Type

Type

Sort by: Order: Results:

  • Patil, Akshay Gadi; Raman, Shanmuganathan (Cornell University Library, 2016-04)
    Non-photorealistic rendering techniques work on image features and often manipulate a set of characteristics such as edges and texture to achieve a desired depiction of the scene. Most computational photography methods ...
  • Malireddi, Sri Raghu; Raman, Shanmuganathan (Cornell University Library, 2016-04)
    Automatic segmentation of objects from a single image is a challenging problem which generally requires training on large number of images. We consider the problem of automatically segmenting only the dynamic objects from ...
  • Chavan, Tanmay; Dutta, Sangya; Mohapatra, Nihar Ranjan; Ganguly, Udayan (Cornell University Library, 2019-02)
    The human brain comprises about a hundred billion neurons connected through quadrillion synapses. Spiking Neural Networks (SNNs) take inspiration from the brain to model complex cognitive and learning tasks. Neuromorphic ...
  • Rajpura, Param; Goyal, Manik; Hegde, Ravi S.; Bojinov, Hristo (Cornell University Library, 2017-09)
    Although Deep Convolutional Neural Networks trained with strong pixel-level annotations have significantly pushed the performance in semantic segmentation, annotation efforts required for the creation of training data ...
  • Salvi, Govind; Sharma, Puneet; Raman, Shanmuganathan (Cornell University Library, 2013-05)
    Most of the real world scenes have a very high dynamic range (HDR). The mobile phone cameras and the digital cameras available in markets are limited in their capability in both the range and spatial resolution. Same ...
  • Kanojia, Gagan; Kumawat, Sudhakar; Raman, Shanmuganathan (Cornell University Library, 2019-09)
    Traditional 3D convolutions are computationally expensive, memory intensive, and due to large number of parameters, they often tend to overfit. On the other hand, 2D CNNs are less computationally expensive and less memory ...
  • Joshi, Sharad; Saxena, Suraj; Khanna, Nitin (Cornell University Library, 2018-08)
    Knowledge of source smartphone corresponding to a document image can be helpful in a variety of applications including copyright infringement, ownership attribution, leak identification and usage restriction. In this letter, ...
  • Mastan, Indra Deep; Raman, Shanmuganathan (Cornell University Library, 2019-05)
    Many real-world solutions for image restoration are learning-free and based on handcrafted image priors such as self-similarity. Recently, deep-learning methods that use training data have achieved state-of-the-art results ...
  • Joshi, Sharad; Khanna, Nitin (Cornell University Library, 2018-06)
    The knowledge of source printer can help in printed text document authentication, copyright ownership, and provide important clues about the author of a fraudulent document along with his/her potential means and motives. ...
  • Nagar, Rajendra; Raman, Shanmuganathan (Cornell University Library, 2018-05)
    Over-segmentation of an image into superpixels has become a useful tool for solving various problems in image processing and computer vision. Reflection symmetry is quite prevalent in both natural and man-made objects and ...
  • Raman, Shanmuganathan; Pachori, Shubham (Cornell University Library, 2016-10)
    This paper provides a framework to hash images containing instances of unknown object classes. In many object recognition problems, we might have access to huge amount of data. It may so happen that even this huge data ...

Search Digital Repository


Browse

My Account