Generalized affine moment invariants for object recognition
نویسندگان
چکیده
This paper introduces a new way of extracting affine invariant features from image functions. The presented approach is based on combining affine moment invariants (AMI) with multiscale invariants, in particular multiscale autoconvolution (MSA) and spatial multiscale affine invariants (SMA). Our approach includes all of these invariants as special cases, but also makes it possible to construct new ones. According to the performed experiments the introduced features provide discriminating information for affine invariant object classification, clearly outperforming standard AMI, MSA, and SMA.
منابع مشابه
3D Object Recognition Using Multiple Views, Affine Moment Invariants and Multilayered Perceptron Network
This paper addresses a performance analysis of affine moment invariants for 3D object recognition. Affine moment invariants are commonly used as shape feature for 2D object or pattern recognition. The current study proved that with some adaptation to multiple views technique, affine moments are sufficient to model 3D objects. In addition, the simplicity of moments calculation reduces the proces...
متن کاملGeneralized affine moment invariants for object recogntion
This paper introduces a new way of extracting affine invariant features from image functions. The presented approach is based on combining affine moment invariants (AMI) with multiscale invariants, in particular multiscale autoconvolution (MSA) and spatial multiscale affine invariants (SMA). Our approach includes all of these invariants as special cases, but also makes it possible to construct ...
متن کاملMoment Invariants in Image Analysis
This paper aims to present a survey of object recognition/classification methods based on image moments. We review various types of moments (geometric moments, complex moments) and moment-based invariants with respect to various image degradations and distortions (rotation, scaling, affine transform, image blurring, etc.) which can be used as shape descriptors for classification. We explain a g...
متن کاملLearning Affine Invariant Pattern Recognition Using High-Order Neural Networks
In this work, high order neural networks have been successfully used to recognize affine transformed images. Affine invariants are important features used to classify images of objects deteriorated by affine transformations. The dataset used in training and testing contains two classes, the star image and the wave image. The proposed high order neural network is inspired from the system of affi...
متن کاملObject Recognition by Implicit Invariants
The use of traditional moment invariants is limited to a certain set of simple geometric transforms, such as rotation, scaling and affine transform. This paper presents a novel concept of so-called implicit moment invariants, which enable us to recognize objects under a broader set of geometric deformations.
متن کامل