Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Author: search.filters.author.Peddigari, V.Subject: search.filters.subject.Image Processing

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Reflection removal in smart devices using a prior assisted independent components analysis
    (SPIE spie@spie.org, 2015) Kalwad, P.; Prakash, D.; Peddigari, V.; Srinivasa, P.
    When photographs are taken through a glass or any other semi-reflecting transparent surface, in museums, shops, aquariums etc., we encounter undesired reflection. Reflection Removal is an ill-posed problem and is caused by superposition of two layers namely the scene in front of camera and the scene behind the camera getting reflected because of the semi-reflective surface. Modern day hand held Smart Devices (smartphones, tablets, phablets, etc) are typically used for capturing scenes as they are equipped with good camera sensors and processing capabilities and we can expect image quality to be similar to a professional camera. In this direction, we propose a novel method to reduce reflection in images, which is an extension of Independent Component Analysis (ICA) approach, by making use of two cameras present - a back camera (capturing actual scene) and a front facing camera. When compared to the original ICA implementation, our method gives on an average of 10% improvement on the peak signal to noise ratio of the image. © 2015 SPIE-IS&T.
  • No Thumbnail Available
    Item
    Automatic reflection removal using reflective layer image information
    (Institute of Electrical and Electronics Engineers Inc., 2015) Prakash, D.; Kalwad, P.S.; Peddigari, V.; Srinivasa, P.
    This paper tries to address the problem of removing unwanted reflection layer from the image mixtures. These reflections may occur due to semi-reflective glass mediums. This demands separating the input image into the reflecting layer and the subject layer, also known as, background layer which is the actual scene itself. But decomposing a single input image into these two layers is a massively ill-posed problem with infinite combinations of decomposition. This type of problem falls under the category of blind source separation. There are ample classical separation approaches available in the literature which either requires multiple images or works on a single image with user assistance. In this paper we propose a method for separating the two layers from a single input image without any user or human intervention using some prior information about the reflective layer. © 2015 IEEE.