Projective Reed-Solomon code is an important class of maximal distance separable codes in reliable communication and deep holes play important roles in its decoding.In this paper,we obtain two classes of deep holes of...Projective Reed-Solomon code is an important class of maximal distance separable codes in reliable communication and deep holes play important roles in its decoding.In this paper,we obtain two classes of deep holes of projective Reed-Solomon codes over finite fields with even characteristic.That is,let F_(q) be finite field with even characteristic,k∈{2,q-2},and let u(x)be the Lagrange interpolation polynomial of the first q components of the received vector u∈F_(q)+1 q Suppose that the(q+1)-th component of u is 0,and u(x)=λx^(k)+f_(≤k-2)(x),λx^(q-2)+f_(≤k-2)(x),where λ∈F^(*)_(q) and f_(≤k-2)(x)is a polynomial over F_(q) with degree no more than k-2.Then the received vector u is a deep hole of projective Reed-Solomon codes PRS(F_(q),k).In fact,our result partially solved an open problem on deep holes of projective Reed-Solomon codes proposed by Wan in 2020.展开更多
This paper described a signal processor for the Reed-Solomon (R-S) code using micro-programming. For the purpose of fast encoding and decoding,a formula for detecting two errors is derived, and the Qian search method...This paper described a signal processor for the Reed-Solomon (R-S) code using micro-programming. For the purpose of fast encoding and decoding,a formula for detecting two errors is derived, and the Qian search method for the decoding process is improved. The number of searches is significantly reduced from 256 to 4. At the same time, the circuit is simplified and the speed is increased. For the convenience of programming, a micro-programming compiling package is developed. The package can be used for programming of different formats of R-S code signal processors of DAB, MD and DCC. The software and the hardware can be used for error correcting, error detecting and error compensation of different formats of R-S code.展开更多
The complexity of decoding the standard Reed-Solomon code is a well-known open problem in coding theory.The main problem is to compute the error distance of a received word.Using the Weil bound for character sum estim...The complexity of decoding the standard Reed-Solomon code is a well-known open problem in coding theory.The main problem is to compute the error distance of a received word.Using the Weil bound for character sum estimate,Li and Wan showed that the error distance can be determined when the degree of the received word as a polynomial is small.In the first part,the result of Li and Wan is improved.On the other hand,one of the important parameters of an error-correcting code is the dimension.In most cases,one can only get bounds for the dimension.In the second part,a formula for the dimension of the generalized trace Reed-Solomon codes in some cases is obtained.展开更多
The complexity of decoding the standard Reed-Solomon code is a well known open prob-lem in coding theory. The main problem is to compute the error distance of a received word. Using the Weil bound for character sum es...The complexity of decoding the standard Reed-Solomon code is a well known open prob-lem in coding theory. The main problem is to compute the error distance of a received word. Using the Weil bound for character sum estimate, we show that the error distance can be determined precisely when the degree of the received word is small. As an application of our method, we give a significant improvement of the recent bound of Cheng-Murray on non-existence of deep holes (words with maximal error distance).展开更多
Determining deep holes is an important open problem in decoding Reed-Solomon codes. It is well known that the received word is trivially a deep hole if the degree of its Lagrange interpolation polynomial equals the di...Determining deep holes is an important open problem in decoding Reed-Solomon codes. It is well known that the received word is trivially a deep hole if the degree of its Lagrange interpolation polynomial equals the dimension of the Reed-Solomon code. For the standard Reed-Solomon codes [p-1, k]p with p a prime, Cheng and Murray conjectured in 2007 that there is no other deep holes except the trivial ones. In this paper, we show that this conjecture is not true. In fact, we find a new class of deep holes for standard Reed-Solomon codes [q-1, k]q with q a power of the prime p. Let q≥4 and 2≤k≤q-2. We show that the received word u is a deep hole if its Lagrange interpolation polynomial is the sum of monomial of degree q-2 and a polynomial of degree at most k-1. So there are at least 2(q-1)qk deep holes if k q-3.展开更多
Reed-Solomon （RS） codes have been widely adopted in many modern communication systems. This paper describes a new method for error detection in the syndrome calculator block of RS decoders. The main feature of this ...Reed-Solomon （RS） codes have been widely adopted in many modern communication systems. This paper describes a new method for error detection in the syndrome calculator block of RS decoders. The main feature of this method is to prove that it is possible to compute only a few syndrome coeffi- cients -- less than half-- to detect whether the codeword is correct. The theoretical estimate of the prob- ability that the new algorithm failed is shown to depend on the number of syndrome coefficients computed. The algorithm is tested using the RS（204,188） code with the first four coefficients. With a bit error rate of 1 ~ 104, this method reduces the power consumption by 6% compared to the basic RS（204,188） decoder. The error detection algorithm for the syndrome calculator block does not require modification of the basic hardware implementation of the syndrome coefficients computation. The algorithm significantly reduces the computation complexity of the syndrome calculator block, thus lowering the power needed.展开更多
To improve error-correcting performance, an iterative concatenated soft decoding algorithm for Reed-Solomon （RS） codes is presented in this article. This algorithm brings both complexity as well as advantages in per...To improve error-correcting performance, an iterative concatenated soft decoding algorithm for Reed-Solomon （RS） codes is presented in this article. This algorithm brings both complexity as well as advantages in performance over presently popular sot~ decoding algorithms. The proposed algorithm consists of two powerful soft decoding techniques, adaptive belief propagation （ABP） and box and match algorithm （BMA）, which are serially concatenated by the accumulated log-likelihood ratio （ALLR）. Simulation results show that, compared with ABP and ABP-BMA algorithms, the proposed algorithm can bring more decoding gains and a better tradeoff between the decoding performance and complexity.展开更多
A new Chien search method for shortened Reed-Solomon （RS） code is proposed, based on this, a versatile RS decoder for correcting both errors and erasures is designed. Compared with the traditional RS decoder, the we...A new Chien search method for shortened Reed-Solomon （RS） code is proposed, based on this, a versatile RS decoder for correcting both errors and erasures is designed. Compared with the traditional RS decoder, the weighted coefficient of the Chien search method is calculated sequentially through the three pipelined stages of the decoder. And therefore, the computation of the errata locator polynomial and errata evaluator polynomial needs to be modified. The versatile RS decoder with minimum distance 21 has been synthesized in the Xilinx Virtex-Ⅱ series field programmable gate array （FPGA） xe2v1000-5 and is used by coneatenated coding system for satellite communication. Results show that the maximum data processing rate can be up to 1.3 Gbit/s.展开更多
Reed-Solomon codes are widely used to establish a reliable channel to transmit information in digital communication which has a strong error correction capability and a variety of efficient decoding algorithm.Usually ...Reed-Solomon codes are widely used to establish a reliable channel to transmit information in digital communication which has a strong error correction capability and a variety of efficient decoding algorithm.Usually we use the maximum likelihood decoding(MLD)algorithm in the decoding process of Reed-Solomon codes.MLD algorithm relies on determining the error distance of received word.Dür,Guruswami,Wan,Li,Hong,Wu,Yue and Zhu et al.got some results on the error distance.For the Reed-Solomon code C,the received word u is called an ordinary word of C if the error distance d(u,C)=n-deg u(x)with u(x)being the Lagrange interpolation polynomial of u.We introduce a new method of studying the ordinary words.In fact,we make use of the result obtained by Y.C.Xu and S.F.Hong on the decomposition of certain polynomials over the finite field to determine all the ordinary words of the standard Reed-Solomon codes over the finite field of q elements.This completely answers an open problem raised by Li and Wan in[On the subset sum problem over finite fields,Finite Fields Appl.14(2008)911-929].展开更多
In this paper, we first propose the maximum arc problem, normal rational curve conjecture, and extensions of normal rational curves over finite local rings, analogously to the finite geometry over finite fields. We th...In this paper, we first propose the maximum arc problem, normal rational curve conjecture, and extensions of normal rational curves over finite local rings, analogously to the finite geometry over finite fields. We then study the deep hole problem of generalized Reed-Solomon (RS) codes over finite local rings. Several different classes of deep holes are constructed. The relationship between finite geometry and deep holes of RS codes over finite local rings are also studied.展开更多
In this paper, the subspace subcodes of generalized Reed-Solomn codes are codes are introduced and the fomulas to compute the dimensions of these codes are given.
The concept of homogeneous interpolation problem (HIP) over fields is introduced.It is discovered that solving HIP over finite fields is equivalent to decoding Reed-Solomon (RS) codes.The Welch-Berlekamp algorithm of ...The concept of homogeneous interpolation problem (HIP) over fields is introduced.It is discovered that solving HIP over finite fields is equivalent to decoding Reed-Solomon (RS) codes.The Welch-Berlekamp algorithm of decoding RS codes is derived;besides,by introducing the concept of incomplete locator of error patterns,the algorithm called incomplete iterative decoding is established.展开更多
Based on the studies of Reed-Solomon codes and orthogonalspace-time block codes over Rayleigh fading channel, a theoreticalmethod for estimating performance of Reed-Solomon codes concatenatedwith orthogonal space- tim...Based on the studies of Reed-Solomon codes and orthogonalspace-time block codes over Rayleigh fading channel, a theoreticalmethod for estimating performance of Reed-Solomon codes concatenatedwith orthogonal space- time block codes is presented in this paper.And an upper bound of the bit error rate is also obtained. It isshown through computer simulations that the signal-to-noise ratioreduces about 15 dB or more after orthogonal space-time block codesare concatenate with Reed-Solomon(15,6)codes over Rayleigh fadingchannel, when the bit error rate is 10^-4.展开更多
Let x=(x<sub>0</sub>, …, x<sub>n-1</sub>) be a sequence in the finite field GF（q） with length n, S<sup>i</sup>, x is the i-cyclic shift of x,i.e. S<sup>i</sup>x=(x<...Let x=(x<sub>0</sub>, …, x<sub>n-1</sub>) be a sequence in the finite field GF（q） with length n, S<sup>i</sup>, x is the i-cyclic shift of x,i.e. S<sup>i</sup>x=(x<sub>i</sub>, x<sub>i+1</sub>, …, x<sub>i-1</sub>) （where i+1 means （i+1）rood n）. If there exists a positive integer 0【r≤n making S<sup>r</sup>x=x+（u, u, …, u） hold for some u∈GF（q）, then the r is called one of the generalized periods of this sequence x. The least one r<sub>min</sub> of such periods is called the minimum generalized period of x. In narticular, if r<sub>min</sub>=n (i. e. the展开更多
A novel adaptively iterative list decoding(ILD) approach using for Reed-Solomon(RS) codes was investigated. The proposed scheme is exploited to reduce the complexity of RS Chase algorithm(CA) via an iterative decoding...A novel adaptively iterative list decoding(ILD) approach using for Reed-Solomon(RS) codes was investigated. The proposed scheme is exploited to reduce the complexity of RS Chase algorithm(CA) via an iterative decoding attempt mode. In each decoding attempt process, a test pattern is generated by flipping the bits of the least reliable positions(LRPs) within the received hard-decision(HD) vector. The ILD algorithm continues until a test pattern is successfully decoded by the underlying Berlekamp-Massey algorithm(BMA) of RS codes. Flipping within the same bits, the ILD algorithm provides the same test pattern set as the conventional RS CA, thus there is no degradation in error-rate performance. Without decoding all test patterns, the ILD algorithm can simplify the decoding complexity by its early termination. Simulation results show that the average complexity of the ILD algorithm is much lower than that of the conventional RS CA(and is similar to that of BMA decoding) at high signal-to-noise ratio(SNR) region with no less to the RS CA decoding error-rate performance.展开更多
In the article“Deep Learning-Enhanced Brain Tumor Prediction via Entropy-Coded BPSO in CIELAB Color Space”by Mudassir Khalil,Muhammad Imran Sharif,Ahmed Naeem,Muhammad Umar Chaudhry,Hafiz Tayyab Rauf,Adham E.Ragab C...In the article“Deep Learning-Enhanced Brain Tumor Prediction via Entropy-Coded BPSO in CIELAB Color Space”by Mudassir Khalil,Muhammad Imran Sharif,Ahmed Naeem,Muhammad Umar Chaudhry,Hafiz Tayyab Rauf,Adham E.Ragab Computers,Materials&Continua,2023,Vol.77,No.2,pp.2031–2047.DOI:10.32604/cmc.2023.043687,URL:https://www.techscience.com/cmc/v77n2/54831,there was an error regarding the affiliation for the author Hafiz Tayyab Rauf.Instead of“Centre for Smart Systems,AI and Cybersecurity,Staffordshire University,Stoke-on-Trent,ST42DE,UK”,the affiliation should be“Independent Researcher,Bradford,BD80HS,UK”.展开更多
A two-stage algorithm based on deep learning for the detection and recognition of can bottom spray codes and numbers is proposed to address the problems of small character areas and fast production line speeds in can ...A two-stage algorithm based on deep learning for the detection and recognition of can bottom spray codes and numbers is proposed to address the problems of small character areas and fast production line speeds in can bottom spray code number recognition.In the coding number detection stage,Differentiable Binarization Network is used as the backbone network,combined with the Attention and Dilation Convolutions Path Aggregation Network feature fusion structure to enhance the model detection effect.In terms of text recognition,using the Scene Visual Text Recognition coding number recognition network for end-to-end training can alleviate the problem of coding recognition errors caused by image color distortion due to variations in lighting and background noise.In addition,model pruning and quantization are used to reduce the number ofmodel parameters to meet deployment requirements in resource-constrained environments.A comparative experiment was conducted using the dataset of tank bottom spray code numbers collected on-site,and a transfer experiment was conducted using the dataset of packaging box production date.The experimental results show that the algorithm proposed in this study can effectively locate the coding of cans at different positions on the roller conveyor,and can accurately identify the coding numbers at high production line speeds.The Hmean value of the coding number detection is 97.32%,and the accuracy of the coding number recognition is 98.21%.This verifies that the algorithm proposed in this paper has high accuracy in coding number detection and recognition.展开更多
基金Supported by Foundation of Sichuan Tourism University(20SCTUTY01)Initial Scientific Research Fund of Doctors in Sichuan Tourism University。
文摘Projective Reed-Solomon code is an important class of maximal distance separable codes in reliable communication and deep holes play important roles in its decoding.In this paper,we obtain two classes of deep holes of projective Reed-Solomon codes over finite fields with even characteristic.That is,let F_(q) be finite field with even characteristic,k∈{2,q-2},and let u(x)be the Lagrange interpolation polynomial of the first q components of the received vector u∈F_(q)+1 q Suppose that the(q+1)-th component of u is 0,and u(x)=λx^(k)+f_(≤k-2)(x),λx^(q-2)+f_(≤k-2)(x),where λ∈F^(*)_(q) and f_(≤k-2)(x)is a polynomial over F_(q) with degree no more than k-2.Then the received vector u is a deep hole of projective Reed-Solomon codes PRS(F_(q),k).In fact,our result partially solved an open problem on deep holes of projective Reed-Solomon codes proposed by Wan in 2020.
文摘This paper described a signal processor for the Reed-Solomon (R-S) code using micro-programming. For the purpose of fast encoding and decoding,a formula for detecting two errors is derived, and the Qian search method for the decoding process is improved. The number of searches is significantly reduced from 256 to 4. At the same time, the circuit is simplified and the speed is increased. For the convenience of programming, a micro-programming compiling package is developed. The package can be used for programming of different formats of R-S code signal processors of DAB, MD and DCC. The software and the hardware can be used for error correcting, error detecting and error compensation of different formats of R-S code.
基金Project supported by the National Natural Science Foundation of China (No.10990011)the Doctoral Program Foundation of Ministry of Education of China (No.20095134120001)the Sichuan Province Foundation of China (No. 09ZA087)
文摘The complexity of decoding the standard Reed-Solomon code is a well-known open problem in coding theory.The main problem is to compute the error distance of a received word.Using the Weil bound for character sum estimate,Li and Wan showed that the error distance can be determined when the degree of the received word as a polynomial is small.In the first part,the result of Li and Wan is improved.On the other hand,one of the important parameters of an error-correcting code is the dimension.In most cases,one can only get bounds for the dimension.In the second part,a formula for the dimension of the generalized trace Reed-Solomon codes in some cases is obtained.
文摘The complexity of decoding the standard Reed-Solomon code is a well known open prob-lem in coding theory. The main problem is to compute the error distance of a received word. Using the Weil bound for character sum estimate, we show that the error distance can be determined precisely when the degree of the received word is small. As an application of our method, we give a significant improvement of the recent bound of Cheng-Murray on non-existence of deep holes (words with maximal error distance).
基金supported by National Natural Science Foundation of China (Grant No.10971145)by the Ph.D. Programs Foundation of Ministry of Education of China (Grant No. 20100181110073)
文摘Determining deep holes is an important open problem in decoding Reed-Solomon codes. It is well known that the received word is trivially a deep hole if the degree of its Lagrange interpolation polynomial equals the dimension of the Reed-Solomon code. For the standard Reed-Solomon codes [p-1, k]p with p a prime, Cheng and Murray conjectured in 2007 that there is no other deep holes except the trivial ones. In this paper, we show that this conjecture is not true. In fact, we find a new class of deep holes for standard Reed-Solomon codes [q-1, k]q with q a power of the prime p. Let q≥4 and 2≤k≤q-2. We show that the received word u is a deep hole if its Lagrange interpolation polynomial is the sum of monomial of degree q-2 and a polynomial of degree at most k-1. So there are at least 2(q-1)qk deep holes if k q-3.
基金Supported by the National High-Tech Research and Development (863) Program of China (No. 2007AA01Z2B3)
文摘Reed-Solomon （RS） codes have been widely adopted in many modern communication systems. This paper describes a new method for error detection in the syndrome calculator block of RS decoders. The main feature of this method is to prove that it is possible to compute only a few syndrome coeffi- cients -- less than half-- to detect whether the codeword is correct. The theoretical estimate of the prob- ability that the new algorithm failed is shown to depend on the number of syndrome coefficients computed. The algorithm is tested using the RS（204,188） code with the first four coefficients. With a bit error rate of 1 ~ 104, this method reduces the power consumption by 6% compared to the basic RS（204,188） decoder. The error detection algorithm for the syndrome calculator block does not require modification of the basic hardware implementation of the syndrome coefficients computation. The algorithm significantly reduces the computation complexity of the syndrome calculator block, thus lowering the power needed.
基金supported by the National Natural Science Foundation of China(60472104)
文摘To improve error-correcting performance, an iterative concatenated soft decoding algorithm for Reed-Solomon （RS） codes is presented in this article. This algorithm brings both complexity as well as advantages in performance over presently popular sot~ decoding algorithms. The proposed algorithm consists of two powerful soft decoding techniques, adaptive belief propagation （ABP） and box and match algorithm （BMA）, which are serially concatenated by the accumulated log-likelihood ratio （ALLR）. Simulation results show that, compared with ABP and ABP-BMA algorithms, the proposed algorithm can bring more decoding gains and a better tradeoff between the decoding performance and complexity.
基金Sponsored by the Ministerial Level Advanced Research Foundation (20304)
文摘A new Chien search method for shortened Reed-Solomon （RS） code is proposed, based on this, a versatile RS decoder for correcting both errors and erasures is designed. Compared with the traditional RS decoder, the weighted coefficient of the Chien search method is calculated sequentially through the three pipelined stages of the decoder. And therefore, the computation of the errata locator polynomial and errata evaluator polynomial needs to be modified. The versatile RS decoder with minimum distance 21 has been synthesized in the Xilinx Virtex-Ⅱ series field programmable gate array （FPGA） xe2v1000-5 and is used by coneatenated coding system for satellite communication. Results show that the maximum data processing rate can be up to 1.3 Gbit/s.
基金supported by the National Science Foundation of China Grant 11771304Fundamental Research Funds for the Central Universities.X.F.Xu was partially supported by Foundation of Sichuan Tourism University Grant 20SCTUTY01.
文摘Reed-Solomon codes are widely used to establish a reliable channel to transmit information in digital communication which has a strong error correction capability and a variety of efficient decoding algorithm.Usually we use the maximum likelihood decoding(MLD)algorithm in the decoding process of Reed-Solomon codes.MLD algorithm relies on determining the error distance of received word.Dür,Guruswami,Wan,Li,Hong,Wu,Yue and Zhu et al.got some results on the error distance.For the Reed-Solomon code C,the received word u is called an ordinary word of C if the error distance d(u,C)=n-deg u(x)with u(x)being the Lagrange interpolation polynomial of u.We introduce a new method of studying the ordinary words.In fact,we make use of the result obtained by Y.C.Xu and S.F.Hong on the decomposition of certain polynomials over the finite field to determine all the ordinary words of the standard Reed-Solomon codes over the finite field of q elements.This completely answers an open problem raised by Li and Wan in[On the subset sum problem over finite fields,Finite Fields Appl.14(2008)911-929].
基金The research of Jun Zhang was supported by the National Natural Science Foundation of China(Grant No.11971321)by National Key Research and Development Program of China(Grant No.2018YFA0704703)The research of Haiyan Zhou was supported by the National Natural Science Foundation of China(Grant No.12071221).
文摘In this paper, we first propose the maximum arc problem, normal rational curve conjecture, and extensions of normal rational curves over finite local rings, analogously to the finite geometry over finite fields. We then study the deep hole problem of generalized Reed-Solomon (RS) codes over finite local rings. Several different classes of deep holes are constructed. The relationship between finite geometry and deep holes of RS codes over finite local rings are also studied.
文摘In this paper, the subspace subcodes of generalized Reed-Solomn codes are codes are introduced and the fomulas to compute the dimensions of these codes are given.
基金Project supported by the National Natural Science Foundation of China.
文摘The concept of homogeneous interpolation problem (HIP) over fields is introduced.It is discovered that solving HIP over finite fields is equivalent to decoding Reed-Solomon (RS) codes.The Welch-Berlekamp algorithm of decoding RS codes is derived;besides,by introducing the concept of incomplete locator of error patterns,the algorithm called incomplete iterative decoding is established.
文摘Based on the studies of Reed-Solomon codes and orthogonalspace-time block codes over Rayleigh fading channel, a theoreticalmethod for estimating performance of Reed-Solomon codes concatenatedwith orthogonal space- time block codes is presented in this paper.And an upper bound of the bit error rate is also obtained. It isshown through computer simulations that the signal-to-noise ratioreduces about 15 dB or more after orthogonal space-time block codesare concatenate with Reed-Solomon(15,6)codes over Rayleigh fadingchannel, when the bit error rate is 10^-4.
基金Project supported by the National Natural Science Fund for Youth
文摘Let x=(x<sub>0</sub>, …, x<sub>n-1</sub>) be a sequence in the finite field GF（q） with length n, S<sup>i</sup>, x is the i-cyclic shift of x,i.e. S<sup>i</sup>x=(x<sub>i</sub>, x<sub>i+1</sub>, …, x<sub>i-1</sub>) （where i+1 means （i+1）rood n）. If there exists a positive integer 0【r≤n making S<sup>r</sup>x=x+（u, u, …, u） hold for some u∈GF（q）, then the r is called one of the generalized periods of this sequence x. The least one r<sub>min</sub> of such periods is called the minimum generalized period of x. In narticular, if r<sub>min</sub>=n (i. e. the
基金supported by the National Natural Science Foundation of China (61671080,61601047)
文摘A novel adaptively iterative list decoding(ILD) approach using for Reed-Solomon(RS) codes was investigated. The proposed scheme is exploited to reduce the complexity of RS Chase algorithm(CA) via an iterative decoding attempt mode. In each decoding attempt process, a test pattern is generated by flipping the bits of the least reliable positions(LRPs) within the received hard-decision(HD) vector. The ILD algorithm continues until a test pattern is successfully decoded by the underlying Berlekamp-Massey algorithm(BMA) of RS codes. Flipping within the same bits, the ILD algorithm provides the same test pattern set as the conventional RS CA, thus there is no degradation in error-rate performance. Without decoding all test patterns, the ILD algorithm can simplify the decoding complexity by its early termination. Simulation results show that the average complexity of the ILD algorithm is much lower than that of the conventional RS CA(and is similar to that of BMA decoding) at high signal-to-noise ratio(SNR) region with no less to the RS CA decoding error-rate performance.
文摘In the article“Deep Learning-Enhanced Brain Tumor Prediction via Entropy-Coded BPSO in CIELAB Color Space”by Mudassir Khalil,Muhammad Imran Sharif,Ahmed Naeem,Muhammad Umar Chaudhry,Hafiz Tayyab Rauf,Adham E.Ragab Computers,Materials&Continua,2023,Vol.77,No.2,pp.2031–2047.DOI:10.32604/cmc.2023.043687,URL:https://www.techscience.com/cmc/v77n2/54831,there was an error regarding the affiliation for the author Hafiz Tayyab Rauf.Instead of“Centre for Smart Systems,AI and Cybersecurity,Staffordshire University,Stoke-on-Trent,ST42DE,UK”,the affiliation should be“Independent Researcher,Bradford,BD80HS,UK”.
文摘A two-stage algorithm based on deep learning for the detection and recognition of can bottom spray codes and numbers is proposed to address the problems of small character areas and fast production line speeds in can bottom spray code number recognition.In the coding number detection stage,Differentiable Binarization Network is used as the backbone network,combined with the Attention and Dilation Convolutions Path Aggregation Network feature fusion structure to enhance the model detection effect.In terms of text recognition,using the Scene Visual Text Recognition coding number recognition network for end-to-end training can alleviate the problem of coding recognition errors caused by image color distortion due to variations in lighting and background noise.In addition,model pruning and quantization are used to reduce the number ofmodel parameters to meet deployment requirements in resource-constrained environments.A comparative experiment was conducted using the dataset of tank bottom spray code numbers collected on-site,and a transfer experiment was conducted using the dataset of packaging box production date.The experimental results show that the algorithm proposed in this study can effectively locate the coding of cans at different positions on the roller conveyor,and can accurately identify the coding numbers at high production line speeds.The Hmean value of the coding number detection is 97.32%,and the accuracy of the coding number recognition is 98.21%.This verifies that the algorithm proposed in this paper has high accuracy in coding number detection and recognition.
