Performance Comparison of SVM and K-NN for Oriya Character Recognition

Mohanty, Sanghamitra; Bebartta, Himadri Nandini Das

doi:10.14569/specialissue.2011.010116

Cited by 10 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Classifiers are frequently used approach, e.g. Hidden Markov Model -HMM (Bertero, Fung, 2017), K-Nearest Neighbour -KNN or Support Vector Machines -SVM (Bertero, Fung, 2017; Khan et al, 2011). We verified several classifiers in this work, considering simplicity and accuracy as main improvement factors.…”

Section: Introductionmentioning

confidence: 55%

Archives of Acoustics

Dimitrova-Grekow

Klis

Igras-Cybulska³

2019

View full text Add to dashboard Cite

The human voice is one of the basic means of communication, thanks to which one also can easily convey the emotional state. This paper presents experiments on emotion recognition in human speech based on the fundamental frequency. AGH Emotional Speech Corpus was used. This database consists of audio samples of seven emotions acted by 12 different speakers (6 female and 6 male). We explored phrases of all the emotions -all together and in various combinations. Fast Fourier Transformation and magnitude spectrum analysis were applied to extract the fundamental tone out of the speech audio samples. After extraction of several statistical features of the fundamental frequency, we studied if they carry information on the emotional state of the speaker applying different AI methods. Analysis of the outcome data was conducted with classifiers: K-Nearest Neighbours with local induction, Random Forest, Bagging, JRip, and Random Subspace Method from algorithms collection for data mining WEKA. The results prove that the fundamental frequency is a prospective choice for further experiments.

show abstract

Section: Introductionmentioning

confidence: 55%

Archives of Acoustics

Dimitrova-Grekow

Klis

Igras-Cybulska³

2019

View full text Add to dashboard Cite

show abstract

“…Performance comparison of SVM and K-NN for Oriya character recognition is reported in [6]. The authors mainly discuss feature vector-based classification methods, which have prevailed upon structural methods, especially in printed character recognition.…”

Section: Work On Other Oriya Charactersmentioning

confidence: 99%

Recognition of Isolated Handwritten Oriya Numerals using Hopfield Neural Network

Sarangi¹,

Sahoo²,

Ahmed³

2012

IJCA

View full text Add to dashboard Cite

Designing an automatic pattern recognition system is a challenging task. However, despite the design challenges, its enormous application potentials have attracted the attention of researchers and developers over the last four to five decades. Design of recognition systems for handwritten character applications has been a subject of intensive research, and the search is still on for a robust technique capable of dealing with natural variations in handwritten characters. In this paper the performance of Hopfield neural network (HNN) model in recognizing the handwritten Oriya (an Indian language) digits is addressed. The implementation has been carried out in two different ways. In first case, 290 test patterns (29 elements of each classes 0-9) created by different persons in Microsoft Paint were presented to the network in image form of 12×12. It is found that the network recognized 97.95% of the input characters correctly even if 40% of the input characters were having a significant level of noise. In the second experiment, the inputs were the collected handwritten characters in image format.A total of 1500 different input patterns were fed to the network sequentially and 95.4% recognition accuracy is achived. All the activities such as preprocessing of data (image cropping, resizing , digitization and implementations) have been carried out using MATLAB.

show abstract

“…In this research SVM classified bold, small, bold and big, normal and small, normal and bold. SVM achieved an accuracy of 98.9% as opposed to K-NN which achieved an accuracy of 96.47% [2]. A research on AHP-SVM in 500Kv Substation in which AHP decreased the amount of criteria used from twenty criteria to twelve criteria found could help the process of computation and in determining the main criteria [3].…”

Section: Introductionmentioning

confidence: 99%

Selection and Recommendation Scholarships Using AHP-SVM-TOPSIS

Putra

Ariyanti

Cholissodin

2016

JITeCS

View full text Add to dashboard Cite

Abstract. Gerakan Nasional Orang Tua Asuh Scholarship offers a number of scholarship packages. As there are a number of applicants, a system for selection and recommendation is required. we used 3 methods to solve the problem, the methods are AHP for feature selection, SVM for classification from 3 classes to 2 classes, and then TOPSIS give a rank recommendation who is entitled to receive a scholarship from 2 classes. In testing threshold for AHP method the best accuracy 0.01, AHP selected 33 from 50 subcriteria. SVM has highest accuracy in this research is 89.94% with Sequential Training parameter are λ =0.5, constant of γ =0.01 , ε = 0.0001, and C = 1. Keywords: Selection, Recommendation, Scholarships, AHP-SVM-TOPSIS

show abstract

Performance Comparison of SVM and K-NN for Oriya Character Recognition

Cited by 10 publications

References 13 publications

Archives of Acoustics

Archives of Acoustics

Recognition of Isolated Handwritten Oriya Numerals using Hopfield Neural Network

Selection and Recommendation Scholarships Using AHP-SVM-TOPSIS

Contact Info

Product

Resources

About