The field of autonomous robotic systems has advanced tremendously in the last few years, allowing them to perform complicated tasks in various contexts. One of the most important and useful applications of guide robots is the support of the blind. The successful implementation of this study requires a more accurate and powerful self-localization system for guide robots in indoor environments. This paper proposes a self-localization system for guide robots.  To successfully implement this study, images were collected from the perspective of a robot inside a room, and a deep learning system such as a convolutional neural network (CNN) was used. An image-based self-localization guide robot image-classification system delivers a more accura

Image compression is an important tool to reduce the bandwidth and storage
requirements of practical image systems. To reduce the increasing demand of storage
space and transmission time compression techniques are the need of the day. Discrete
time wavelet transforms based image codec using Set Partitioning In Hierarchical
Trees (SPIHT) is implemented in this paper. Mean Square Error (MSE), Peak Signal
to Noise Ratio (PSNR) and Maximum Difference (MD) are used to measure the
picture quality of reconstructed image. MSE and PSNR are the most common picture
quality measures. Different kinds of test images are assessed in this work with
different compression ratios. The results show the high efficiency of SPIHT algori

Image   processing   is  an   important   source   for   the  image

analytical    in   order    to    get   variable    parameters    such   as   the

intensity  .In  present   work  it  has  been  found   a  relation   between the  tensity and  number    of  pixd  in  the  image  ,  and  from  this relation   we  have   got   in  this  paper   the  inten

        The wavelet transform has become a useful computational tool for a variety of signal and image processing applications.

     The aim of this paper is to present the comparative study of various wavelet filters. Eleven different wavelet filters (Haar, Mallat, Symlets, Integer, Conflict, Daubechi 1, Daubechi 2, Daubechi 4, Daubechi 7, Daubechi 12 and Daubechi 20) are used to compress seven true color images of 256x256 as a samples. Image quality, parameters such as peak signal-to-noise ratio (PSNR), normalized mean square error have been used to evaluate the performance of wavelet filters.

   In our work PSNR is used as a measure of accuracy performanc

In this paper two main stages for image classification has been presented. Training stage consists of collecting images of interest, and apply BOVW on these images (features extraction and description using SIFT, and vocabulary generation), while testing stage classifies a new unlabeled image using nearest neighbor classification method for features descriptor. Supervised bag of visual words gives good result that are present clearly in the experimental part where unlabeled images are classified although small number of images are used in the training process.

Its well known that understanding human facial expressions is a key component in understanding emotions and finds broad applications in the field of human-computer interaction (HCI), has been a long-standing issue. In this paper, we shed light on the utilisation of a deep convolutional neural network (DCNN) for facial emotion recognition from videos using the TensorFlow machine-learning library from Google. This work was applied to ten emotions from the Amsterdam Dynamic Facial Expression Set-Bath Intensity Variations (ADFES-BIV) dataset and tested using two datasets.

I n  this  paper ,we 'viii  consider  the density  questions  associC;lted with  the single  hidden layer feed forward  model. We proved  that a FFNN   with   one   hidden   layer  can   uniformly   approximate   any continuous  function  in C(k)(where k is a compact set in R11 ) to any required accuracy.

However, if the set of basis function is dense then the ANN's can has al most one hidden layer. But if the set of basis function  non-dense, then we  need more  hidden layers. Also, we have shown  that there exist  localized functions and that there is no t

The aim of this paper is to design fast neural networks to approximate periodic functions, that is, design a fully connected networks contains links between all nodes in adjacent layers which can speed up the approximation times, reduce approximation failures, and increase possibility of obtaining the globally optimal approximation. We training suggested network by Levenberg-Marquardt training algorithm then speeding suggested networks by choosing most activation function (transfer function) which having a very fast convergence rate for reasonable size networks.             In all algorithms, the gradient of the performance function (energy function) is used to determine how to