UMD Theses and Dissertations

Permanent URI for this collectionhttp://hdl.handle.net/1903/3

New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a given thesis/dissertation in DRUM.

More information is available at Theses and Dissertations at University of Maryland Libraries.

Browse

Filters

2006 - 20082

Settings

Subject: search.filters.subject.texture analysis

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    MACHINE VISION TECHNOLOGY FOR FOOD QUALITY AND SAFETY INSPECTIONS
    (2008-10-02) Jin, Fenghua; Tao, Yang; Fischell Department of Bioengineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    With increased expectations for food products of high quality and safety standards, the need for accurate, fast and objective determination of these characteristics in food products continues to grow. Machine vision as a non-destructive technology, provides an automated and economic way to accomplish these requirements. This research thus explored two applications of using machine vision techniques for food quality and safety inspections. The first application is using a combined X-ray and laser range imaging system to detect bone and other physical contaminants inside poultry meat. For this project, our research focuses on how to calibrate the imaging system. A unique three-step calibration method was developed and results showed that high accuracy has been achieved for the whole system calibration - a root mean square error of 0.20 mm, a standard deviation of 0.20 mm, and a maximum error of 0.48 mm. The second application is separating walnuts' shells and meat. A backlight imaging system was developed based on our finding that the backlit images of walnut shells and meat showed quite different texture patterns due to their different light transmittance properties. The texture patterns were characterized by several rotation invariant texture analysis methods. The uncorrelated and redundant features were further removed by a support vector machine (SVM) based recursive feature elimination method, with the SVM classifier trained concurrently for separations of walnuts' shells and meat. The experimental results showed that the proposed approach was very effective and could achieve an overall 99.2% separation accuracy. This high separation accuracy and low instrument cost make the proposed imaging system a great benefit to the walnut processing industry.
  • Thumbnail Image
    Item
    A holistic approach to structure from motion
    (2006-07-23) ji, hui; Aloimonos, Yiannis; Fermuller, Cornelia; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    This dissertation investigates the general structure from motion problem. That is, how to compute in an unconstrained environment 3D scene structure, camera motion and moving objects from video sequences. We present a framework which uses concatenated feed-back loops to overcome the main difficulty in the structure from motion problem: the chicken-and-egg dilemma between scene segmentation and structure recovery. The idea is that we compute structure and motion in stages by gradually computing 3D scene information of increasing complexity and using processes which operate on increasingly large spatial image areas. Within this framework, we developed three modules. First, we introduce a new constraint for the estimation of shape using image features from multiple views. We analyze this constraint and show that noise leads to unavoidable mis-estimation of the shape, which also predicts the erroneous shape perception in human. This insight provides a clear argument for the need for feed-back loops. Second, a novel constraint on shape is developed which allows us to connect multiple frames in the estimation of camera motion by matching only small image patches. Third, we present a texture descriptor for matching areas of extended sizes. The advantage of this texture descriptor, which is based on fractal geometry, lies in its invariance to any smooth mapping (Bi-Lipschitz transform) including changes of viewpoint, illumination and surface distortion. Finally, we apply our framework to the problem of super-resolution imaging. We use the 3D motion estimation together with a novel wavelet-based reconstruction scheme to reconstruct a high-resolution image from a sequence of low-resolution images.