Purpose:This work aims to normalize the NLPCONTRIBUTIONS scheme(henceforward,NLPCONTRIBUTIONGRAPH)to structure,directly from article sentences,the contributions information in Natural Language Processing(NLP)scholarly...Purpose:This work aims to normalize the NLPCONTRIBUTIONS scheme(henceforward,NLPCONTRIBUTIONGRAPH)to structure,directly from article sentences,the contributions information in Natural Language Processing(NLP)scholarly articles via a two-stage annotation methodology:1)pilot stage-to define the scheme(described in prior work);and 2)adjudication stage-to normalize the graphing model(the focus of this paper).Design/methodology/approach:We re-annotate,a second time,the contributions-pertinent information across 50 prior-annotated NLP scholarly articles in terms of a data pipeline comprising:contribution-centered sentences,phrases,and triple statements.To this end,specifically,care was taken in the adjudication annotation stage to reduce annotation noise while formulating the guidelines for our proposed novel NLP contributions structuring and graphing scheme.Findings:The application of NLPCONTRIBUTIONGRAPH on the 50 articles resulted finally in a dataset of 900 contribution-focused sentences,4,702 contribution-information-centered phrases,and 2,980 surface-structured triples.The intra-annotation agreement between the first and second stages,in terms of F1-score,was 67.92%for sentences,41.82%for phrases,and 22.31%for triple statements indicating that with increased granularity of the information,the annotation decision variance is greater.Research limitations:NLPCONTRIBUTIONGRAPH has limited scope for structuring scholarly contributions compared with STEM(Science,Technology,Engineering,and Medicine)scholarly knowledge at large.Further,the annotation scheme in this work is designed by only an intra-annotator consensus-a single annotator first annotated the data to propose the initial scheme,following which,the same annotator reannotated the data to normalize the annotations in an adjudication stage.However,the expected goal of this work is to achieve a standardized retrospective model of capturing NLP contributions from scholarly articles.This would entail a larger initiative of enlisting multiple annotators to accommodate different worldviews into a“single”set of structures and relationships as the final scheme.Given that the initial scheme is first proposed and the complexity of the annotation task in the realistic timeframe,our intraannotation procedure is well-suited.Nevertheless,the model proposed in this work is presently limited since it does not incorporate multiple annotator worldviews.This is planned as future work to produce a robust model.Practical implications:We demonstrate NLPCONTRIBUTIONGRAPH data integrated into the Open Research Knowledge Graph(ORKG),a next-generation KG-based digital library with intelligent computations enabled over structured scholarly knowledge,as a viable aid to assist researchers in their day-to-day tasks.Originality/value:NLPCONTRIBUTIONGRAPH is a novel scheme to annotate research contributions from NLP articles and integrate them in a knowledge graph,which to the best of our knowledge does not exist in the community.Furthermore,our quantitative evaluations over the two-stage annotation tasks offer insights into task difficulty.展开更多
One of the critical hurdles, and breakthroughs, in the field of Natural Language Processing (NLP) in the last two decades has been the development of techniques for text representation that solves the so-called curse ...One of the critical hurdles, and breakthroughs, in the field of Natural Language Processing (NLP) in the last two decades has been the development of techniques for text representation that solves the so-called curse of dimensionality, a problem which plagues NLP in general given that the feature set for learning starts as a function of the size of the language in question, upwards of hundreds of thousands of terms typically. As such, much of the research and development in NLP in the last two decades has been in finding and optimizing solutions to this problem, to feature selection in NLP effectively. This paper looks at the development of these various techniques, leveraging a variety of statistical methods which rest on linguistic theories that were advanced in the middle of the last century, namely the distributional hypothesis which suggests that words that are found in similar contexts generally have similar meanings. In this survey paper we look at the development of some of the most popular of these techniques from a mathematical as well as data structure perspective, from Latent Semantic Analysis to Vector Space Models to their more modern variants which are typically referred to as word embeddings. In this review of algoriths such as Word2Vec, GloVe, ELMo and BERT, we explore the idea of semantic spaces more generally beyond applicability to NLP.展开更多
The natural language processing(NLP)domain has witnessed significant advancements with the emergence of transformer-based models,which have reshaped the text understanding and generation landscape.While their capabili...The natural language processing(NLP)domain has witnessed significant advancements with the emergence of transformer-based models,which have reshaped the text understanding and generation landscape.While their capabilities are well recognized,there remains a limited systematic synthesis of how these models perform across tasks,scale efficiently,adapt to domains,and address ethical challenges.Therefore,the aim of this paper was to analyze the performance of transformer-based models across various NLP tasks,their scalability,domain adaptation,and the ethical implications of such models.This meta-analysis paper synthesizes findings from 25 peer-reviewed studies on NLP transformer-based models,adhering to the PRISMA framework.Relevant papers were sourced from electronic databases,including IEEE Xplore,Springer,ACM Digital Library,Elsevier,PubMed,and Google Scholar.The findings highlight the superior performance of transformers over conventional approaches,attributed to selfattention mechanisms and pre-trained language representations.Despite these advantages,challenges such as high computational costs,data bias,and hallucination persist.The study provides new perspectives by underscoring the necessity for future research to optimize transformer architectures for efficiency,address ethical AI concerns,and enhance generalization across languages.This paper contributes valuable insights into the current trends,limitations,and potential improvements in transformer-based models for NLP.展开更多
Sparse representation has been highly successful in various tasks related to image processing and computer vision.For ancient mural image inpainting,traditional group sparse representation models usually lead to struc...Sparse representation has been highly successful in various tasks related to image processing and computer vision.For ancient mural image inpainting,traditional group sparse representation models usually lead to structure blur and line discontinuity due to the construction of similarity group solely based on the Euclidean distance and the randomness of dictionary initialization.To address the aforementioned issues,an improved curvature Gabor transform and group sparse representation(CGabor-GSR)model for ancient Dunhuang mural inpainting is proposed.To begin with,mutual information is introduced to weight the Euclidean distance,and then the weighted Euclidean distance acts as a new standard of similarity group.Subsequently,to mitigate the randomness of dictionary initialization,a curvature Gabor wavelet transform is proposed to extract the features and initialize the feature dictionary with dimension reduction based on principal component analysis(PCA).Ultimately,singular value decomposition(SVD)and split Bregman iteration(SBI)can be used to resolve the CGabor-GSR model to reconstruct the mural images.Experimental results on Dunhuang mural inpainting demonstrate tha the proposed CGabor-GSR achieves a better performance than compared algorithms in both objective and visual evaluation.展开更多
The success of ultrasonic nondestructive testing technology depends not only on the generation and measurement of the desired waveform, but also on the signal processing of the measured waves. The traditional time-dom...The success of ultrasonic nondestructive testing technology depends not only on the generation and measurement of the desired waveform, but also on the signal processing of the measured waves. The traditional time-domain methods have been partly successful in identifying small cracks, but not so successful in estimating crack size, especially in strong backscattering noise. Sparse signal representation can provide sparse information that represents the signal time-frequency signature, which can also be used in processing ultrasonic nondestructive signals. A novel ultrasonic nondestructive signal processing algorithm based on signal sparse representation is proposed. In order to suppress noise, matching pursuit algorithm with Gabor dictionary is selected as the signal decomposition method. Precise echoes information, such as crack location and size, can be estimated by quantitative analysis with Gabor atom. To verify the performance, the proposed algorithm is applied to computer simulation signal and experimental ultrasonic signals which represent multiple backscattered echoes from a thin metal plate with artificial holes. The results show that this algorithm not only has an excellent performance even when dealing with signals in the presence of strong noise, but also is successful in estimating crack location and size. Moreover, the algorithm can be applied to data compression of ultrasonic nondestructive signal.展开更多
A new direction finding method is presented to deal with coexisted noncoherent and co- herent signals without smoothing operation. First the direction-of-arrival （DOA） estimation task is herein reformulated as a spa...A new direction finding method is presented to deal with coexisted noncoherent and co- herent signals without smoothing operation. First the direction-of-arrival （DOA） estimation task is herein reformulated as a sparse reconstruction problem of the cleaned array covariance matrix, which is processed to eliminate the affection of the noise. Then by using the block of matrices, the information of DOAs which we pursuit are implied in the sparse coefficient matrix. Finally, the sparse reconstruction problem is solved by the improved M-FOCUSS method, which is applied to the situation of block of matrices. This method outperforms its data domain counterpart in terms of noise suppression, and has a better performance in DOA estimation than the customary spatial smoothing technique. Simulation results verify the efficacy of the proposed method.展开更多
By introducing a fictitious mode to be a counterpart mode of the system mode under review we introduce the entangled state representation （η｜, which can arrange master equations of density operators p（t） in quant...By introducing a fictitious mode to be a counterpart mode of the system mode under review we introduce the entangled state representation （η｜, which can arrange master equations of density operators p（t） in quantum statistics as state-vector evolution equations due to the elegant properties of （η｜. In this way many master equations （respectively describing damping oscillator, laser, phase sensitive, and phase diffusion processes with different initial density operators） can be concisely solved. Specially, for a damping process characteristic of the decay constant k we find that the matrix element of p（t） at time t in 〈η｜ representation is proportional to that of the initial po in the decayed entangled state （ηe^-kt｜ representation, accompanying with a Gaussian damping factor. Thus we have a new insight about the nature of the dissipative process. We also set up the so-called thermo-entangled state representation of density operators, ρ = f（d^2η/π）（η｜ρ〉D（η）, which is different from all the previous known representations.展开更多
With the combination between system simulation and virtual reality,we have established an integrated virtual refinery simulation platform,and analyzed the overall design and principal architecture.This paper introduce...With the combination between system simulation and virtual reality,we have established an integrated virtual refinery simulation platform,and analyzed the overall design and principal architecture.This paper introduces a simulation algorithm about a refinery based on virtual reality,and explains how the algorithm can be applied to the virtual refinery integrated simulation platform in detail.The virtual refinery simulation platform,which consists of a three-dimensional scene system,an integrated database system and a dynamic-static simulation system,has many applications,such as dynamic-static simulation of key process unit used as process control and oil tank blending simulation for scheduling.With the visualization and human-computer interaction for acquiring production and process data,this platform can provide effective supports on staff training related with monitoring,control and operation in refinery.Virtual refinery can also be web published through the internet and it is helpful for the distance training and education.展开更多
We investigate how displaced thermal states （DTSs） evolve in a laser channel. Remarkably, the initial DTS, an example of a mixed state, still remains mixed and thermal. At long times, they finally decay to a highly ...We investigate how displaced thermal states （DTSs） evolve in a laser channel. Remarkably, the initial DTS, an example of a mixed state, still remains mixed and thermal. At long times, they finally decay to a highly classical thermal field only related to the laser parameters κ and g. The normal ordering product of density operator of the DTS in the laser channel leads to obtaining the analytical time-evolution expressions of the photon number, Wigner function, and von Neumann entropy. Also, some interesting results are presented via numerically investigating these explicit time-dependent expressions.展开更多
In this paper,a new risk model is studied in which the rate of premium income is regarded as a random variable,the arrival of insurance policies is a Poisson process and the process of claim occurring is p-thinning pr...In this paper,a new risk model is studied in which the rate of premium income is regarded as a random variable,the arrival of insurance policies is a Poisson process and the process of claim occurring is p-thinning process.The integral representations of the survival probability are gotten.The explicit formula of the survival probability on the infinite interval is obtained in the special casc cxponential distribution.The Lundberg inequality and the common formula of the ruin probability are gotten in terms of some techniques from martingale theory.展开更多
This paper is concerned with a class of uncertain backward stochastic differential equations （UBSDEs） driven by both an m-dimensional Brownian motion and a d-dimensional canonical process with uniform Lipschitzian c...This paper is concerned with a class of uncertain backward stochastic differential equations （UBSDEs） driven by both an m-dimensional Brownian motion and a d-dimensional canonical process with uniform Lipschitzian coefficients. Such equations can be useful in mod- elling hybrid systems, where the phenomena are simultaneously subjected to two kinds of un- certainties： randomness and uncertainty. The solutions of UBSDEs are the uncertain stochastic processes. Thus, the existence and uniqueness of solutions to UBSDEs with Lipschitzian coeffi- cients are proved.展开更多
Linear quadtree is a popular image representation method due to its convenient imaging procedure. However, the excessive emphasis on the symmetry of segmentation, i.e. dividing repeatedly a square into four equal sub-...Linear quadtree is a popular image representation method due to its convenient imaging procedure. However, the excessive emphasis on the symmetry of segmentation, i.e. dividing repeatedly a square into four equal sub-squares, makes linear quadtree not an optimal representation. In this paper, a no-loss image representation, referred to as Overlapped Rectangle Image Representation (ORIR), is presented to support fast image operations such as Legendre moments computation. The ORIR doesn’t importune the symmetry of segmentation, and it is capable of representing, by using an identical rectangle, the information of the pixels which are not even adjacent to each other in the sense of 4-neighbor and 8-neighbor. Hence, compared with the linear quadtree, the ORIR significantly reduces the number of rectangles required to represent an image. Based on the ORIR, an algorithm for exact Legendre moments computation is presented. The theoretical analysis and the experimental results show that the ORIR-based algorithm for exact Legendre moments computation is faster than the conventional exact algorithms.展开更多
基金This work was co-funded by the European Research Council for the project ScienceGRAPH(Grant agreement ID:819536)by the TIB Leibniz Information Centre for Science and Technology.
文摘Purpose:This work aims to normalize the NLPCONTRIBUTIONS scheme(henceforward,NLPCONTRIBUTIONGRAPH)to structure,directly from article sentences,the contributions information in Natural Language Processing(NLP)scholarly articles via a two-stage annotation methodology:1)pilot stage-to define the scheme(described in prior work);and 2)adjudication stage-to normalize the graphing model(the focus of this paper).Design/methodology/approach:We re-annotate,a second time,the contributions-pertinent information across 50 prior-annotated NLP scholarly articles in terms of a data pipeline comprising:contribution-centered sentences,phrases,and triple statements.To this end,specifically,care was taken in the adjudication annotation stage to reduce annotation noise while formulating the guidelines for our proposed novel NLP contributions structuring and graphing scheme.Findings:The application of NLPCONTRIBUTIONGRAPH on the 50 articles resulted finally in a dataset of 900 contribution-focused sentences,4,702 contribution-information-centered phrases,and 2,980 surface-structured triples.The intra-annotation agreement between the first and second stages,in terms of F1-score,was 67.92%for sentences,41.82%for phrases,and 22.31%for triple statements indicating that with increased granularity of the information,the annotation decision variance is greater.Research limitations:NLPCONTRIBUTIONGRAPH has limited scope for structuring scholarly contributions compared with STEM(Science,Technology,Engineering,and Medicine)scholarly knowledge at large.Further,the annotation scheme in this work is designed by only an intra-annotator consensus-a single annotator first annotated the data to propose the initial scheme,following which,the same annotator reannotated the data to normalize the annotations in an adjudication stage.However,the expected goal of this work is to achieve a standardized retrospective model of capturing NLP contributions from scholarly articles.This would entail a larger initiative of enlisting multiple annotators to accommodate different worldviews into a“single”set of structures and relationships as the final scheme.Given that the initial scheme is first proposed and the complexity of the annotation task in the realistic timeframe,our intraannotation procedure is well-suited.Nevertheless,the model proposed in this work is presently limited since it does not incorporate multiple annotator worldviews.This is planned as future work to produce a robust model.Practical implications:We demonstrate NLPCONTRIBUTIONGRAPH data integrated into the Open Research Knowledge Graph(ORKG),a next-generation KG-based digital library with intelligent computations enabled over structured scholarly knowledge,as a viable aid to assist researchers in their day-to-day tasks.Originality/value:NLPCONTRIBUTIONGRAPH is a novel scheme to annotate research contributions from NLP articles and integrate them in a knowledge graph,which to the best of our knowledge does not exist in the community.Furthermore,our quantitative evaluations over the two-stage annotation tasks offer insights into task difficulty.
文摘One of the critical hurdles, and breakthroughs, in the field of Natural Language Processing (NLP) in the last two decades has been the development of techniques for text representation that solves the so-called curse of dimensionality, a problem which plagues NLP in general given that the feature set for learning starts as a function of the size of the language in question, upwards of hundreds of thousands of terms typically. As such, much of the research and development in NLP in the last two decades has been in finding and optimizing solutions to this problem, to feature selection in NLP effectively. This paper looks at the development of these various techniques, leveraging a variety of statistical methods which rest on linguistic theories that were advanced in the middle of the last century, namely the distributional hypothesis which suggests that words that are found in similar contexts generally have similar meanings. In this survey paper we look at the development of some of the most popular of these techniques from a mathematical as well as data structure perspective, from Latent Semantic Analysis to Vector Space Models to their more modern variants which are typically referred to as word embeddings. In this review of algoriths such as Word2Vec, GloVe, ELMo and BERT, we explore the idea of semantic spaces more generally beyond applicability to NLP.
文摘The natural language processing(NLP)domain has witnessed significant advancements with the emergence of transformer-based models,which have reshaped the text understanding and generation landscape.While their capabilities are well recognized,there remains a limited systematic synthesis of how these models perform across tasks,scale efficiently,adapt to domains,and address ethical challenges.Therefore,the aim of this paper was to analyze the performance of transformer-based models across various NLP tasks,their scalability,domain adaptation,and the ethical implications of such models.This meta-analysis paper synthesizes findings from 25 peer-reviewed studies on NLP transformer-based models,adhering to the PRISMA framework.Relevant papers were sourced from electronic databases,including IEEE Xplore,Springer,ACM Digital Library,Elsevier,PubMed,and Google Scholar.The findings highlight the superior performance of transformers over conventional approaches,attributed to selfattention mechanisms and pre-trained language representations.Despite these advantages,challenges such as high computational costs,data bias,and hallucination persist.The study provides new perspectives by underscoring the necessity for future research to optimize transformer architectures for efficiency,address ethical AI concerns,and enhance generalization across languages.This paper contributes valuable insights into the current trends,limitations,and potential improvements in transformer-based models for NLP.
基金supported by National Natural Science Foundation of China(No.61963023)Humanities and Social Sciences Youth Foundation of Ministry of Education(No.19YJC760012)Lanzhou Jiaotong University Basic Top-Notch Personnel Project(No.2022JC36).
文摘Sparse representation has been highly successful in various tasks related to image processing and computer vision.For ancient mural image inpainting,traditional group sparse representation models usually lead to structure blur and line discontinuity due to the construction of similarity group solely based on the Euclidean distance and the randomness of dictionary initialization.To address the aforementioned issues,an improved curvature Gabor transform and group sparse representation(CGabor-GSR)model for ancient Dunhuang mural inpainting is proposed.To begin with,mutual information is introduced to weight the Euclidean distance,and then the weighted Euclidean distance acts as a new standard of similarity group.Subsequently,to mitigate the randomness of dictionary initialization,a curvature Gabor wavelet transform is proposed to extract the features and initialize the feature dictionary with dimension reduction based on principal component analysis(PCA).Ultimately,singular value decomposition(SVD)and split Bregman iteration(SBI)can be used to resolve the CGabor-GSR model to reconstruct the mural images.Experimental results on Dunhuang mural inpainting demonstrate tha the proposed CGabor-GSR achieves a better performance than compared algorithms in both objective and visual evaluation.
基金supported by National Natural Science Foundation of China (Grant No. 60672108, Grant No. 60372020)
文摘The success of ultrasonic nondestructive testing technology depends not only on the generation and measurement of the desired waveform, but also on the signal processing of the measured waves. The traditional time-domain methods have been partly successful in identifying small cracks, but not so successful in estimating crack size, especially in strong backscattering noise. Sparse signal representation can provide sparse information that represents the signal time-frequency signature, which can also be used in processing ultrasonic nondestructive signals. A novel ultrasonic nondestructive signal processing algorithm based on signal sparse representation is proposed. In order to suppress noise, matching pursuit algorithm with Gabor dictionary is selected as the signal decomposition method. Precise echoes information, such as crack location and size, can be estimated by quantitative analysis with Gabor atom. To verify the performance, the proposed algorithm is applied to computer simulation signal and experimental ultrasonic signals which represent multiple backscattered echoes from a thin metal plate with artificial holes. The results show that this algorithm not only has an excellent performance even when dealing with signals in the presence of strong noise, but also is successful in estimating crack location and size. Moreover, the algorithm can be applied to data compression of ultrasonic nondestructive signal.
基金Supported by the National Natural Science Foundation of China (61072098 61072099+1 种基金 60736006)PCSIRT-IRT1005
文摘A new direction finding method is presented to deal with coexisted noncoherent and co- herent signals without smoothing operation. First the direction-of-arrival （DOA） estimation task is herein reformulated as a sparse reconstruction problem of the cleaned array covariance matrix, which is processed to eliminate the affection of the noise. Then by using the block of matrices, the information of DOAs which we pursuit are implied in the sparse coefficient matrix. Finally, the sparse reconstruction problem is solved by the improved M-FOCUSS method, which is applied to the situation of block of matrices. This method outperforms its data domain counterpart in terms of noise suppression, and has a better performance in DOA estimation than the customary spatial smoothing technique. Simulation results verify the efficacy of the proposed method.
基金supported by President Foundation of Chinese Academy of Sciences and National Natural Science Foundation of China under Grant Nos. 10775097 and 10874174
文摘By introducing a fictitious mode to be a counterpart mode of the system mode under review we introduce the entangled state representation （η｜, which can arrange master equations of density operators p（t） in quantum statistics as state-vector evolution equations due to the elegant properties of （η｜. In this way many master equations （respectively describing damping oscillator, laser, phase sensitive, and phase diffusion processes with different initial density operators） can be concisely solved. Specially, for a damping process characteristic of the decay constant k we find that the matrix element of p（t） at time t in 〈η｜ representation is proportional to that of the initial po in the decayed entangled state （ηe^-kt｜ representation, accompanying with a Gaussian damping factor. Thus we have a new insight about the nature of the dissipative process. We also set up the so-called thermo-entangled state representation of density operators, ρ = f（d^2η/π）（η｜ρ〉D（η）, which is different from all the previous known representations.
基金supported by The National High Technology Research and Development Program of China(2009AA044701)
文摘With the combination between system simulation and virtual reality,we have established an integrated virtual refinery simulation platform,and analyzed the overall design and principal architecture.This paper introduces a simulation algorithm about a refinery based on virtual reality,and explains how the algorithm can be applied to the virtual refinery integrated simulation platform in detail.The virtual refinery simulation platform,which consists of a three-dimensional scene system,an integrated database system and a dynamic-static simulation system,has many applications,such as dynamic-static simulation of key process unit used as process control and oil tank blending simulation for scheduling.With the visualization and human-computer interaction for acquiring production and process data,this platform can provide effective supports on staff training related with monitoring,control and operation in refinery.Virtual refinery can also be web published through the internet and it is helpful for the distance training and education.
基金Project supported by the National Natural Science Foundation of China(Grant No.11347026)the Natural Science Foundation of Shandong Province,China(Grant Nos.ZR2016AM03 and ZR2017MA011)
文摘We investigate how displaced thermal states （DTSs） evolve in a laser channel. Remarkably, the initial DTS, an example of a mixed state, still remains mixed and thermal. At long times, they finally decay to a highly classical thermal field only related to the laser parameters κ and g. The normal ordering product of density operator of the DTS in the laser channel leads to obtaining the analytical time-evolution expressions of the photon number, Wigner function, and von Neumann entropy. Also, some interesting results are presented via numerically investigating these explicit time-dependent expressions.
文摘In this paper,a new risk model is studied in which the rate of premium income is regarded as a random variable,the arrival of insurance policies is a Poisson process and the process of claim occurring is p-thinning process.The integral representations of the survival probability are gotten.The explicit formula of the survival probability on the infinite interval is obtained in the special casc cxponential distribution.The Lundberg inequality and the common formula of the ruin probability are gotten in terms of some techniques from martingale theory.
基金Supported by National Natural Science Foundation of China(71171003,71210107026)Anhui Natural Science Foundation(10040606003)Anhui Natural Science Foundation of Universities(KJ2012B019,KJ2013B023)
文摘This paper is concerned with a class of uncertain backward stochastic differential equations （UBSDEs） driven by both an m-dimensional Brownian motion and a d-dimensional canonical process with uniform Lipschitzian coefficients. Such equations can be useful in mod- elling hybrid systems, where the phenomena are simultaneously subjected to two kinds of un- certainties： randomness and uncertainty. The solutions of UBSDEs are the uncertain stochastic processes. Thus, the existence and uniqueness of solutions to UBSDEs with Lipschitzian coeffi- cients are proved.
基金Supported by the National High Technology Research and Development Program of China (No. 2006AA04Z211)
文摘Linear quadtree is a popular image representation method due to its convenient imaging procedure. However, the excessive emphasis on the symmetry of segmentation, i.e. dividing repeatedly a square into four equal sub-squares, makes linear quadtree not an optimal representation. In this paper, a no-loss image representation, referred to as Overlapped Rectangle Image Representation (ORIR), is presented to support fast image operations such as Legendre moments computation. The ORIR doesn’t importune the symmetry of segmentation, and it is capable of representing, by using an identical rectangle, the information of the pixels which are not even adjacent to each other in the sense of 4-neighbor and 8-neighbor. Hence, compared with the linear quadtree, the ORIR significantly reduces the number of rectangles required to represent an image. Based on the ORIR, an algorithm for exact Legendre moments computation is presented. The theoretical analysis and the experimental results show that the ORIR-based algorithm for exact Legendre moments computation is faster than the conventional exact algorithms.
