Figure 4 - uploaded by Ganapatsingh G Rajput
Content may be subject to copyright.
Source publication
A mixer of printed and handwritten numerals may appear in a single document such as application forms, postal mail, and official documents. The process of identifying of such mixed numerals and sending it to respective OCRs is a complex task. In this paper, we present a novel method for recognition of printed and hand written isolated Kannada numer...
Context in source publication
Similar publications
In this research, recognition accuracy of a rank based shape classification method is measured in recognizing the totally unconstrained handwritten digits. Experimental results on real-life sample data that was collected from postal zip codes written by mail writers show that the suggested classification scheme correctly classifies 98.5% training d...
Ever since character recognition originated, its potential use in the automation of mail sorting has been a vogue area of research. Despite over 50 years of research [2], this has not come to complete implementation even in highly voluminous postal systems like the Indian postal system. This paper proposes a pragmatic way of solving this historical...
Objective: to describe the epidemiological profile of pension benefits paid to victims of traumatic brain injury (TBI) due to occupational accidents in Brazil, in 2009. Method: this descriptive epidemiological study which was conducted with all workers who are part of the General System of Social Security in Brazil. Secondary data from the Single I...
In the field of Optical Character Recognition (OCR), zoning is used to extract topological information from patterns. In this paper we propose Zone based features for recognition of the mixer of Handwritten and Printed Kannada Digits. A digit image is divided into 64 zones and pixel density is computed for each zone. This procedure is sequentially...
This article discusses the process undertaken to develop and validate the Leave No Trace (LNT) Attitudinal Inventory and Measure (LNT AIM), an instrument designed to measure attitudes regarding specific practices addressed by the LNT Principles for Responsible Recreation. We envision this tool being useful for determining the necessity for LNT educ...
Citations
... The first type is divided into two sub-divisions: (a) Optical Character Recognition (OCR), and (b) Manual Character Recognition (MCR) [3]. Various methods of identification were reviewed, for example handwritten numerals [4,5], printed and handwritten mixed kannada numerals [6], writings and scripts of Arabic [7], Arabic numbers [8], Vietnamese character recognition [9], and license plate recognition [10]. In general, all studies aim to obtain the best possible accuracy in identification, but feature extraction methodologies and classification methods vary. ...
Optical Character Recognition (OCR) research includes computer vision, artificial intelligence, and pattern recognition. Character recognition has garnered a lot of attention in the last decade due to its broad variety of uses and applications, including multiple-choice test data, business documents (e.g., ID cards, bank notes, passports, etc.), and automatic number plate recognition. This paper introduces an automatic recognition system for printed numerals. The automatic reading system is based on extracting local statistical and geometrical features from the text image. Those features are represented by eight vectors extracted from each digit. Two of these features are local statistical (A, A th), and six are local geometrical (P 1 , P 2 , P 3 , P 4 , P 5 , and P 6). Thus, the database created consists of 1120 statistical and geometrical features. For the purpose of recognition, the features of the test image are compared with the features of all the images saved in the database depending on the value of the Minimum Distance (MD). All digits (0-9) were identified with 100% accuracy. The average computational time required to recognize a numeral at any font size is 0.06879 seconds.
... The classification and recognition is carried out using a feed forward back propagation neural network a recognition accuracy of 98% and 96% are obtained for Kannada and Telugu numerals respectively. The problem of recognizing printed and handwritten numerals seen in various documents has been addressed by Rajput et al. [8] where a Support Vector Machine based classification is implemented. Scanned numerals are converted to binary image and normalized to a size of 40 x 40. ...
Handwritten digit recognition is one of the classical issues in the field of image grouping, a subfield of computer vision. The event of the handwritten digit is generous. With a wide opportunity, the issue of handwritten digit recognition by using computer vision and machine learning techniques has been a well-considered upon field. The field has gone through an exceptional turn of events, since the development of machine learning techniques. Utilizing the strategy for Support Vector Machine (SVM) and Principal Component Analysis (PCA), a robust and swift method to solve the problem of handwritten digit recognition, for the Kannada language is introduced. In this work, the Kannada-MNIST dataset is used for digit recognition to evaluate the performance of SVM and PCA. Efforts were made previously to recognize handwritten digits of different languages with this approach. However, due to the lack of a standard MNIST dataset for Kannada numerals, Kannada Handwritten digit recognition was left behind. With the introduction of the MNIST dataset for Kannada digits, we budge towards solving the problem statement and show how applying PCA for dimensionality reduction before using the SVM classifier increases the accuracy on the RBF kernel. 60,000 images are used for training and 10,000 images for testing the model and an accuracy of 99.02% on validation data and 95.44% on test data is achieved. Performance measures like Precision, Recall, and F1-score have been evaluated on the method used.
... Support Vector Machine Theory is the main machine learning method of Statistical Learning Theory. Support Vector Machine Theory is widely used in text identification in complex background [5] , handwritten font recognition [6] , facial recognition [7] , and other fields due to its ability to resist "high-dimensional disaster" and "over-learning". Support vector machine can transform a problem to "solve quadratic programming with constrained condition" problem. ...
In the production process of electronic components such as capacitors, bubble defects will occur inside the devices, which will lead to the loss of the functions of electronic components. Traditional methods for detecting bubble defects have many problems, such as low efficiency and low accuracy. Aiming at the bubble defects of the existing electronic components, an SVM-based detection method was proposed, which combined machine learning and image processing to complete the automatic detection of the bubble defects of electronic components. By using the feedback method, the error results obtained from the model classification are added to the training sample set, so that the problems of insufficient sample quantity and incorrect sample classification are solved. The accuracy of the proposed method was verified by capacitor component samples. The accuracy rate was 98.95%, the emission rate was 0.12%, and the error rate was 0.93%. It can be seen that the method proposed in this paper has a good effect on the defect detection of electronic components with the capacitor as an example.
... In [11], the authors used a nearest neighbor classifier to achieve 91% accuracy of 250 test numerals. Support Vector Machines (SVMs) were used to achieve 98% accuracy on a small dataset of 5000 40 × 40 numeral-images in [12]. The largest dataset currently used in academic literature that contains Kannada characters is the Chars74k dataset [13] that contains 657 characters of the Kannada script collected using a tablet PC, albeit with a mere 25 samples per-number. ...
In this paper, we disseminate a new handwritten digits-dataset, termed Kannada-MNIST, for the Kannada script, that can potentially serve as a direct drop-in replacement for the original MNIST dataset. In addition to this dataset, we disseminate an additional real world handwritten dataset (with $10k$ images), which we term as the Dig-MNIST dataset that can serve as an out-of-domain test dataset. We also duly open source all the code as well as the raw scanned images along with the scanner settings so that researchers who want to try out different signal processing pipelines can perform end-to-end comparisons. We provide high level morphological comparisons with the MNIST dataset and provide baselines accuracies for the dataset disseminated. The initial baselines obtained using an oft-used CNN architecture ($96.8\%$ for the main test-set and $76.1\%$ for the Dig-MNIST test-set) indicate that these datasets do provide a sterner challenge with regards to generalizability than MNIST or the KMNIST datasets. We also hope this dissemination will spur the creation of similar datasets for all the languages that use different symbols for the numeral digits.
... Authors mainly focused on creating a standard data set to provide framework for other related researches and helps in overcoming lack of data set for Kannada character set. Recognition of printed and handwritten Kannada numerals is discussed in [3] using SVM (Support Vector Machine) technique. Authors have worked on identifying handwritten numerals by mixing both printed and handwritten dataset and classified them using SVM. ...
... Support vector machine is used for subsequent classification and recognition purpose. Recognition of printed and hand written isolated Kannada numerals using single OCR system is presented in [34]. Here, printed/hand written Kannada numeral is scanned and converted to binary image and normalized to a size of 40 9 40 pixels. ...
Even though various advances have been made in recent years, the recognition of handwritten characters is still an open challenge in the Pattern Recognition field. Different approaches are invented for the recognition of printed characters of Indian languages. However, few attempts are done for the recognition of handwritten characters. A high degree of recognition accuracy for the handwritten characters is yet to be achieved. In this paper, a new approach based on deep belief network with the distributed average of gradients feature is presented for the recognition of isolated handwritten characters of Kannada, which is the official language of Karnataka state in India. In the proposed methods, a better accuracy is achieved. © 2018 Springer Science+Business Media, LLC, part of Springer Nature
... The recognition accuracy of 99.78% was achieved with minimum computational and storage requirements [4]. A method for recognition of printed and handwritten mixed Kannada numerals is presented using multi-class SVM for recognition yielding a recognition accuracy of 97.76% [5]. Ragha & Sasikumar describes system for Kannada characters. ...
... Here in the present work, the image is processed such that its character is recognized. The major problem which arises while identifying the characters in printed or handwritten is the difference in the style in literature [5]. Template matching, or matrix matching, is one of the most common classification methods. ...
... In this paper it use same Gaussian filter for filtering, the Gaussian filter smoothing the image and it helps find edges of characters accurately. In [5] authors concentrate Printed Number Recognition using MATLAB. ...
Rapid growth of technology and prevalent use of computer in the business and other areas, more and more organization are converting their paper document into electronic documents that can be processed by computer. Kannada, the native language of south western state in India has more than 60 million in Karnataka and outside. Much research has been done on the identification of English, Arabic, Japanese and Chinese. It is observed that the research on recognition of Kannada characters is still an open research problem. In this paper, an attempt has been made to develop a simple and efficient method for the Recognition of Kannada printed and handwritten characters. Here in the present work, the images of Kannada printed and handwritten characters are captured from an ordinary mobile camera of 5 Mega pixel resolutions and images are pre-processed to remove noise. Here it recognizes the Kannada characters based on template matching, and a character is identified by analyzing its shape and comparing its features that distinguish each character. Cross correlation technique is implemented in matching the characters. Experimental results shows, it demonstrates relatively high accuracy in recognizing both printed and handwritten characters and with better time efficiency when compared to previous methods.
... f * g τ f t g t τ dt (6) Where f* denotes the complex conjugate of f and is the time lag. Similarly, for discrete functions, the crosscorrelation is defined as: ...
Stone in-scripted literature speaks about the history, language of different regions of the world. Preservation of such document through digitalization process is become very important. To stop degradation and missing further, the analysis of the same will through light on historical events of that region. In this connection present work proposes a simple method of digitization using ordinary digital camera further, the pre-processing algorithm is implemented to enhance the image and improve the readability. Here it recognizes the Kannada characters based on template matching. In this method is normally implemented by first picking template and then it call the search image, then by simply comparing the template over each point in the search image and it calculate the sum of products between the coefficient. Based on this calculated product value it recognizes the character. Cross correlation technique is implemented in matching the characters coefficient. Experimental results shows, it demonstrates relatively high accuracy in recognizing Stone inscriptions characters of both Hoysala, Ganga time frames and with better time efficiency when compared to previous methods. Copyright © 2014 Institute of Advanced Engineering and Science. All rights reserved.
... A method for dating of the Greek inscription's content [7] uses "platonic" realization of alphabet symbols for the specific inscription and various Geometric characteristics for the features, and classifies the period according to some statistical criteria. A study for the recognition of ancient middle Persian documents [8] chooses a set of invariant moments as the features and the classifiers used are minimum mean distance, k-Nearest Neighbours (KNN) and Parzen. A classification rate of 90.5%-95% was achieved in that. ...
Ancient inscriptions which reveal the details of yester years are difficult to interpret by modern readers and efforts are being made in automating such tasks of deciphering historical records. The Kannada script which is used to write in Kannada language has gradually evolved from the ancient script known as Brahmi. Kannada script has traveled a long way from the earlier Brahmi model and has undergone a number of changes during the regimes of Ashoka, Shatavahana, Kadamba, Ganga, Rashtrakuta, Chalukya, Hoysala , Vijayanagara and Wodeyar dynasties. In this paper we discuss on Classification of ancient Kannada Scripts during three different periods Ashoka, Kadamba and Satavahana. A reconstructed grayscale ancient Kannada epigraph image is input, which is binarized using Otsu’s method. Normalized Central and Zernike Moment features are extracted for classification. The RF Classifier designed is tested on handwritten base characters belonging to Ashoka, Satavahana and Kadamba dynasties. For each dynasty, 105 handwritten samples with 35 base characters are considered. The classification rates for the training and testing base characters from Satavahana period, for varying number of trees and thresholds of RF are determined. Finally a Comparative analysis of the Classification rates is made for the designed RF with SVM and k-NN classifiers, for the ancient Kannada base characters from 3 different eras Ashoka, Kadamba and Satavahana period.
