is computed. A fuzzy hostility index indicative of the degree of coherence of the moving objects in the image frames, is used to segment the optical flow field. This yields different coherent regions of interest (ROIs) in the segmented flow field. A POI is then detected in the different ROIs obtained. Tracking of the moving object is then carried out by computing the flow fields between predefined ROIs in the neighborhood of the detected POI in the subsequent image frames. Since the selected ROIs are smaller than the image frames, a fair amount of reduction in the time required for the computation of the optical flow field is achieved, thereby facilitating real-time operation. An application of the proposed technique is demonstrated on three video sequences of high-speed flying fighter aircrafts.

Quantum Cellular Automata based Novel Unit 2:1 Multiplexer

Quantum Cellular Automata (QCA) is an emerging nanotechnology and one of the top six technologies of the future. CMOS technology has a lot of limitations while scaling into a nano-level. QCA technology is a perfect replacement of CMOS technology with no such limitations. In this paper we have proposed one 2:1 multiplexer circuit having lowest complexity and area compared to the existing QCA based approaches. The proposed design is verified using QCADesigner.

A 2 Dot 1 Electron Quantum Cellular Automata Based Parallel Memory

In the present scope, a new design methodology of parallel memory is offered. It is designed using 2 dot 1 electron Quantum-Dot Cellular Automata (QCA) paradigm. This methodology ensures better efficiency and high degree of compactness. One bit design methodology can be extended to design multiple bit parallel memory. Here we present 2 bit memory using 2 dot 1 electron QCA.

Genetic algorithm and gravitational emulation based hybrid load balancing strategy in cloud computing

Cloud computing enables a new supplement of consumption and delivery model for internet based services and protocol. It helps to provide software, hardware and data in form of collaborative services on the demand of the end user. To meet the QoS and ensure high interoperability and scalability is one of the most challenging tasks for cloud service provider. However, there are also several technical challenges that need to be tackled before the benefits can be fully realized. Among them reliability, resource provisioning, and efficient resources consuming etc are major concern. Load balancing also one of them. It includes selecting a proper node that must be full filled end user demand and also distribution of dynamic workload evenly into the multiple nodes. So load balancing can be described as an optimization problem and should be adapting nature due to the changing needs. In this paper we suggest a novel load balancing strategy to search under loaded node to balance load from overwhelmed node. CloudAnalyst used as a simulation tool for the proposed load balancing strategy. Experimental results of the sample application are really very encouraging. Significantly the results of the proposed algorithm are compared and outperformed the traditional strategy like First Come First Serve(FCFS), local search algorithm like Stochastic Hill Climbing(SHC) and soft computing approaches like Genetic Algorithm (GA) and Ant Colony Optimization(ACO).

An Ant Colony Based Load Balancing Strategy in Cloud Computing

Cloud computing thrives a new supplement of consumption and delivery model for internet based services and protocol. It provides large scale computing infrastructure defined on usage and also provides infrastructure services in a very flexible manner which may scales up and down according to user demand. To meet the QoS and satisfy the end users demands for resources in time is one of the main goals for cloud service provider. For this reason selecting a proper node that can complete end users task with QoS is really challenging job. Thus in Cloud distributing dynamic workload across multiple nodes in a distributed environment evenly, is called load balancing. Load balancing can be an optimization problem and should be adapting its strategy to the changing needs. This paper proposes a novel ant colony based algorithm to balance the load by searching under loaded node. Proposed load balancing strategy has been simulated using the CloudAnalyst. Experimental result for a typical sample application outperformed the traditional approaches like First Come First Serve (FCFS), local search algorithm like Stochastic Hill Climbing (SHC),another soft computing approach Genetic Algorithm (GA) and some existing Ant Colony Based strategy.

A parallel bi-directional self-organizing neural network (PBDSONN) architecture for color image extraction and segmentation

The parallel self-organizing neural network (PSONN) architecture uses bilevel sigmoidal activation functions for the purpose of extraction of embedded objects from pure color noisy perspectives. The process of extraction often involves an enhancement of the images under consideration. The network employs multilevel sigmoidal activation function to segment true color images. Both these activation functions are characterized by fixed thresholding parameters, which do not incorporate the underlying heterogeneity in the image intensity gamut. Methods for incorporating dynamic thresholding mechanisms into the thresholding characteristics of the PSONN architecture are investigated in this paper. We also propose a parallel bi-directional self-organizing neural network (PBDSONN) architecture to address the limitations of the PSONN architecture. Three constituent BDSONNs in the proposed architecture process color component information by embedded adaptive fuzzy context sensitive thresholding (CONSENT) mechanisms. A source layer feeds the BDSONNs with input color component information. Another sink layer fuses the processed color component information into resultant outputs. Comparative results of the quality of the extracted/segmented images indicate the efficacy of the proposed PBDSONN architecture over the PSONN architecture with fixed as well as dynamic thresholding mechanisms.