فهرس المقالات Super resolution

• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  1 - Depth Image Resolution Enhancement Using Discrete Wavelet Transform and Convolution Neural Networks
  Mohsen Ashourian Seyed Mehrdad Mahdavi
  10.52547/mjtd.10.1.9
  The depth image plays an increasingly important role in fundamental research and daily applications, with the reducing the price and increasing the number of affordable and portable depth cameras. Infrared sensors or depth sensors are widely used to control dynamic and أکثر

  The depth image plays an increasingly important role in fundamental research and daily applications, with the reducing the price and increasing the number of affordable and portable depth cameras. Infrared sensors or depth sensors are widely used to control dynamic and static 3D scenes. However, the depth image quality is limited to low-quality images, as the infrared sensor does not have high resolution. Therefore, given the problems and the importance of using 3-D images, the quality of these images should be improved in order to provide accurate images from depth cameras. In this paper a resolution enhancement method of depth images using convolutional neural networks is considered. A convolutional neural network with a depth of 20 and three layers and a pre-trained neural network is used. We developed the system and tested its performance for two datasets, Middlebury and EURECOM Kinect Face. Results show for EURECOM Kinect Face images, PSNR improvement is approximately 7 to 16 dB and for Middlebury images the PSNR improvement is about 6 to 12 dB. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  2 - Evaluation of super-resolution algorithm for detection and recognition of features from MODIS and OLI images at sub-pixel scale using Hopfield Neural Network
  Mohammad Hosein Mehrzade Abarghooee Ali Sarkargar Ardakani
  Fuzzy classification techniques have been developed recently to estimate the classcomposition of image pixels, but their output provides no indication of how theseclasses are distributed spatially within the instantaneous field of view represented bythe pixel. Super-res أکثر

  Fuzzy classification techniques have been developed recently to estimate the classcomposition of image pixels, but their output provides no indication of how theseclasses are distributed spatially within the instantaneous field of view represented bythe pixel. Super-resolution land-cover mapping is a promising technology forprediction of the spatial distribution of each land-cover class at the sub-pixel scale.This distribution is often determined based on the principle of spatial dependence andfrom land-cover fraction images derived with soft classification technology. As such,while the accuracy of land cover target identification has been improved using fuzzyclassification, it remains for robust techniques that provide better spatial representationof land cover to be developed. An approach was adopted that used the output from afuzzy classification to constrain a Hopfield neural network formulated as an energyminimization tool. The network converges to a minimum of an energy function. Thisenergy minimum represents a “best guess” map of the spatial distribution of classcomponents in each pixel. The technique was applied to remote sensing imagery(MODIS & OLI images), and the resultant maps provided an accurate and improvedrepresentation of the land covers. Low RMSE, high accuracy. By using a Hopfieldneural network, more accurate measures of land cover targets can be obtained, The Hopfield neural network used in this way represents a simple, robust, and efficienttechnique, and results suggest that it is a useful tool for identifying land cover targetsfrom remotely sensed imagery at the sub-pixel scale. The present research purpose wasevaluation of HNN algorithm efficiency for different land covers (Land, Water,Agriculture land and Vegetation) through Area Error Proportion, RMSE andCorrelation coefficient parameters on MODIS & OLI images and related ranking,results of present super resolution algorithm has shown that according to precedence,most improvement in feature’s recognition happened for Water, Land, Agricultureland and ad last Vegetation with RMSEs 0.044, 0.072, 0.1 and 0.108. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  3 - Pseudo Zernike Moment-based Multi-frame Super Resolution
  Sara Salkhordeh Hamidreza Rashidy Kanan
  The goal of multi-frame Super Resolution (SR) is to fuse multiple Low Resolution (LR) images to produce one High Resolution (HR) image. The major challenge of classic SR approaches is accurate motion estimation between the frames. To handle this challenge, fuzzy motion أکثر

  The goal of multi-frame Super Resolution (SR) is to fuse multiple Low Resolution (LR) images to produce one High Resolution (HR) image. The major challenge of classic SR approaches is accurate motion estimation between the frames. To handle this challenge, fuzzy motion estimation method has been proposed that replaces value of each pixel using the weighted averaging all its neighboring pixels in all LR images which carries the degree of similarity between image blocks centered on two pixels. Since in case of rotation between LR images, comparing the gray level of blocks around the pixels is not a suitable criterion for calculating weight, so, magnitude of Zernike Moments (ZM) has been used as a rotation invariant feature. Due to the lower sensitivity of Pseudo Zernike Moments (PZM) to noise and the higher discrimination capability of it for the same order compared to ZM, in this paper, we propose a new method based on magnitude of PZM of the blocks as a rotation invariant descriptor for representation of pixels in weight calculation. Experimental results on several image sequences show that the performance of the proposed algorithm is better than the existing and new techniques from the aspect of PSNR and visual image quality. تفاصيل المقالة