scholarly journals An Effective and Improved CNN-ELM Classifier for Handwritten Digits Recognition and Classification

Symmetry ◽  
2020 ◽  
Vol 12 (10) ◽  
pp. 1742
Author(s):  
Saqib Ali ◽  
Jianqiang Li ◽  
Yan Pei ◽  
Muhammad Saqlain Aslam ◽  
Zeeshan Shaukat ◽  
...  
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Activation Function ◽  
Computational Time ◽  
Robust Model ◽  
Perfect Symmetry ◽  
Handwritten Digit ◽  
Low Efficiency ◽  
Learning Machine ◽  
Sigmoid Activation Function

Optical character recognition is gaining immense importance in the domain of deep learning. With each passing day, handwritten digits (0–9) data are increasing rapidly, and plenty of research has been conducted thus far. However, there is still a need to develop a robust model that can fetch useful information and investigate self-build handwritten digit data efficiently and effectively. The convolutional neural network (CNN) models incorporating a sigmoid activation function with a large number of derivatives have low efficiency in terms of feature extraction. Here, we designed a novel CNN model integrated with the extreme learning machine (ELM) algorithm. In this model, the sigmoid activation function is upgraded as the rectified linear unit (ReLU) activation function, and the CNN unit along with the ReLU activation function are used as a feature extractor. The ELM unit works as the image classifier, which makes the perfect symmetry for handwritten digit recognition. A deeplearning4j (DL4J) framework-based CNN-ELM model was developed and trained using the Modified National Institute of Standards and Technology (MNIST) database. Validation of the model was performed through self-build handwritten digits and USPS test datasets. Furthermore, we observed the variation of accuracies by adding various hidden layers in the architecture. Results reveal that the CNN-ELM-DL4J approach outperforms the conventional CNN models in terms of accuracy and computational time.

scholarly journals A Method Combining CNN and ELM for Feature Extraction and Classification of SAR Image

2019 ◽  
Vol 2019 ◽  
pp. 1-8 ◽  
Author(s):  
Peng Wang ◽  
Xiaomin Zhang ◽  
Yan Hao
Keyword(s):  
Image Recognition ◽  
Recognition Rate ◽  
Activation Function ◽  
Recognition Algorithm ◽  
Sar Image ◽  
Stationary Target ◽  
Speed Up ◽  
Low Efficiency ◽  
Learning Machine ◽  
Sigmoid Activation Function

Due to the large number of Sigmoid activation function derivation in the traditional convolution neural network (CNN), it is difficult to solve the question of the low efficiency of extracting the feature of Synthetic Aperture Radar (SAR) images. The Sigmoid activation function in the CNN is improved to be a rectified linear unit (ReLU) activation function, and the classifier is modified by the Extreme Learning Machine (ELM). Finally, in this CNN model, the improved CNN works as the feature extractor and ELM performs as a recognizer. A SAR image recognition algorithm based on the CNN-ELM algorithm is proposed by combining the CNN and the ELM algorithm. The experiment is conducted on the Moving and Stationary Target Acquisition and Recognition (MSTAR) database which contains 10 kinds of target images. The experiment result shows that the algorithm can realize the sparsity of the network, alleviate the overfitting problem, and speed up the convergence speed of the network. It is worth mentioning that the running time of this experiment is very short. Compared with other experiment on the same database, it indicates that this experiment has generated a higher recognition rate. The accuracy of the SAR image recognition is 100%.

scholarly journals Extreme Learning Machine with sigmoid activation function on large data

2019 ◽  
Vol 8 (2S11) ◽  
pp. 3523-3526
Keyword(s):  
Efficient Algorithm ◽  
Large Data ◽  
Activation Function ◽  
Large Data Sets ◽  
Data Sets ◽  
Data Set ◽  
Learning Machine ◽  
Sigmoid Activation Function ◽  
State Of Art ◽  
Better Than

This paper describes an efficient algorithm for classification in large data set. While many algorithms exist for classification, they are not suitable for larger contents and different data sets. For working with large data sets various ELM algorithms are available in literature. However the existing algorithms using fixed activation function and it may lead deficiency in working with large data. In this paper, we proposed novel ELM comply with sigmoid activation function. The experimental evaluations demonstrate the our ELM-S algorithm is performing better than ELM,SVM and other state of art algorithms on large data sets.

scholarly journals Improve OCR Accuracy with Advanced Image Preprocessing using Machine Learning with Python

2020 ◽  
Vol 9 (7) ◽  
pp. 1026-1030
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Neural Networks ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Image Preprocessing ◽  
Optical Character ◽  
Handwritten Text ◽  
Printed Text ◽  
Learning Machine

Optical Character Recognition or Optical Character Reader (OCR) is a pattern-based method consciousness that transforms the concept of electronic conversion of images of handwritten text or printed text in a text compiled. Equipment or tools used for that purpose are cameras and apartment scanners. Handwritten text is scanned using a scanner. The image of the scrutinized document is processed using the program. Identification of manuscripts is difficult compared to other western language texts. In our proposed work we will accept the challenge of identifying letters and letters and working to achieve the same. Image Preprocessing techniques can effectively improve the accuracy of an OCR engine. The goal is to design and implement a machine with a learning machine and Python that is best to work with more accurate than OCR's pre-built machines with unique technologies such as MatLab, Artificial Intelligence, Neural networks, etc.

Handwritten Digit Recognition Using Deep Learning

2021 ◽  
pp. 153-158
Author(s):  
Bhagyashree P M ◽  
L K Likhitha ◽  
D S Rajesh
Keyword(s):  
Deep Learning ◽  
Learning Strategies ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Handwriting Recognition ◽  
Handwritten Digit Recognition ◽  
Digit Recognition ◽  
Handwritten Digit ◽  
Overall Performance ◽  
Similar Accuracy

Traditional systems of handwritten Digit Recognition have depended on handcrafted functions and a massive amount of previous knowledge. Training an Optical character recognition (OCR) system primarily based totally on those stipulations is a hard task. Research in the handwriting recognition subject is centered on deep learning strategies and has accomplished breakthrough overall performance in the previous couple of years. Convolutional neural networks (CNNs) are very powerful in perceiving the structure of handwritten digits in ways that assist in automated extraction of features and make CNN the most appropriate technique for solving handwriting recognition problems. Here, our goal is to attain similar accuracy through the use of a pure CNN structure.CNN structure is proposed to be able to attain accuracy even higher than that of ensemble architectures, alongside decreased operational complexity and price. The proposed method gives 99.87 accuracy for real-world handwritten digit prediction with less than 0.1 % loss on training with 60000 digits while 10000 under validation.

scholarly journals Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN)

Sensors ◽  
2020 ◽  
Vol 20 (12) ◽  
pp. 3344 ◽  
Author(s):  
Savita Ahlawat ◽  
Amit Choudhary ◽  
Anand Nayyar ◽  
Saurabh Singh ◽  
Byungun Yoon
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Recognition Accuracy ◽  
Handwriting Recognition ◽  
Computational Cost ◽  
Handwritten Digit Recognition ◽  
Digit Recognition ◽  
Handwritten Digit

Traditional systems of handwriting recognition have relied on handcrafted features and a large amount of prior knowledge. Training an Optical character recognition (OCR) system based on these prerequisites is a challenging task. Research in the handwriting recognition field is focused around deep learning techniques and has achieved breakthrough performance in the last few years. Still, the rapid growth in the amount of handwritten data and the availability of massive processing power demands improvement in recognition accuracy and deserves further investigation. Convolutional neural networks (CNNs) are very effective in perceiving the structure of handwritten characters/words in ways that help in automatic extraction of distinct features and make CNN the most suitable approach for solving handwriting recognition problems. Our aim in the proposed work is to explore the various design options like number of layers, stride size, receptive field, kernel size, padding and dilution for CNN-based handwritten digit recognition. In addition, we aim to evaluate various SGD optimization algorithms in improving the performance of handwritten digit recognition. A network’s recognition accuracy increases by incorporating ensemble architecture. Here, our objective is to achieve comparable accuracy by using a pure CNN architecture without ensemble architecture, as ensemble architectures introduce increased computational cost and high testing complexity. Thus, a CNN architecture is proposed in order to achieve accuracy even better than that of ensemble architectures, along with reduced operational complexity and cost. Moreover, we also present an appropriate combination of learning parameters in designing a CNN that leads us to reach a new absolute record in classifying MNIST handwritten digits. We carried out extensive experiments and achieved a recognition accuracy of 99.87% for a MNIST dataset.

scholarly journals Skew detection based on vertical projection in latin character recognition of text document image

2018 ◽  
Vol 7 (4.44) ◽  
pp. 198
Author(s):  
Ronny Susanto ◽  
Farica P. Putri ◽  
Y. Widya Wiratama
Keyword(s):  
Error Rate ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Rotation Angle ◽  
Document Image ◽  
Computational Time ◽  
Vertical Projection ◽  
Word Error Rate ◽  
Skew Detection ◽  
Text Document

The accuracy of Optical Character Recognition is deeply affected by the skew of the image.  Skew detection & correction is one of the steps in OCR preprocessing to detect and correct the skew of document image. This research measures the effect of Combined Vertical Projection skew detection method to the accuracy of OCR. Accuracy of OCR is measured in Character Error Rate, Word Error Rate, and Word Error Rate (Order Independent). This research also measures the computational time needed in Combined Vertical Projection with different iteration. The experiment of Combined Vertical Projection is conducted by using iteration 0.5, 1, and 2 with rotation angle within -10 until 10 degrees. The experiment results show that the use of Combined Vertical Projection could lower the Character Error Rate, Word Error Rate, and Word Error Rate (Order Independent) up to 35.53, 34.51, and 32.74 percent, respectively. Using higher iteration value could lower the computational time but also decrease the accuracy of OCR.   

A Meetei Mayek Handwritten Digit Recognition System

2020 ◽  
Vol 17 (1) ◽  
pp. 334-339
Author(s):  
Chingakham Neeta Devi ◽  
Debaprasad Das ◽  
Haobam Mamata Devi
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Recognition System ◽  
Support Vector ◽  
Handwritten Digit Recognition ◽  
Digit Recognition ◽  
Speeded Up Robust Features ◽  
Bag Of Features ◽  
Optical Character ◽  
Handwritten Digit

Optical Character Recognition is an appealing field of work for research where an image containing text is given as input and text in the image is translated into an editable format. This paper proposes Meetei/Meitei Mayek Handwritten Digit Recognition System where an Isolated Handwritten Meetei Mayek Digit Database consisting of 10000 plus digits has been developed. This proposed Handwritten Meetei Mayek Digit Recognition System is an important component of Manipuri Meetei Mayek Optical Character Recognition system which is under development. For feature extraction, we have used State-of-Art techniques—Histogram of Oriented Gradients and Bag of Features Descriptor for Speeded Up Robust Features. Five classifiers have been employed for classification viz. Support Vector Machine, with Linear, Polynomial and Radial Basis Function kernels, K-Nearest Neighbours and Bootstrap Aggregating and compared in terms of accuracy. Support Vector Machine using Radial Basis Function Kernel has found to achieve the recognition accuracy with the highest value compared with the other classifiers with the extracted Histogram of Oriented Gradients and Bag of Features for Speeded Up Robust Features.

Deep Extreme Learning Machine-Based Optical Character Recognition System for Nastalique Urdu-Like Script Languages

2020 ◽  
Author(s):  
Syed Saqib Raza Rizvi ◽  
Muhammad Adnan Khan ◽  
Sagheer Abbas ◽  
Muhammad Asadullah ◽  
Nida Anwer ◽  
...  
Keyword(s):  
Extreme Learning Machine ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Recognition Rate ◽  
Recognition System ◽  
Software Systems ◽  
Script Language ◽  
Optical Character ◽  
Handwritten Text ◽  
Learning Machine

Abstract Optical character recognition systems convert printed or handwritten scripts into digital text formats like ASCII or UNICODE. Urdu-like script languages like Urdu, Punjabi and Sindhi are widely spoken languages of the world, especially in Asia. An enormous amount of printed and handwritten text of such languages exist, which needs to be converted into computer-understandable formats for knowledge extraction. In this study, extreme learning machine’s (ELM’s) most recently proposed variant called deep extreme learning machine (DELM)-based optical character recognition (OCR) system is proposed to enhance Urdu-like script language’s character recognition rate. The proposed DELM-based character recognition model is optimizing the OCR process by reducing the overhead of Pre-processing, Segmentation and Feature Extraction Layer. The proposed system evaluations accomplished 98.75% training accuracy with 1.492 × 10−3 RMSE and 98.12% testing accuracy with 1.587 × 10−3 RMSE, with six DELM hidden layers. The results show that the proposed system has attained the foremost recognition rate as compared to any previously proposed Urdu-like script language OCR system. This technique is applicable for machine-printed text and fractionally useful for handwritten text as well. This study will aid in the advancement of more accurate Urdu-like script OCR’s software systems in the future.

A Novel Approach Towards Handwritten Digit Recognition Using Refraction Property of Light Rays

2020 ◽  
Vol 10 (3) ◽  
pp. 1-17 ◽  
Author(s):  
Roopkatha Samanta ◽  
Soulib Ghosh ◽  
Agneet Chatterjee ◽  
Ram Sarkar
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
State Of The Art ◽  
Feature Descriptor ◽  
Handwritten Digit Recognition ◽  
Digit Recognition ◽  
Novel Approach ◽  
Light Rays ◽  
Handwritten Digit ◽  
Invariant Shape

Due to the enormous application, handwritten digit recognition (HDR) has become an extremely important domain in optical character recognition (OCR)-related research. The predominant challenges faced in this domain include different photometric inconsistencies together with computational complexity. In this paper, the authors proposed a language invariant shape-based feature descriptor using the refraction property of light rays. It is to be noted that the proposed approach is novel as an adaptation of refraction property is completely new in this domain. The proposed method is assessed using five datasets of five different languages. Among the five datasets, four are offline (written Devanagari, Bangla, Arabic, and Telugu) and one is online (written in Assamese) handwritten digit datasets. The approach provides admirable outcomes for online digits whereas; it yields satisfactory results for offline handwritten digits. The method gives good result for both online and offline handwritten digits, which proves its robustness. It is also computationally less expensive compared to other state-of-the-art methods including deep learning-based models.

Sign in / Sign up

Export Citation Format

Share Document