Article

An Isotropic 3 3 Image Gradient Operator

Presentation at Stanford A.I. Project 1968 02/2014;
12 Bookmarks
 · 
1,609 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The research presented here is an attempt to use a very basic, low cost and non-specialized microcontroller for image processing tasks. The applications emanating from such an attempt will result in inexpensive face detection, intelligent motion sensors to low cost vehicle counting systems. We have been able to develop a system based on Microchip dsPIC microcontroller that implements edge detection of still images. Hardware-based signal processors such as Texas Instrument DSP (Digital Signal Processing) or Field Gate Arrays (FPGA) are generally an expensive solution for image processing applications. On the other hand a conventional 8-bit microcontroller doesn't have enough capability to handle memory intensive DSP algorithms. In this regard, Microchip offers a tradeoff between cost and performance. Although performance does not compete with TI DSPs or FPGAs, the proposed system yet provides a sound platform to perform Signal processing directly on embedded hardware. Our research presents a preliminary approach to perform any type of image processing task using microchip 16-bit Microcontrollers and 16-bit digital signal controllers. Even though this attempt is aimed at Edge Detection, the research opens up possibilities for numerous other algorithms of signal and image processing that can be implemented using the same low cost hardware.
    Information and Automation for Sustainability (ICIAFs), 2010 5th International Conference on; 01/2011
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In recent years, the search for computational systems that classify images based on aesthetic properties has gained momentum. Such systems have a wide range of potential applications, including image search, organization, acquisition and generation. This work explores the use of complexity estimates to predict the aesthetic merit of photographs. We use a set of image metrics and two different classifiers. Our approach classifies images gathered from a photography web site, attempting to reproduce the evaluation made by a group of users. For this purpose, we use complexity estimate metrics based on the encoding size and compression error of JPEG and fractal compression, which are applied to the original value channel and to the images resulting from applying Sobel and Canny filters to this channel. By employing these estimates, in conjunction with the average and standard deviation of the value channel, i.e., 20 features, a success rate of 74.59% was attained. Using the three most influential features yields a success rate of 71.34%, which is competitive with the best results reported in the literature, 71.44%, using the same dataset.
    Journal of Mathematics and the Arts 06/2012; 2-3(6):125-136.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This article presents an edge-corner detector, implemented in the realm of the GEIST project (an Computer Aided Touristic Information System) to extract the information of straight edges and their intersections (image corners) from camera-captured (real world) and computer-generated images (from the database of Historical Monuments, using ob- server position and orientation data). Camera and computer-generated images are processed for reduction of detail, skeletonization and corner-edge detection. The corners surviving the detection and skeletonization process from both images are treated as landmarks and fed to a matching algorithm, which estimates the sampling errors which usually contaminate GPS and pose tracking data (fed to the computer-image generatator).
    Ingeniería y ciencia, ISSN 1794-9165, Nº. 2, 2005, pags. 5-23. 01/2012;

Full-text

View
429 Downloads
Available from
Jun 2, 2014