Wyniki wyszukiwania - BazTech

1

A novel method for invariant image reconstruction

Pawlak Mirosław, Panesar Gurmukh Singh, Korytkowski Marcin

Journal of Artificial Intelligence and Soft Computing Research

|

2021

|

Vol. 11, No. 1

69--80

EN

In this paper we propose a novel method for invariant image reconstruction with the properly selected degree of symmetry. We make use of Zernike radial moments to represent an image due to their invariance properties to isometry transformations and the ability to uniquely represent the salient features of the image. The regularized ridge regression estimation strategy under symmetry constraints for estimating Zernike moments is proposed. This extended regularization problem allows us to enforces the bilateral symmetry in the reconstructed object. This is achieved by the proper choice of two regularization parameters controlling the level of reconstruction accuracy and the acceptable degree of symmetry. As a byproduct of our studies we propose an algorithm for estimating an angle of the symmetry axis which in turn is used to determine the possible asymmetry present in the image. The proposed image recovery under the symmetry constraints model is tested in a number of experiments involving image reconstruction and symmetry estimation.

2

A bio-inspired integration method for object semantic representation

Wei H.

Journal of Artificial Intelligence and Soft Computing Research

|

2016

|

Vol. 6, No. 3

137--154

EN

We have two motivations. Firstly, semantic gap is a tough problem puzzling almost all sub-fields of Artificial Intelligence. We think semantic gap is the conflict between the abstractness of high-level symbolic definition and the details, diversities of low-level stimulus. Secondly, in object recognition, a pre-defined prototype of object is crucial and indispensable for bi-directional perception processing. On the one hand this prototype was learned from perceptional experience, and on the other hand it should be able to guide future downward processing. Human can do this very well, so physiological mechanism is simulated here. We utilize a mechanism of classical and non-classical receptive field (nCRF) to design a hierarchical model and form a multi-layer prototype of an object. This also is a realistic definition of concept, and a representation of denoting semantic. We regard this model as the most fundamental infrastructure that can ground semantics. Here a AND-OR tree is constructed to record prototypes of a concept, in which either raw data at low-level or symbol at high-level is feasible, and explicit production rules are also available. For the sake of pixel processing, knowledge should be represented in a data form; for the sake of scene reasoning, knowledge should be represented in a symbolic form. The physiological mechanism happens to be the bridge that can join them together seamlessly. This provides a possibility for finding a solution to semantic gap problem, and prevents discontinuity in low-order structures.

3

Methods for generating 3D exact views of convex polyhedra for visual identification. Part 2, Non-interative methods, implementation and test results

Kowalczyk M., Mokrzycki W.

Machine Graphics and Vision

|

2003

|

Vol. 12, No. 4

435-452

EN

This paper is the second part of our study describing methods for obtaining a 3D multiview exact and complete model of convex polyhedra used for visual identification. Non-iterative methods, like the iterative ones, explore the concept of the view sphere with perspective projection and the view sphere covering as a mechanism for representation completeness. The non-iterative methods consist in calculating a view, determining the corresponding single-view area (the so-called seedling single-view area) and then searching for the neighbouring single-view areas (generating the views at the same time) in a spiral way until the whole view sphere is covered by the latter. Having a complete set of the single-view areas (complete view sphere covering), we get a complete set of views as well. Test results and computational complexity estimation are also included.

4

Methods for generating 3D exact views of convex polyhedra for visual identification. Part 1, View sphere with perspective projection and interative methods

Kowalczyk M., Mokrzycki W.

Machine Graphics and Vision

|

2003

|

Vol. 12, No. 4

409-433

EN

The paper studies the methods of generating 3D exact multiview models of convex polyhedra for visual identification systems. In particular, an original view space concept (a view sphere with perspective projection) and the representation completeness controlling concept (a view sphere covering by single-view areas) as well as two groups of methods: iterative (part I of the paper) and non-iterative ones (part II) are characterized. A set of views generated by each method forms a complete view representation which is verified by controlling the view sphere covering by the so called single-view areas). The perspective projection used for calculating the views, the complete, tight covering of the view sphere by the single-view areas and 3-dimensionality of the views ensure unambiguous and proper identification of polyhedral objects. Part I of our study presents the view sphere with perspective projection concept, the view sphere covering by the single-view areas mechanism, and the iterative methods generating feature-dependent views and reaching a complete view set through an iterative process of views generation.