The process of segmenting images is one of the most critical ones in automatic image analysis whose goal can be regarded as to find what objects are present in images. Artificial neural networks have been well developed so far. First two generations of neural networks have a lot of successful applications. Spiking neuron networks (SNNs) are often referred to as the third generation of neural networks which have potential to solve problems related to biological stimuli. They derive their strength and interest from an accurate modeling of synaptic interactions between neurons, taking into account the time of spike emission. SNNs overcome the computational power of neural networks made of threshold or sigmoidal units. Based on dynamic event-driven processing, they open up new horizons for developing models with an exponential capacity of memorizing and a strong ability to fast adaptation. Moreover, SNNs add a new dimension, the temporal axis, to the representation capacity and the processing abilities of neural networks. In this paper, we present how SNN can be applied with efficacy in image segmentation and edge detection. Results obtained confirm the validity of the approach.

This paper concentrates on the use of Echo State Networks (ESN), an effective form of reservoir computing, for improving microscopic cellular images segmentation. ESN is a sparsely connected recurrent neural network with most of its weights fixed a priori to randomly chosen values. The only trainable weights are those on links connected to the outputs. The process of segmentation is done with two approaches: the basic form with one reservoir and our approach that corresponds to using multiple reservoirs. Obtained results confirm the benefits of the second approach that outperforms all the state-of-the-art methods considered in this paper for the microscopic image segmentation problem.

No abstract

For various forms of skin lesion, many different feature extraction methods have been investigated so far. Indeed, feature extraction is a crucial step in machine learning processes. In general, we can distinct handcrafted and deep learning features. In this paper, we investigate the efficiency of using 17 commonly pre-trained convolutional neural networks (CNN) architectures as feature extractors and of 24 machine learning classifiers to evaluate the classification of skin lesions from two different datasets: ISIC 2019 and PH2. In this research, we find out that a DenseNet201 combined with Fine KNN or Cubic SVM achieved the best results in accuracy (92.34% and 91.71% ) for the ISIC 2019 dataset. The results also show that the suggested method outperforms others approaches with an accuracy of 99% on the PH2 dataset.

In this paper, we propose a spiking neural network model for edge detection in images. The proposed model is biologically inspired by the mechanisms employed by natural vision systems, more specifically by the biologically fulfilled function of simple cells of the human primary visual cortex that are selective for orientation. Several aspects are studied in this model according to three characteristics: feedforward spiking neural structure; conductance-based model of the Hodgkin-Huxley neuron and Gabor receptive fields structure. A visualized map is generated using the firing rate of neurons representing the orientation map of the visual cortex area. We have simulated the proposed model on different images. Successful computer simulation results are obtained. For comparison, we have chosen five methods for edge detection. We finally evaluate and compare the performances of our model toward contour detection using a public dataset of natural images with associated contour ground truths. Experimental results show the ability and high performance of the proposed network model.

Abstract. Artificial neural networks have been well developed so far. First two generations of neural networks have had a lot of successful applications. Spiking Neuron Networks (SNNs) are often referred to as the third generation of neural networks which have potential to solve problems related to biological stimuli. They derive their strength and interest from an accurate modeling of synaptic interactions between neurons, taking into account the time of spike emission.SNNs overcome the computational power of neural networks made of threshold or sigmoidal units. Based on dynamic event-driven processing, they open up new horizons for developing models with an exponential capacity of memorizing and a strong ability to fast adaptation. Moreover, SNNs add a new dimension, the temporal axis, to the representation capacity and the processing abilities of neural networks. In this chapter, we present how SNN can be applied with efficacy in image clustering, segmentation and edge detection. Results obtained confirm the validity of the approach.

Abstract-

A mobile ad hoc network (MANET) is a set of mobile and self-organizing nodes that cooperate to create dynamic network architecture to establish communications. Its characteristics present critical challenges: limited residual energy of nodes and transmission range, wireless links sensitivity to environmental effects, and the mobility aspect, which leads to frequent link failure and rapid changes in the network topology. In this paper, we propose a new multipath routing protocol RMQS-ua (Reliable Multipath Routing Protocol based on Link Quality and Stability in Urban Areas). Our objective is to select the path that has better link quality and more stable links to guarantee reliable data transmission. We consider a combination of signal to noise ratio SNR and an enhanced packet reception ratio PRR to evaluate link quality, and the exponential moving average (EMA) to estimate the link stability. RMQS-ua is designed for an urban area that includes shadowing effect and background noise which deteriorates the link quality. Simulation results show that RMQS-ua improves network performance, and provides more reliability compared to some recent existing protocols.