TITLE

Image Recognition of Occluded Objects Based on Improved Curve Moment Invariants

AUTHOR(S)
Kang Lichun; Lim Kah Bin; Yao Jin
PUB. DATE
June 2009
SOURCE
Journal of Digital Information Management;Jun2009, Vol. 7 Issue 3, p152
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
This paper presents some fundamental knowledge of image recognition of partially occluded objects, and brings forward an improved set of curve moment in variants to recognize occluded objects in images. Occluded objects in an image are not rich in information, while the improved curve moment in variants can represent those objects in a unique way. Therefore, the occluded objects can be efficiently recognized through their shape representation by the set of curve moment in variants as their features. A number of model objects are pre defined in the experiments to build the prior knowledge database for the sake of matching and recognizing unknown objects in future input images. Image pre-processing is employed for both model objects and unknown input objects to obtain their boundary and partition it into subparts. Corner points along the boundary are detected after image pre-processing so that the objects can be described by the curve moment in variants of each subpart. Finally, the matching of curve moment in variants between model object and unknown object is carried on to recognize the unknown object in the input scene image. The results of experiments show that this method is robust and efficient to recognize partially occluded objects in 2D images; furthermore, the invariance to the affine transformation of objects in images are also proved in the paper.
ACCESSION #
43893729

 

Related Articles

  • On Symmetry and Multiple-View Geometry: Structure, Pose, and Calibration from a Single Image. Wei Hong; Allen Yang Yang; Kun Huang; Yi Ma // International Journal of Computer Vision;Dec2004, Vol. 60 Issue 3, p241 

    In this paper, we provide a principled explanation of how knowledge in global 3-D structural invariants, typically captured by a group action on a symmetric structure, can dramatically facilitate the task of reconstructing a 3-D scene from one or more images. More importantly, since every...

  • COLOR CONSTANT DESCRIPTORS COMBINING IMAGE DERIVATIVE STRUCTURES. Hong BAO; De XU; Bing LI // Computing & Informatics;2012, Vol. 31 Issue 5, p971 

    Color constant image description is a fundamental problem in many computer vision applications. In this paper, the diagonal-offset model is adopted as reflectance model to get color constant image descriptors. This model makes the descriptors much more robust, and also fits the real world images...

  • A Combined Approach for Face Detection. Priscilla, C.Victoria; Poorna, B. // International Journal of Computer Applications;2013, Vol. 62, p14 

    This paper aims to detect the face in the digital image with the combination of morphological operations, Local Binary Pattern descriptor and with the moment invariants. In the digital image, the detection of face has gained much importance in the last decade, with enormous applications in the...

  • Gradient-based shape descriptors. �apar, Abdulkerim; Kurt, Binnur; G�kmen, Muhittin // Machine Vision & Applications;Dec2009, Vol. 20 Issue 6, p365 

    This paper presents two shape descriptors which could be applied to both binary and grayscale images. The proposed algorithm utilizes gradient based features which are extracted along the object boundaries. We use two-dimensional steerable G-Filters (IEEE Trans Pattern Anal Mach Intell...

  • SEAMLESS IMAGE-PAGE ALIGNMENT AND RECTANGULAR AREAS REMOVAL. BOIANGIU, Costin-Anton; SPATARU, Andrei-Cristian; PETRESCU, Serban; MOLDOVEANU, Alin // Annals of DAAAM & Proceedings;Jan2009, p329 

    This paper describes an algorithm aimed at correcting visual elements in image pages, both for preprocessing and further reference purposes. The correction scenarios are a consequence of either unacceptable amounts of noise in portions of the image-page, or the need to standardize the image-page...

  • Cutting Affine Moment Invariants. Jianwei Yang; Ming Li; Zirun Chen; Yunjie Chen // Mathematical Problems in Engineering;2012, Vol. 2012, Special section p1 

    The extraction of affine invariant features plays an important role in many fields of image processing. In this paper, the original image is transformed into new images to extract more affine invariant features. To construct new images, the original image is cut in two areas by a closed...

  • Guest Editors' Introduction: Image Databases. Iyengar, S. Sitharama; Kashyap, Rangasami L. // IEEE Transactions on Software Engineering;May88, Vol. 14 Issue 5, p608 

    There has been a tremendous spurt in research and activity in image processing techniques and applications. This has been a productive endeavor in that it has revolutionized the state and art of technology in several diverse areas such as medical diagnostics, tactical sensing for defense...

  • Accurate Orthogonal Circular Moment Invariants of Gray-Level Images. Hosny, Khalid Mohamed // Journal of Computer Science;2011, Vol. 7 Issue 5, p715 

    Problem statement: Orthogonal circular moments of gray level images such as Zernike, pseudo Zernike and Fourier-Mellin moments are widely used in different applications of image processing, pattern recognition and computer vision. Computational processes of these moments and their translation...

  • Optimized Set of RST Moment Invariants. Hosny, Khalid M. // American Journal of Applied Sciences;2008, Vol. 5 Issue 6, p726 

    Moment invariants are widely used in image processing, pattern recognition and computer vision. Several methods and algorithms have been proposed for fast and efficient calculation of moment's invariants where numerical approximation errors are involved in most of these methods. In this paper,...

  • Invariant Hough Random Ferns for Object Detection and Tracking. Yimin Lin; Naiguang Lu; Xiaoping Lou; Fang Zou; Yanbin Yao; Zhaocai Du // Mathematical Problems in Engineering;2014, p1 

    This paper introduces an invariant Hough random ferns (IHRF) incorporating rotation and scale invariance into the local feature description, random ferns classifier training, and Hough voting stages. It is especially suited for object detection under changes in object appearance and scale,...

Share

Read the Article

Courtesy of VIRGINIA BEACH PUBLIC LIBRARY AND SYSTEM

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics