http:^^www.cs.wisc.edu^~dyer^cs766^proj.html
来自「This data set contains WWW-pages collect」· HTML 代码 · 共 310 行 · 第 1/2 页
HTML
310 行
Date: Mon, 11 Nov 1996 17:30:37 GMTServer: NCSA/1.5Content-type: text/htmlLast-modified: Wed, 20 Dec 1995 15:24:37 GMTContent-length: 15487<HTML><HEAD><TITLE>CS 766 Student Projects</TITLE></HEAD><BODY><H2>CS 766 Student Projects</H2><BR><UL><HR SIZE=5><LI><B>Chris Baum</B><BR><I>Image Warping</I><P>A two-pass algorithm for digital image warping is implemented and tested on high quality color images (640 x 480). Input parameters to the algorithm are the source and destination images, and the source and destination meshes. An X-windows widget interface is used to display a pair of images for reference to input the input and outputmeshes. The mesh is interpolated to the size of the images (cubic spline is used in this case). The second step would be to usethis routine to align images for mosaic splining.<HR SIZE=5><LI><B>Todd Bezenek</B> and <B>Yinong Wei</B><BR><I>A Spherical Mosaic System</I><P>An image mosaic is a conglomeration of overlapping images in which theimages fit together so well that their combination is indistinguishablefrom a single, large image of the same subject. Many efforts have beenexpended to create mosaics with various properties. In this project, weintend to develop a mosaic that allows the user to view an entire threedimensional space (in any one direction at a time) in which his positionis fixed at the center.<HR SIZE=5><LI><B>Jon Bodner</B><BR><I>Hand Gesture Histogram Recognition -- Analysis and Improvement</I><P>My project is based on the paper "Orientation Histograms for Hand Gesture Recognition" by W. Freeman and M. Roth. This paper describes a simple algorithm to analyze grey-scale images of hands and recognize the gesture. Their definition of gesture is static; it refers to the gross hand orientation at a given time. The algorithm used in the paper is rotation dependent, but it is lighting invariant.<P>For the first part of my project, I intend to implement the Freeman and Roth algorithm and try it out with several sample images I generate. The images will be taken in different lighting to mirror the tests performed by Freeman and Roth.<P>After testing out the correctness of my implementation, I intend to test the limits of the algorithm in two areas: rotation sensitivity and lighting sensitivity. In particular, I want to explore the limits on lighting insensitivity and depth of the limitation on rotations.<P>Lighting insensitivity is one of the strongest features of this algorithm. There is no exact quantification given in the paper; it only presents two different lighting levels. If possible, I would like to measure the ambient light with a light meter and determine the range in which the algorithm performs best.<P>Testing the limits of rotation is a little harder. Gestures, by their nature are not rotation invariant. However, humans use a fuzzy range to match a given hand signal. It is not clear how wide the recognition range is for Freeman and Roth's algorithm, especially with similar gestures.<P>Once the range is determined, I would like to implement a fuzzy function which is used to do the matching between the training sets and the gestures to be recognized. I will then compare the results of this modified version to the results of the original.<HR SIZE=5><LI><B>Yanming Cao</B><BR><I>Hand Gesture Recognition</I><P>I will implement Freeman's method for hand gesture recognition as described in thepaper "Orientation Histograms for Hand Gesture Recognition," by W. Freeman and M. Roth, from <I>Proc. Int. Workshop on Automatic Faceand Gesture Recognition</I>, 1995.The algorithm, claimed by the authors simple and fast, uses the histogram oflocal orientation as a feature vector for gesture classification andinterpolation. It is relatively robust to changes in lighting.<HR SIZE=5><LI><B>Nirupama Chandrasekaran</B> and <B>Jamie Jason</B><BR><I>Mosaic Construction using Gaussian Pyramids</I><P>The goal of image mosaics is to take a collection of images andcombine their information in such a way as to obtain a single image.During the early stages of this process, images must be registered todetermine correlation between them. This registration can be a ratherexpensive and time-consuming process for a class of transformationsthat include both 2D translation and rotation. In this project weplan to investigate coarse-to-fine image registration usingGaussian pyramids.<P>In our project, the first step in image registration is to buildGaussian pyramids for the two images we wish to register. Currentlywe are proposing that the top of the pyramid be an image that isapproximately 16-by-16 pixels. Once we have the Gaussian pyramids wecan begin registering at the coarsest level. We will then use theregistration information from a higher level (i.e., coarser) as a hintto the next lower level (i.e., finer). This hint will be used toreduce the search space to the 8-neighbors of the corresponding pixelin the next lower level.<HR SIZE=5><LI><B>Beth Cole</B><BR><I>Hough Transform Variations for the Detection of Circles and Ellipses</I><P>My project will consist of a paper on Hough transforms. The paper willbegin with a brief introduction to what Hough transforms are followed bya short survey of the uses, advantages and disadvantages of the method.The second section will introduce a variety of variations on andimprovements to the original conception. The third section will examinesome of these variations with respect to the particular task of identifyingcircles and ellipses as well as additional variations that are particularto the task of identifying circles and ellipses. In conclusion acomparison of the suggested methods will be made with suggestions forpossible further work.<HR SIZE=5><LI><B>Joshua Conner</B><BR><I>Shape Recognition through Machine Learning</I><P>This project will attempt to move further up the vision hierarchy by combining features into simple concepts. I will train a neural networkusing simple features such as number of corners and edge lengths, and then determine its ability to classify images into shapes. Success of the system will be measured in terms of generality of shape which canbe identified as well as by robustness over a range of inputs.<HR SIZE=5><LI><B>Jonathan Goldstein</B> and <B>Marc Shapiro</B><BR><I>Finding Overlapping Simple 2D Shapes using a Really Generalized Hough Transform</I><P>The goal of this project is to develop and implement an algorithm to decomposean image into a set of overlapping 2D shapes. For instance, we can choosecircles and rectangles with constant gray levels as primitives. Each circle inthe decomposed image would be characterized by four parameters: center coordinates (x, y), radius r, and gray level g. A rectangle would have fiveparameters: lower left corner coordinates (x, y), width w, height h, and gray level g. The output of the algorithm is an "in-front-of graph", a partialordering of the shapes found in the image. The result is a compactapproximation of the image as overlapping shapes.<HR SIZE=5><LI><B>Gil Gribb</B><BR><I>What Ever You Need From What Ever Works: Data-Driven Approaches to Intermediate-Level Vision</I>⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?