ON GEOMETRIC AND ORTHOGONAL MOMENTS

2000 ◽  
Vol 14 (07) ◽  
pp. 875-894 ◽  
Author(s):  
JUN SHEN ◽  
WEI SHEN ◽  
DANFEI SHEN
Keyword(s):  
Pattern Analysis ◽  
Equivalence Theorem ◽  
Image Features ◽  
Shape Classification ◽  
Orthogonal Moments ◽  
Zero Crossings ◽  
Different Types ◽  
Base Functions ◽  
Different Shapes ◽  
Function Discontinuity

Moments are widely used in pattern recognition, image processing, computer vision and multiresolution analysis. To clarify and to guide the use of different types of moments, we present in this paper a study on the different moments and compare their behavior. After an introduction to geometric, Legendre, Hermite and Gaussian–Hermite moments and their calculation, we analyze at first their behavior in spatial domain. Our analysis shows orthogonal moment base functions of different orders having different number of zero-crossings and very different shapes, therefore they can better separate image features based on different modes, which is very interesting for pattern analysis and shape classification. Moreover, Gaussian–Hermite moment base functions are much more smoothed, they are thus less sensitive to noise and avoid the artifacts introduced by window function discontinuity. We then analyze the spectral behavior of moments in frequency domain. Theoretical and numerical analyses show that orthogonal Legendre and Gaussian–Hermite moments of different orders separate different frequency bands more effectively. It is also shown that Gaussian–Hermite moments present an approach to construct orthogonal features from the results of wavelet analysis. The orthogonality equivalence theorem is also presented. Our analysis is confirmed by numerical results, which are then reported.

scholarly journals Research on a Rice Counting Algorithm Based on an Improved MCNN and a Density Map

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 721
Author(s):  
Ao Feng ◽  
Hongxiang Li ◽  
Zixi Liu ◽  
Yuanjiang Luo ◽  
Haibo Pu ◽  
...  
Keyword(s):  
Grain Weight ◽  
Gaussian Kernel ◽  
Density Level ◽  
Thousand Grain Weight ◽  
Original Algorithm ◽  
Different Types ◽  
Different Shapes ◽  
Density Map ◽  
Important Basis ◽  
Adhesion Condition

The thousand grain weight is an index of size, fullness and quality in crop seed detection and is an important basis for field yield prediction. To detect the thousand grain weight of rice requires the accurate counting of rice. We collected a total of 5670 images of three different types of rice seeds with different qualities to construct a model. Considering the different shapes of different types of rice, this study used an adaptive Gaussian kernel to convolve with the rice coordinate function to obtain a more accurate density map, which was used as an important basis for determining the results of subsequent experiments. A Multi-Column Convolutional Neural Network was used to extract the features of different sizes of rice, and the features were fused by the fusion network to learn the mapping relationship from the original map features to the density map features. An advanced prior step was added to the original algorithm to estimate the density level of the image, which weakened the effect of the rice adhesion condition on the counting results. Extensive comparison experiments show that the proposed method is more accurate than the original MCNN algorithm.

A new class of isotropic generators for developing 6-DOF isotropic manipulators

Robotica ◽  
2008 ◽  
Vol 26 (5) ◽  
pp. 619-625 ◽  
Author(s):  
K. Y. Tsai ◽  
T. K. Lee ◽  
Y. S. Jang
Keyword(s):  
Reference Point ◽  
Parallel Manipulators ◽  
Geometric Constraint ◽  
Kinematic Chains ◽  
New Class ◽  
New Methods ◽  
Center Point ◽  
Different Types ◽  
Different Shapes ◽  
Straight Lines

SUMMARYDeveloping 6-DOF isotropic manipulators using isotropic generators is simple and efficient, and isotropic generators can be employed to develop serial, redundant, or parallel isotropic manipulators. An isotropic generator consists of a reference point and six straight lines. The existing generators, however, have one common geometric constraint: the reference point is equidistant from the six straight lines. Some practical isotropic designs might not be obtained due to this constraint. This paper proposes methods for developing new isotropic generators. The generators thus developed are not subject to the constraint, and the new methods allow us to specify the location of the tool center point, the size of the platform or the base, or the shape of isotropic parallel manipulators. Many new generators are presented to develop 6-DOF parallel manipulators with different shapes or different types of kinematic chains.

Image Processing and Artificial Neural Network for Robot Application

2014 ◽  
Vol 658 ◽  
pp. 678-683 ◽  
Author(s):  
Cristian Pop ◽  
Sanda Margareta Grigorescu ◽  
Erwin Christian Lovasz
Keyword(s):  
Neural Network ◽  
Robot Vision ◽  
Working Environment ◽  
Shape Classification ◽  
Input And Output ◽  
Different Types ◽  
Object Sorting ◽  
Feature Based ◽  
Position And Orientation ◽  
Vision Application

This paper presents a robot vision application, implemented in MATLAB working environment, developed for feature-based object recognition, object sorting and manipulation, based on shape classification and its pose calculus for proper positioning. The application described in this article, designed to detect, identify, classify and manipulate objects is based on previous robot vision applications that are presented in more detail in [1]. The idea underlying the mentioned applications is to determine the type, position and orientation of the work pieces (in those cases different types of bearings). Taking it further, in the presented application, objects that show shape with a gradual level of complexity are used. For this reason pattern recognition are discriminated by training a two layers neural network. The network is presented and also the input and output vectors.

New concept for art and antiquities identification based on craquelure pattern analysis

2020 ◽  
Vol 62 (3) ◽  
pp. 134-138
Author(s):  
R GR Maev ◽  
A Baradarani ◽  
J R B Taylor
Keyword(s):  
Pattern Analysis ◽  
Morphological Processing ◽  
Health Conditions ◽  
Photographic Images ◽  
Multi Scale ◽  
Perspective Distortion ◽  
Art Objects ◽  
Image Dataset ◽  
Different Types ◽  
Matching Procedure

In this paper, it is shown that the craquelure patterns of paintings and other antiquities can be considered as fingerprints so that the authenticity of any given artwork can then be verified against prior works. The authors propose to extract craquelure features from photographic images and use them in the implementation of a unique matching procedure to address the art forgery issue as well as to monitor the health conditions of the objects concerned. This feature extraction strategy is robust against illumination, scale, rotation and perspective distortion. The craquelure extraction system developed, called multi-scale multi-orientation morphological processing (MMMP), performs analyses in each sub-band. A comprehensive craquelure image dataset has been constructed from a variety of different types of painting and other art objects. The results show significant improvement and compare favourably with the current best results in the market.

scholarly journals Vibration Pattern Related to Transverse Cracks in Rotors

2002 ◽  
Vol 9 (4-5) ◽  
pp. 217-224 ◽  
Author(s):  
Nicolò Bachschmid ◽  
Ezio Tanzi
Keyword(s):  
Thermal Effects ◽  
Transverse Cracks ◽  
Vibration Excitation ◽  
Different Types ◽  
Vibration Pattern ◽  
Rotating Shafts ◽  
Different Shapes

A method for calculating the breathing behavior of transverse cracks of different types in rotating shafts is described. Thermal effects are included. Some results in terms of vibration excitation related to different shapes of cracks are presented.

scholarly journals A Method of Objects Classification Based on Learning and Visual Perception

2018 ◽  
Vol 36 (2) ◽  
pp. 359-367
Author(s):  
Na Li ◽  
Xinbo Zhao ◽  
Yongjia Yang ◽  
Xiaochun Zou
Keyword(s):  
Eye Tracking ◽  
Visual Saliency ◽  
Image Features ◽  
Classification Method ◽  
Attention Model ◽  
Whole Process ◽  
Visual Behaviors ◽  
Different Types ◽  
Visual Saliency Model ◽  
High Level

Objects classification is one of the most significant problems in computer vision. For improving the accuracy of objects classification, we put forward a new classification method enlightened the whole process that human distinguish different types of objects. Our method mixed visual saliency model and CNN, is more close to human and has apparently biological advantages. Firstly, we built an eye-tracking database to learn people visual behaviors when they classify various objects and recorded the eye-tracking data. Secondly, this database is used to train a learning-based visual attention model, which is based on low-level (e.g., orientation, color, intensity, etc.) and high-level (e.g., faces, people, cars, etc.) image features to analyze and predict the human's classification RoIs. Finally, we established a CNN framework to classify RoIs. The results of the experiment showed our attention model can determine saliency regions and predict human's classification RoIs more precisely and our classification method improved the efficiency of classification markedly.

scholarly journals Better to Explain or to Testify? The Position of the Accused as a Source of Oral Evidence in a Criminal Trial in a Comparative Perspective

2021 ◽  
Vol 27 ◽  
pp. 47-77
Author(s):  
Hanna Kuczyńska
Keyword(s):  
Common Law ◽  
Criminal Trial ◽  
Comparative Perspective ◽  
Legal Systems ◽  
Anglo Saxon ◽  
Present Evidence ◽  
Different Types ◽  
Different Shapes ◽  
The Common ◽  
Oral Evidence

In this article the position of the accused as a source of personal evidence in three different European legal systems: Poland, Germany, and England, will be presented. This analysis will be oriented to understand the way of functioning of the two different models of giving statements of fact by the accused at a criminal trial. The main difference is that in the common law model of criminal trial the accused may only present evidence by testifying as a witness speaking about what happened, whereas in the continental model the accused gives a specific personal type of evidence (that in the Anglo-Saxon literature is rather described as “oral evidence”) that is known as explanations. From this differentiation several consequences arise: among others, the possibility of presenting untruthful explanations and presenting many versions of events in the continental model which have to be assessed by the judges. At the same time, the same right of the accused to silence and not to give incriminating evidence applies in both models of criminal trial – however, in two different shapes and with different types of limitations.

scholarly journals Inter-subject pattern analysis for multivariate group analysis of functional neuroimaging. A unifying formalization

2020 ◽  
Author(s):  
Qi Wang ◽  
Thierry Artières ◽  
Sylvain Takerkart
Keyword(s):  
Neural Coding ◽  
Pattern Analysis ◽  
Population Studies ◽  
Functional Neuroimaging ◽  
Group Analysis ◽  
Population Level ◽  
Image Features ◽  
Added Value ◽  
Brain Decoding ◽  
Open Datasets

AbstractBackground and objectiveIn medical imaging, population studies have to overcome the differences that exist between individuals to identify invariant image features that can be used for diagnosis purposes. In functional neuroimaging, an appealing solution to identify neural coding principles that hold at the population level is inter-subject pattern analysis, i.e. to learn a predictive model on data from multiple subjects and evaluate its generalization performance on new subjects. Although it has gained popularity in recent years, its widespread adoption is still hampered by the blatant lack of a formal definition in the literature. In this paper, we precisely introduce the first principled formalization of inter-subject pattern analysis targeted at multivariate group analysis of functional neuroimaging.MethodsWe propose to frame inter-subject pattern analysis as a multi-source transductive transfer question, thus grounding it within several well defined machine learning settings and broadening the spectrum of usable algorithms. We describe two sets of inter-subject brain decoding experiments that use several open datasets: a magnetoencephalography study with 16 subjects and a functional magnetic resonance imaging paradigm with 100 subjects. We assess the relevance of our framework by performing model comparisons, where one brain decoding model exploits our formalization while others do not.ResultsThe first set of experiments demonstrates the superiority of a brain decoder that uses subject-by-subject standardization compared to state of the art models that use other standardization schemes, making the case for the interest of the transductive and the multi-source components of our formalization The second set of experiments quantitatively shows that, even after such transformation, it is more difficult for a brain decoder to generalize to new participants rather than to new data from participants available in the training phase, thus highlighting the transfer gap that needs to be overcome.ConclusionThis paper describes the first formalization of inter-subject pattern analysis as a multi-source transductive transfer learning problem. We demonstrate the added value of this formalization using proof-of-concept experiments on several complementary functional neuroimaging datasets. This work should contribute to popularize inter-subject pattern analysis for functional neuroimaging population studies and pave the road for future methodological innovations.

scholarly journals Improving Landscape Spacious Development

2018 ◽  
Vol 7 (3.2) ◽  
pp. 463
Author(s):  
Vladyslav Tymoshevskyi ◽  
Ilona Yurko ◽  
Grigoriy Shariy
Keyword(s):  
Functional Relationship ◽  
Arable Land ◽  
Payback Period ◽  
Capital Expenditures ◽  
Geometrical Parameters ◽  
Triangular Form ◽  
Design Decisions ◽  
Land Protection ◽  
Different Types ◽  
Different Shapes

The purpose of research resulted in recommendations development for landscapes spatial and territory organization improvement, in particular, on the basis of fields geometric parameters influence analysis. The conducted researches are focused on ordering of arable land territory, having spatial and territory unfavorable conditions for management. Analysis is carried out and estimation of fields geometrical parameters influence on mechanized cultivation is provided. The scale for assessing feasibility of crop rotation separating triangular form fields into trapezoidal form workspaces was formed. Different forms triangular plots (rectangular, equilateral, isosceles, scalene) and areas (from 6 to 72 ha) are considered during the study. For a comprehensive analysis of design decisions, economic indicators were used, namely: capital expenditures, annual expenses, additional products cost. Power polynomials were used to establish trends and describe the functional relationship between the different shapes of land plots area and the annual profit, resulted expenses and payback period. They were described by equations and graphs were constructed. Unprofitable, ineffective, expedient and optimal division of the triangular different types areas into trapezoidal form workspaces are presented in the table. The obtained results can be used in land management projects development for territories spatial development, territory organization, rational use organization and land protection. 

Sign in / Sign up

Export Citation Format

Share Document