Weighted Aspect Moment Invariant in Pattern Recognition
نویسندگان
چکیده
Many drawbacks has been found in Hu’s moment Invariant or known as Geometric Moment Invariant (GMI). Due to its flexibility, GMI is still widely used by the researchers until now. This paper proposes an alternative approach, Weighted Aspect Moment Invariant (WAMI) by combining Weighted Central Moment (WCM) and Aspect Moment Invariant (AsMI) to solve GMI’s drawbacks in term of noise and unequal data scaling. Various insect images are used in this study with two different sizes as simulation images. The simulation results show that the proposed WAMI improves inter-class and intra-class criteria for unequally scaling data compared to AsMI.
منابع مشابه
Embedded Scale United Moment Invariant for Identification of Handwriting Individuality
Past few years, a lot of research on moment functions have been explored in pattern recognition. Several new techniques have been investigated to improve conventional regular moment by proposing the scaling factor of geometrical function. In this paper, integrated scaling formulations of Aspect Invariant Moment and Higher Order Scaling Invariant with United Moment Invariant are presented in Wri...
متن کاملPseudo Zernike Moment-based Multi-frame Super Resolution
The goal of multi-frame Super Resolution (SR) is to fuse multiple Low Resolution (LR) images to produce one High Resolution (HR) image. The major challenge of classic SR approaches is accurate motion estimation between the frames. To handle this challenge, fuzzy motion estimation method has been proposed that replaces value of each pixel using the weighted averaging all its neighboring pixels i...
متن کاملImage Projective Invariants
In this paper, we propose relative projective differential invariants (RPDIs) which are invariant to general projective transformations. By using RPDIs and the structural frame of integral invariant, projective weighted moment invariants (PIs) can be constructed very easily. It is first proved that a kind of projective invariants exists in terms of weighted integration of images, with relative ...
متن کاملAn Integrated Formulation of Zernike Representation in Character Images
Many studies have been done on improving Geometric Moment Invariants proposed by Hu since 1962 for pattern recognition. However, many researchers have found that there are some drawbacks with this geometric moment. Hence, this paper presents an integrated formulation of United Moment and Aspect Moment into Zernike Moment Invariant to seek the invarianceness of the solutions. The proposed method...
متن کاملA Mathematical Walkthrough of Weighted Central Moments and Its Relation to Geometric Moment
Moment invariants are a common approach widely used in pattern recognition. The fashionable invariants are proposed by Hu’s who used central moment to generate seven moment invariants. However, these invariants cause a problem with the existence of data which is concentrated near the center-of-mass since some of them are far away from it. Consequently, these data will be neglected, and the calc...
متن کامل