A Novel Approach for Optical Character Recognition (OCR) of Handwritten Telugu Alphabets using Convolutional Neural Networks

Recognition Accuracy ◽

Research Use ◽

Optical Character ◽

Classification Tasks ◽

Scanned Images

In the proposed paper we introduce a new Pashtu numerals dataset having handwritten scanned images. We make the dataset publically available for scientific and research use. Pashtu language is used by more than fifty million people both for oral and written communication, but still no efforts are devoted to the Optical Character Recognition (OCR) system for Pashtu language. We introduce a new method for handwritten numerals recognition of Pashtu language through the deep learning based models. We use convolutional neural networks (CNNs) both for features extraction and classification tasks. We assess the performance of the proposed CNNs based model and obtained recognition accuracy of 91.45%.

Proceedings of the 2015 4th National Conference on Electrical, Electronics and Computer Engineering ◽

Study on neural networks in optical character recognition

10.2991/nceece-15.2016.299 ◽

2016 ◽

Author(s):

Jin-Song Wu

Keyword(s):

Neural Networks ◽

Character Recognition ◽

Optical Character Recognition for Sanskrit Using Convolution Neural Networks

2018 13th IAPR International Workshop on Document Analysis Systems (DAS) ◽

10.1109/das.2018.50 ◽

2018 ◽

Cited By ~ 10

Author(s):

Meduri Avadesh ◽

Navneet Goyal

Keyword(s):

Neural Networks ◽

Character Recognition ◽

Convolution Neural Networks ◽

Optical Character Recognition of Indian Language Manuscripts using Convolutional Neural Networks

Design Engineering ◽

10.17762/de.v2021i3.7789 ◽

2021 ◽

pp. 894-911

Author(s):

Bhavesh Kataria, Dr. Harikrishna B. Jethva

Keyword(s):

Neural Networks ◽

Character Recognition ◽

Short Term Memory ◽

Short Term ◽

Indian Language ◽

Term Memory ◽

Text Document ◽

Optical Character ◽

Long Short Term Memory

India's constitution has 22 languages written in 17 different scripts. These materials have a limited lifespan, and as generations pass, these materials deteriorate, and the vital knowledge is lost. This work uses digital texts to convey information to future generations. Optical Character Recognition (OCR) helps extract information from scanned manuscripts (printed text). This paper proposes a simple and effective solution of optical character recognition (OCR) Sanskrit Character from text document images using long short-term memory (LSTM) and neural networks of Sanskrit Characters. Existing methods focuses only upon the single touching characters. But our main focus is to design a robust method using Bidirectional Long Short-Term Memory (BLSTM) architecture for overlapping lines, touching characters in middle and upper zone and half character which would increase the accuracy of the present OCR system for recognition of poorly maintained Sanskrit literature.

Expiry date recognition using deep neural networks

International Joural of User-System Interaction ◽

10.37789/ijusi.2020.13.1.1 ◽

2020 ◽

Vol 13 (1) ◽

pp. 1-17

Author(s):

Traian Rebedea ◽

Vlad Florea

Keyword(s):

Neural Networks ◽

Character Recognition ◽

Speech Synthesis ◽

Efficient Solution ◽

Deep Neural Networks ◽

Accuracy Improvement ◽

Expiry Date ◽

Food Items ◽

This paper proposes a deep learning solution for optical character recognition, specifically tuned to detect expiration dates that are printed on the packaging of food items. This method can be used to reduce food waste, having a significant impact on the design of smart refrigerators and can prove especially useful for persons with vision difficulties, by combining it with a speech synthesis engine. The main problem in designing an efficient solution for expiry date recognition is the lack of a large enough dataset to train deep neural networks. To tackle this issue, we propose to use an additional dataset composed of synthetically generated images. Both the synthetic and real image datasets are detailed in the paper and we show that the proposed method offers a 9.4% accuracy improvement over using real images alone.

Recognizing Ancient Characters from Tamil Palm Leaf Manuscripts using Convolution Based Deep Learning

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.c5842.098319 ◽

2019 ◽

Vol 8 (3) ◽

pp. 6873-6880

Keyword(s):

Neural Network ◽

Neural Networks ◽

Image Processing ◽

Pattern Recognition ◽

Deep Learning ◽

Convolutional Neural Networks ◽

Character Recognition ◽

Convolutional Network ◽

Palm Leaf

Palm leaf manuscripts has been one of the ancient writing methods but the palm leaf manuscripts content requires to be inscribed in a new set of leaves. This study has provided a solution to save the contents in palm leaf manuscripts by recognizing the handwritten Tamil characters in manuscripts and storing them digitally. Character recognition is one of the most essential fields of pattern recognition and image processing. Generally Optical character recognition is the method of e-translation of typewritten text or handwritten images into machine editable text. The handwritten Tamil character recognition has been one of the challenging and active areas of research in the field of pattern recognition and image processing. In this study a trial was made to identify Tamil handwritten characters without extraction of feature using convolutional neural networks. This study uses convolutional neural networks for recognizing and classifying the Tamil palm leaf manuscripts of characters from separated character images. The convolutional neural network is a deep learning approach for which it does not need to retrieve features and also a rapid approach for character recognition. In the proposed system every character is expanded to needed pixels. The expanded characters have predetermined pixels and these pixels are considered as characteristics for neural network training. The trained network is employed for recognition and classification. Convolutional Network Model development contains convolution layer, Relu layer, pooling layer, fully connected layer. The ancient Tamil character dataset of 60 varying class has been created. The outputs reveal that the proposed approach generates better rates of recognition than that of schemes based on feature extraction for handwritten character recognition. The accuracy of the proposed approach has been identified as 97% which shows that the proposed approach is effective in terms of recognition of ancient characters.

Hierarchical optical character recognition system design based on the Hopfield neural networks

Scientific Technical Review ◽

10.5937/str1503019k ◽

2015 ◽

Vol 65 (3) ◽

pp. 19-26

Author(s):

Nataša Kljajić ◽

Željko Đurović

Keyword(s):

Neural Networks ◽

System Design ◽

Character Recognition ◽

Recognition System ◽

Hopfield Neural Networks ◽

Image Spam Filtering using Machine Learning Techniques

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.b1035.0782s419 ◽

2019 ◽

Vol 8 (2S4) ◽

pp. 186-190

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Character Recognition ◽

Spam Filtering ◽

Data Filtering ◽

Visual Data ◽

Optical Character ◽

Image Spam ◽

Artificial Neural

Unsolicited visual data is undesirable in any form. The art of hiding malicious content in images and adding them as attachments to electronic mails has become a popular nuisance. In recent years, attackers have developed various new techniques to evade traditional spam classification systems. Text-based spam classification has been in focus for a long time and, researchers have successfully created a prodigal system for identifying spam text in electronic mails using Optical Character Recognition technology. In the last decade, extensive work has been performed to tackle image spam but with unsatisfactory results. Various algorithms and data augmentation techniques are used today to develop an optimal model for image spam recognition. Many of these proposed systems come close to the ideal system but do not provide 100 percent accuracy. This paper highlights the role of three popular techniques in image spam filtering. We discuss the importance and application of Optical Character Recognition, Support Vector Machines and, Artificial Neural Networks in unsolicited visual data filtering. This paper sheds light on the algorithms of these techniques. We provide a comparison of their accuracy, which helps us draw useful insights for developing a robust unsolicited visual data classification system. This paper aims to bring clarity regarding the feasibility of using these techniques to develop an unsolicited visual data filtering system. This paper records that the most favourable results are obtained using Artificial Neural Networks.