This paper presents a study on the use of Convolutional Neural Networks for camera relocalisation and its application to map compression. We follow state of the art visual relocalisation results and evaluate response to different data inputs – namely, depth, grayscale, RGB, spatial position and combinations of these. We use a CNN map representation and introduce the notion of CNN map compressio...

Recently discrete-time cellular neural network (DT-CNN) is applied to many image processing such as compression and reconstruction, recognition, and so on. Not a few model works as a simple filter and doesn’t make good use of CNN dynamics by feedback A template, which is one of the significant characteristics of CNN. If CNN is applied to a filter by an only feed forward B template, you should p...

A cellular neural network (CNN) is an information processing system with a large scale nonlinear analog circuit. Setting up a CNN for a particular task needs a proper selection of circuit parameters (cloning template) which determines the dynamics of the network. The present paper provides a methodology, demonstrating the capability of Genetic Algorithms, for aUiomatic selection of cloning temp...

Cellular Neural Networks (CNNs) have been widely used recently in applications such as edge detection, noise reduction and object detection, which are among the main computer imaging processes. They can also be realized as hardware based imaging sensors. The fact that hardware CNN models produce robust and effective results has attracted the attention of researchers using these structures withi...

In this study, a convolutional neural network (CNN) is used to estimate sea ice concentration using synthetic aperture radar (SAR) scenes acquired during freeze-up in the Gulf of St. Lawrence on the east coast of Canada. The ice concentration estimates from the CNN are compared to those from a neural network (multi-layer perceptron or MLP) that uses hand-crafted features as input and a single l...

In this paper, to separate regional-residual anomaly maps and to detect borders of buried geological bodies, we applied the Cellular Neural Network (CNN) approach to gravity and magnetic anomaly maps. CNN is a stochastic image processing technique, based optimization of templates, which imply relationships of neighborhood pixels in 2-Dimensional (2D) potential anomalies. Here, CNN performance i...

In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases). In our model we have presented two methods, namely, convolutional neural network-discrete wavelet (CNN-DW) and convolutional neural network-curvelet transform (CNN-CT). An a...

Centrosomes are major microtubule organising centres comprising a pair of centrioles surrounded by pericentriolar material (PCM). The PCM expands dramatically as cells enter mitosis, and we previously showed that two key PCM components, Centrosomin (Cnn) and Spd-2, cooperate to form a scaffold structure around the centrioles that recruits the mitotic PCM in Drosophila; the SPD-5 and SPD-2 prote...

In this paper, a novel unsupervised competitive learning algorithm, called the centroid neural network adaptive resonance theory (CNN-ART) algorithm, is proposed to relieve the dependence on the initial codewords of the codebook in contrast to the conventional algorithms with vector quantization in lossy image compression. The design of the CNN-ART algorithm is mainly based on the adaptive reso...

This paper presents a texture segmentation algorithm based on Discrete Wavelet Frames(DWF) and Cellular Neural Network(CNN). DWF, zero-crossing, texture energy and selective local averaging are used to get a texture feature extraction and t,o form feature images. Each feature image is segmented into parts by several gray range in its gray histogram. Resulting in the number of pixels that confor...