Filters








124 Hits in 8.1 sec

Object recognition algorithm for mobile devices

Rafał Kozik, Adam Marchewka
2013 Image Processing & Communications  
In this paper an object recognition algorithm for mobile devices is presented.  ...  The algorithm is based on a hierarchical approach for visual information coding proposed by Riesenhuber and Poggio [1] and later extended by Serre et al. [2].  ...  The experiments show that the introduced algorithm allows for efficient feature extraction and a visual information coding.  ... 
doi:10.2478/v10248-012-0088-x fatcat:o2rcdf3ujrbh7c5voc2pdez5eu

Research of The Deeper Neural Networks

You Rong Xiao, Qing Xiu Wu, Shu Qing Li, Jun Ou, J.C.M. Kao, W.-P. Sung
2016 MATEC Web of Conferences  
For the initialization, a blockuniform design method is proposed which separates the error surface into some blocks and finds the optimal block using the uniform design method.  ...  With different network structures, many neural models have been constructed. In this report, a deeper neural networks (DNNs) architecture is proposed.  ...  Hubel and Wiesel [1] have researched the cat's visual cortex. It is known that the complex cells belong to visual cortex. The cells are apt to catch the little sub-regions of the visual object.  ... 
doi:10.1051/matecconf/20166305015 fatcat:4b6vlru2pve6nnttuolqffoche

Research on Salient Object Detection using Deep Learning and Segmentation Methods

2019 International journal of recent technology and engineering  
While many models have been proposed and several applications have emerged, yet a deep understanding of achievements and issues is lacking.  ...  Detecting and segmenting salient objects in natural scenes, often referred to as salient object detection has attracted a lot of interest in computer vision and recently various heuristic computational  ...  The other is a bottom-up visual attention model, which is data driven and it relies on image features.  ... 
doi:10.35940/ijrte.b1046.0982s1119 fatcat:6ofq53vb7zhx7boq4ndpraphs4

Neural Encoding for Human Visual Cortex with Deep Neural Networks Learning "What" and "Where" [article]

Haibao Wang, Lijie Huang, Changde Du, Dan Li, Bo Wang, Huiguang He
2019 bioRxiv   pre-print
In the field of visual neuroscience, with the ability to explain how neurons in primary visual cortex work, population receptive field (pRF) models have enjoyed high popularity and made reliable progress  ...  The modeling approach involves two separate aspects: the spatial characteristic ("where") and feature selection ("what") of neuron populations in visual cortex.  ...  The proposed method first 64 extract hierarchical features from the DNN driven for image recognition.  ... 
doi:10.1101/861989 fatcat:ow4llnj4mray5ig2lmjcs5zwnu

State-of-the-art methods in healthcare text classification system AI paradigm

Jasjit S Suri
2020 Frontiers in Bioscience  
Biological neuron model 4. Deep learning 5. Reinforcement learning 6. Feature extraction and selection in ML 6.1. Feature reduction 6.1.1. Filter methods 6.1.2. Wrapper method 6.1.3.  ...  The human brain recognizes the particular object by forming a representational network of neurons from visual cortex and audio cortex.  ...  Basically, neurons are associated with five layers such as primary visual cortex (V1), secondary visual cortex (V2), inferotemporal cortex (IT), posterior and IT-anterior layers.  ... 
doi:10.2741/4826 fatcat:tuzns4dygfetxotjfqpnqgjk7e

Shift-Invariance Sparse Coding for Audio Classification [article]

Roger Grosse, Rajat Raina, Helen Kwong, Andrew Y. Ng
2012 arXiv   pre-print
Originally applied to modeling the human visual cortex, sparse coding has also been shown to be useful for self-taught learning, in which the goal is to solve a supervised classification task given access  ...  In this paper, we present an efficient algorithm for learning SISC bases.  ...  visual cortex, sparse coding has also been training data.  ... 
arXiv:1206.5241v1 fatcat:cfsy7mz65zgc7belm4gblc6qn4

On the use of machine learning for computational imaging

George Barbastathis, Kishan Dholakia, Gabriel C. Spalding
2020 Optical Trapping and Optical Micromanipulation XVII  
Horn, and Lei Tian for helpful discussions and extensive comments on earlier versions of the paper.  ...  Early instances of the idea that sparse representations may instead be learned from examples were motivated by the power spectral density of natural images and analogies with the primate visual cortex  ...  The approach and results are summarized in Fig. 12 . For training, the samples were imaged twice, once with a 40 × 0.95 NA objective lens and again with a Fig. 11 .  ... 
doi:10.1117/12.2571322 fatcat:2rkgbdtgi5foln7ptwqanhncqu

Digital Color Image Compression In A Perceptual Space

Charles F. Hall, Harry C. Andrews, Andrew G. Tescher
1978 Digital Image Processing II  
These models should lead to a fidelity criterion for visual data which matches human subjec tive evaluation of images.  ...  This work was primarily concerned with the efficient coding of images (as we a r e ) .Several subjective evaluation experiments were performed with images which w e r e preprocessed , cod ed , and pos  ...  Contrast sensitivity is defined as the reciprocal of percent threshold modulation (difference between peaks and troug hs) r equired fo r the obse rver to distinguish the stimulus from a uniform field of  ... 
doi:10.1117/12.956684 fatcat:sjgvcsmgbrcwvo62s5hvc335ie

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
Philosophy in Physics is typeset for physical printing and binding.  ...  Highlights include a comprehensive review of deep learning in electron microscopy; large new electron microscopy datasets for machine learning, dataset search engines based on variational autoencoders,  ...  Acknowledgements Thanks go to Jeremy Sloan and Martin Lotz for internally reviewing this article.  ... 
doi:10.5281/zenodo.4598227 fatcat:hm2ksetmsvf37adjjefmmbakvq

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
Philosophy in Physics is typeset for physical printing and binding.  ...  Highlights include a comprehensive review of deep learning in electron microscopy; large new electron microscopy datasets for machine learning, dataset search engines based on variational autoencoders,  ...  Acknowledgements Thanks go to Jeremy Sloan and Martin Lotz for internally reviewing this article.  ... 
doi:10.5281/zenodo.4591029 fatcat:zn2hvfyupvdwlnvsscdgswayci

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
in Physics will be typeset for physical printing and binding.  ...  Highlights include a comprehensive review of deep learning in electron microscopy; large new electron microscopy datasets for machine learning, dataset search engines based on variational autoencoders,  ...  Acknowledgements Thanks go to Jeremy Sloan and Martin Lotz for internally reviewing this article.  ... 
doi:10.5281/zenodo.4399748 fatcat:63ggmnviczg6vlnqugbnrexsgy

Modern Applied Science, Vol. 3, No. 5, May 2009, all in one file, Part B

Editor MAS
2009 Modern Applied Science  
"An architecture of self-organizing map for temporal signal processing and its application to a Braille recognition task" Wiley Periodicals, Inc. Syst Comp Jpn, 38 (3) : 62-71, 2007.  ...  with 2-3 fold decrease in BOD and COD was observed using the bacterial consortium.  ...  Don McNeil, Apiradee Lim, and Phattrawan Tongkumchum for their invaluable assistance, encouragement and helpful guidance.  ... 
doi:10.5539/mas.v3n5p0b fatcat:gutemdaurvcpdcmghp4m3xvz3i

Ranking to Learn and Learning to Rank: On the Role of Ranking in Pattern Recognition Applications [article]

Giorgio Roffo
2017 arXiv   pre-print
The former aims at studying methods and techniques to sort objects for improving the accuracy of a machine learning model. Enhancing a model performance can be challenging at times.  ...  The last decade has seen a revolution in the theory and application of machine learning and pattern recognition.  ...  shown to be very effective for image classi- fication, speech recognition and sequence modeling in the past few years.  ... 
arXiv:1706.05933v1 fatcat:oc4xtmyqkvf4njpqsojewv75qu

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
in Physics will be typeset for physical printing and binding.  ...  Highlights include a comprehensive review of deep learning in electron microscopy; large new electron microscopy datasets for machine learning, dataset search engines based on variational autoencoders,  ...  Acknowledgements Thanks go to Jeremy Sloan and Martin Lotz for internally reviewing this article.  ... 
doi:10.5281/zenodo.4413249 fatcat:35qbhenysfhvza2roihx52afuy

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
in Physics will be typeset for physical printing and binding.  ...  Highlights include a comprehensive review of deep learning in electron microscopy; large new electron microscopy datasets for machine learning, dataset search engines based on variational autoencoders,  ...  Acknowledgements Thanks go to Jeremy Sloan and Martin Lotz for internally reviewing this article.  ... 
doi:10.5281/zenodo.4429792 fatcat:qs6yuapx4vdbdmwna7ix7nnwty
« Previous Showing results 1 — 15 out of 124 results