In this paper,Modified Multi-scale Segmentation Network(MMU-SNet)method is proposed for Tamil text recognition.Handwritten texts from digi-tal writing pad notes are used for text recognition.Handwritten words recognit...In this paper,Modified Multi-scale Segmentation Network(MMU-SNet)method is proposed for Tamil text recognition.Handwritten texts from digi-tal writing pad notes are used for text recognition.Handwritten words recognition for texts written from digital writing pad through text file conversion are challen-ging due to stylus pressure,writing on glass frictionless surfaces,and being less skilled in short writing,alphabet size,style,carved symbols,and orientation angle variations.Stylus pressure on the pad changes the words in the Tamil language alphabet because the Tamil alphabets have a smaller number of lines,angles,curves,and bends.The small change in dots,curves,and bends in the Tamil alphabet leads to error in recognition and changes the meaning of the words because of wrong alphabet conversion.However,handwritten English word recognition and conversion of text files from a digital writing pad are performed through various algorithms such as Support Vector Machine(SVM),Kohonen Neural Network(KNN),and Convolutional Neural Network(CNN)for offline and online alphabet recognition.The proposed algorithms are compared with above algorithms for Tamil word recognition.The proposed MMU-SNet method has achieved good accuracy in predicting text,about 96.8%compared to other traditional CNN algorithms.展开更多
We present a ghost handwritten digit recognition method for the unknown handwritten digits based on ghost imaging(GI)with deep neural network,where a few detection signals from the bucket detector,generated by the cos...We present a ghost handwritten digit recognition method for the unknown handwritten digits based on ghost imaging(GI)with deep neural network,where a few detection signals from the bucket detector,generated by the cosine transform speckle,are used as the characteristic information and the input of the designed deep neural network(DNN),and the output of the DNN is the classification.The results show that the proposed scheme has a higher recognition accuracy(as high as 98%for the simulations,and 91%for the experiments)with a smaller sampling ratio(say 12.76%).With the increase of the sampling ratio,the recognition accuracy is enhanced.Compared with the traditional recognition scheme using the same DNN structure,the proposed scheme has slightly better performance with a lower complexity and non-locality property.The proposed scheme provides a promising way for remote sensing.展开更多
Digit Recognition is an essential element of the process of scanning and converting documents into electronic format. In this work, a new Multiple-Cell Size (MCS) approach is being proposed for utilizing Histogram of ...Digit Recognition is an essential element of the process of scanning and converting documents into electronic format. In this work, a new Multiple-Cell Size (MCS) approach is being proposed for utilizing Histogram of Oriented Gradient (HOG) features and a Support Vector Machine (SVM) based classifier for efficient classification of Handwritten Digits. The HOG based technique is sensitive to the cell size selection used in the relevant feature extraction computations. Hence a new MCS approach has been used to perform HOG analysis and compute the HOG features. The system has been tested on the Benchmark MNIST Digit Database of handwritten digits and a classification accuracy of 99.36% has been achieved using an Independent Test set strategy. A Cross-Validation analysis of the classification system has also been performed using the 10-Fold Cross-Validation strategy and a 10-Fold classification accuracy of 99.26% has been obtained. The classification performance of the proposed system is superior to existing techniques using complex procedures since it has achieved at par or better results using simple operations in both the Feature Space and in the Classifier Space. The plots of the system’s Confusion Matrix and the Receiver Operating Characteristics (ROC) show evidence of the superior performance of the proposed new MCS HOG and SVM based digit classification system.展开更多
In practice, retraining a trained classifier is necessary when novel data become available. This paper adopts an incremental learning procedure to adaptively train a Kernel-based Nonlinear Representor (KNR), a recentl...In practice, retraining a trained classifier is necessary when novel data become available. This paper adopts an incremental learning procedure to adaptively train a Kernel-based Nonlinear Representor (KNR), a recently presented nonlinear classifier for optimal pattern representation, so that its generalization ability may be evaluated in time-variant situation and a sparser representation is obtained for computationally intensive tasks. The addressed techniques are applied to handwritten digit classification to illustrate the feasibility for pattern recognition.展开更多
In this paper, we intensively study the behavior of three part-based methods for handwritten digit recognition. The principle of the proposed methods is to represent a handwritten digit image as a set of parts and rec...In this paper, we intensively study the behavior of three part-based methods for handwritten digit recognition. The principle of the proposed methods is to represent a handwritten digit image as a set of parts and recognize the image by aggregating the recognition results of individual parts. Since part-based methods do not rely on the global structure of a character, they are expected to be more robust against various delormations which may damage the global structure. The proposed three methods are based on the same principle but different in their details, for example, the way of aggregating the individual results. Thus, those methods have different performances. Experimental results show that even the simplest part-based method can achieve recognition rate as high as 98.42% while the improved one achieved 99.15%, which is comparable or even higher than some state-of-the-art method. This result is important because it reveals that characters can be recognized without their global structure. The results also show that the part-based method has robustness against deformations which usually appear in handwriting.展开更多
The diversity of software and hardware forces programmers to spend a great deal of time optimizing their source code,which often requires specific treatment for each platform.The problem becomes critical on embedded d...The diversity of software and hardware forces programmers to spend a great deal of time optimizing their source code,which often requires specific treatment for each platform.The problem becomes critical on embedded devices,where computational and memory resources are strictly constrained.Compilers play an essential role in deploying source code on a target device through the backend.In this work,a novel backend for the Open Neural Network Compiler(ONNC)is proposed,which exploits machine learning to optimize code for the ARM Cortex-M device.The backend requires minimal changes to Open Neural Network Exchange(ONNX)models.Several novel optimization techniques are also incorporated in the backend,such as quantizing the ONNX model’s weight and automatically tuning the dimensions of operators in computations.The performance of the proposed framework is evaluated for two applications:handwritten digit recognition on the Modified National Institute of Standards and Technology(MNIST)dataset and model,and image classification on the Canadian Institute For Advanced Research and 10(CIFAR-10)dataset with the AlexNet-Light model.The system achieves 98.90%and 90.55%accuracy for handwritten digit recognition and image classification,respectively.Furthermore,the proposed architecture is significantly more lightweight than other state-of-theart models in terms of both computation time and generated source code complexity.From the system perspective,this work provides a novel approach to deploying direct computations from the available ONNX models to target devices by optimizing compilers while maintaining high efficiency in accuracy performance.展开更多
文摘In this paper,Modified Multi-scale Segmentation Network(MMU-SNet)method is proposed for Tamil text recognition.Handwritten texts from digi-tal writing pad notes are used for text recognition.Handwritten words recognition for texts written from digital writing pad through text file conversion are challen-ging due to stylus pressure,writing on glass frictionless surfaces,and being less skilled in short writing,alphabet size,style,carved symbols,and orientation angle variations.Stylus pressure on the pad changes the words in the Tamil language alphabet because the Tamil alphabets have a smaller number of lines,angles,curves,and bends.The small change in dots,curves,and bends in the Tamil alphabet leads to error in recognition and changes the meaning of the words because of wrong alphabet conversion.However,handwritten English word recognition and conversion of text files from a digital writing pad are performed through various algorithms such as Support Vector Machine(SVM),Kohonen Neural Network(KNN),and Convolutional Neural Network(CNN)for offline and online alphabet recognition.The proposed algorithms are compared with above algorithms for Tamil word recognition.The proposed MMU-SNet method has achieved good accuracy in predicting text,about 96.8%compared to other traditional CNN algorithms.
基金the National Natural Science Foundation of China(Grant Nos.61871234 and 11847062).
文摘We present a ghost handwritten digit recognition method for the unknown handwritten digits based on ghost imaging(GI)with deep neural network,where a few detection signals from the bucket detector,generated by the cosine transform speckle,are used as the characteristic information and the input of the designed deep neural network(DNN),and the output of the DNN is the classification.The results show that the proposed scheme has a higher recognition accuracy(as high as 98%for the simulations,and 91%for the experiments)with a smaller sampling ratio(say 12.76%).With the increase of the sampling ratio,the recognition accuracy is enhanced.Compared with the traditional recognition scheme using the same DNN structure,the proposed scheme has slightly better performance with a lower complexity and non-locality property.The proposed scheme provides a promising way for remote sensing.
文摘Digit Recognition is an essential element of the process of scanning and converting documents into electronic format. In this work, a new Multiple-Cell Size (MCS) approach is being proposed for utilizing Histogram of Oriented Gradient (HOG) features and a Support Vector Machine (SVM) based classifier for efficient classification of Handwritten Digits. The HOG based technique is sensitive to the cell size selection used in the relevant feature extraction computations. Hence a new MCS approach has been used to perform HOG analysis and compute the HOG features. The system has been tested on the Benchmark MNIST Digit Database of handwritten digits and a classification accuracy of 99.36% has been achieved using an Independent Test set strategy. A Cross-Validation analysis of the classification system has also been performed using the 10-Fold Cross-Validation strategy and a 10-Fold classification accuracy of 99.26% has been obtained. The classification performance of the proposed system is superior to existing techniques using complex procedures since it has achieved at par or better results using simple operations in both the Feature Space and in the Classifier Space. The plots of the system’s Confusion Matrix and the Receiver Operating Characteristics (ROC) show evidence of the superior performance of the proposed new MCS HOG and SVM based digit classification system.
基金Supported by the Key Project of Chinese Ministry of Education (No.105150).
文摘In practice, retraining a trained classifier is necessary when novel data become available. This paper adopts an incremental learning procedure to adaptively train a Kernel-based Nonlinear Representor (KNR), a recently presented nonlinear classifier for optimal pattern representation, so that its generalization ability may be evaluated in time-variant situation and a sparser representation is obtained for computationally intensive tasks. The addressed techniques are applied to handwritten digit classification to illustrate the feasibility for pattern recognition.
文摘In this paper, we intensively study the behavior of three part-based methods for handwritten digit recognition. The principle of the proposed methods is to represent a handwritten digit image as a set of parts and recognize the image by aggregating the recognition results of individual parts. Since part-based methods do not rely on the global structure of a character, they are expected to be more robust against various delormations which may damage the global structure. The proposed three methods are based on the same principle but different in their details, for example, the way of aggregating the individual results. Thus, those methods have different performances. Experimental results show that even the simplest part-based method can achieve recognition rate as high as 98.42% while the improved one achieved 99.15%, which is comparable or even higher than some state-of-the-art method. This result is important because it reveals that characters can be recognized without their global structure. The results also show that the part-based method has robustness against deformations which usually appear in handwriting.
基金This work was supported in part by the Ministry of Science and Technology of Taiwan,R.O.C.,the Grant Number of project 108-2218-E-194-007.
文摘The diversity of software and hardware forces programmers to spend a great deal of time optimizing their source code,which often requires specific treatment for each platform.The problem becomes critical on embedded devices,where computational and memory resources are strictly constrained.Compilers play an essential role in deploying source code on a target device through the backend.In this work,a novel backend for the Open Neural Network Compiler(ONNC)is proposed,which exploits machine learning to optimize code for the ARM Cortex-M device.The backend requires minimal changes to Open Neural Network Exchange(ONNX)models.Several novel optimization techniques are also incorporated in the backend,such as quantizing the ONNX model’s weight and automatically tuning the dimensions of operators in computations.The performance of the proposed framework is evaluated for two applications:handwritten digit recognition on the Modified National Institute of Standards and Technology(MNIST)dataset and model,and image classification on the Canadian Institute For Advanced Research and 10(CIFAR-10)dataset with the AlexNet-Light model.The system achieves 98.90%and 90.55%accuracy for handwritten digit recognition and image classification,respectively.Furthermore,the proposed architecture is significantly more lightweight than other state-of-theart models in terms of both computation time and generated source code complexity.From the system perspective,this work provides a novel approach to deploying direct computations from the available ONNX models to target devices by optimizing compilers while maintaining high efficiency in accuracy performance.
