Optical character recognition in real environments using neural networks and k-nearest neighbor

2013 ◽  
Vol 39 (4) ◽  
pp. 739-748 ◽  
Author(s):  
O. Matei ◽  
P. C. Pop ◽  
H. Vălean
Keyword(s):  
Neural Networks ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Nearest Neighbor ◽  
K Nearest Neighbor ◽  
Optical Character

scholarly journals Automated Car Number Plate Recognition System using K-Nearest Neighbor

2019 ◽  
Vol 8 (10) ◽  
pp. 1113-1117
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Nearest Neighbor ◽  
Recognition System ◽  
Morphological Operation ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Classification ◽  
Optical Character ◽  
Neighbor Classification

The Automatic number plate recognition (ANPR) is a mass reconnaissance strategy that utilizations optical character recognition on images to peruse the license plates on vehicles. The car number plate detection has the various phases like pre-processing, segmentation and classification. In the previous work, the morphological operation is applied for the car number plate detection. The morphological operation has the low accuracy for the car number plate detection. In the proposed work, the region based segmentation and K-nearest neighbor classification is applied for the character recognition. The proposed is implemented in MATLAB and results are analyzed in terms of accuracy.

scholarly journals Using K-Nearest Neighbor in Optical Character Recognition

2016 ◽  
Vol 7 (1) ◽  
pp. 53 ◽  
Author(s):  
Veronica Ong ◽  
Derwin Suhartono
Keyword(s):  
Machine Learning ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Nearest Neighbor ◽  
Machine Learning Algorithms ◽  
K Nearest Neighbor ◽  
Optical Character ◽  
Training Samples ◽  
Computer Vision Technology ◽  
K Nearest Neighbor Algorithm

The growth in computer vision technology has aided society with various kinds of tasks. One of these tasks is the ability of recognizing text contained in an image, or usually referred to as Optical Character Recognition (OCR). There are many kinds of algorithms that can be implemented into an OCR. The K-Nearest Neighbor is one such algorithm. This research aims to find out the process behind the OCR mechanism by using K-Nearest Neighbor algorithm; one of the most influential machine learning algorithms. It also aims to find out how precise the algorithm is in an OCR program. To do that, a simple OCR program to classify alphabets of capital letters is made to produce and compare real results. The result of this research yielded a maximum of 76.9% accuracy with 200 training samples per alphabet. A set of reasons are also given as to why the program is able to reach said level of accuracy.

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

2021 ◽  
Author(s):  
Shaik Johny Basha ◽  
D. Veeraiah ◽  
G. Pavani ◽  
Sk. T. Afreen ◽  
P. Rajesh ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Optical Character ◽  
Novel Approach

Optical Character Recognition of Indian Language Manuscripts using Convolutional Neural Networks

2021 ◽  
pp. 894-911
Author(s):  
Bhavesh Kataria, Dr. Harikrishna B. Jethva
Keyword(s):  
Neural Networks ◽  
Character Recognition ◽  
Optical 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.

scholarly journals Character Recognition And Extraction of An Indian State License Plates Using K-NN

2019 ◽  
Author(s):  
Rajasekhar Ponakala ◽  
Hari Krishna Adda ◽  
Ch. Aravind Kumar ◽  
Kavya Avula ◽  
K. Anitha Sheela
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Nearest Neighbor ◽  
Extraction Process ◽  
License Plate ◽  
K Nearest Neighbor ◽  
Open Hardware ◽  
Character Extraction ◽  
Indian State ◽  
High Level

License plate recognition is an application-specific optimization in Optical Character Recognition (OCR) software which enables computer systems to read automatically the License Plates of vehicles from digital images. This thesis discusses the character extraction from the respective License Plates of vehicles and problems in the character extraction process. An OCR based training algorithm named k-nearest neighbor with predefined OpenCV libraries is implemented and evaluated in the BeagleBone Black Open Hardware. In an OCR, the character extraction involves certain steps which include Image acquisition, Pre-processing, Feature extraction, Detection/ Segmentation, High-level processing, Decision making. A key advantage of the method is that it is a fairly straightforward technique which utilizes from k-nearest neighbor algorithm segments normalized result as a format in text. The results show that training an image with this algorithm gives better results when compared with other algorithms.

scholarly journals Pashtu Numerals Recognition through Convolutional Neural Networks

2019 ◽  
pp. 91-96
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
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%.

scholarly journals Expiry date recognition using deep neural networks

2020 ◽  
Vol 13 (1) ◽  
pp. 1-17
Author(s):  
Traian Rebedea ◽  
Vlad Florea
Keyword(s):  
Neural Networks ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Speech Synthesis ◽  
Efficient Solution ◽  
Deep Neural Networks ◽  
Accuracy Improvement ◽  
Expiry Date ◽  
Food Items ◽  
Optical Character

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.

Sign in / Sign up

Export Citation Format

Share Document