A self controlled RDP approach for feature extraction in online handwriting recognition using deep learning

Singh, Sukhdeep; Chauhan, Vinod Kumar; Smith, Elisa H. Barney

doi:10.1007/s10489-020-01632-4

Cited by 11 publications

(5 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From preprocessing to feature selection, the sports action information is extracted from the underlying data, and then the category is marked by the classifier to complete the action recognition. The process of action recognition is to obtain high-level action information through the bottom data, so as to learn the action characteristics and finally realize the process of action classification [ 28 ]. Good feature expression is critical to the final accuracy of the algorithm.…”

Section: Methodsmentioning

confidence: 99%

Sports Action Recognition Based on Deep Learning and Clustering Extraction Algorithm

Zhong

Dong

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

This paper constructs a sports action recognition model based on deep learning (DL) and clustering extraction algorithm. For the input detection image frame, athletes’ movements are detected through DL network, and then athletes’ sports movements are fused. Moreover, it expands new knowledge and improves learning ability through automatic learning training set. The neural network (NN) is applied to the sample set containing images of nonathletes, and the negative training sample set is iteratively enhanced according to the generated false positives, and the results are optimized by clustering method. Simulation experiments show that compared with other algorithms, the clustering extraction algorithm in this paper has achieved superior performance in recognition rate and false alarm rate, and the recognition speed is faster. The aim is to extract the athletes’ training postures through the analysis of sports movements, so as to assist coaches to train athletes more professionally and provide some reference for sports movement recognition.

show abstract

Section: Methodsmentioning

confidence: 99%

Sports Action Recognition Based on Deep Learning and Clustering Extraction Algorithm

Zhong

Dong

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…The average recognition accuracy for Kannada vowel consonant combination in proposed solution is at least 10% higher compared to Prashanth et al, 16% higher compared to Kaur et al and 6% higher compared to Singh et al The false positives for Kannada vowel consonant combination in proposed solution is almost 11% lower compared to Prashanth et al (11) , 16% lower compared to Kaur et al (13) and 10% lower compared to Singh et al (19) . Compared to Vowels, the recognition accuracy in proposed solution for consonants has reduced by 1%.…”

Section: Resultsmentioning

confidence: 80%

“…The performance is measured in terms of: recognition accuracy and false positives. The performance is compared against Modified Lenet proposed by Prashanth et al (11) , image gradient with SVM proposed by Kaur et al (13) and RDP approach proposed in Singh et al (19) . The recognition accuracy is measured for vowels and the result is given in Table 2.…”

Section: Resultsmentioning

confidence: 99%

“…Table 5. False positives for consonants False positives Proposed Prashanth et al (11) Kaur et al (13) Singh et al ( (11) Kaur et al (13) Singh et al ( (11) Kaur et al (13) Singh et al (19) The false positives are measured for Vowel consonant combination and the result is given in Table 7.…”

Section: Resultsmentioning

confidence: 99%

“…The study inferred that moving average filter with window span of 3 improved the recognition accuracy of Kannada characters. In (19) stoke features were extracted using self controlled Ramer-Douglas-Peucker (RDP) algorithm and stroke features classified to characters using one dimensional CNN. The method was tested for Gurmukhi scripts, whose complexity is less compared to Kannada scripts.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Two Stage Multi Modal Deep Learning Kannada Character Recognition Model Adaptive to Discriminative Patterns of Kannada Characters

Siddanna¹,

Kiran²

2023

IJST

View full text Add to dashboard Cite

Objectives: Designing optical character recognition systems for Kannada character is challenging due to higher self-similarity in characters and higher number of character classes. This work addresses the two major problems of reduced accuracy and higher false positives due to higher self-similarity in characters. Methods: This work proposes a two stage multi modal deep learning technique to handle the complexity in Kannada character recognition. The characters are first grouped based on morphological and structural similarity. A novel morphological/structural difference maximization convolution kernel based deep learning modal is trained for each of character group to recognize characters in that group. This divide and conquer strategy reduce the complexity of deep learning model in learning discriminative features for Kannada character recognition. Findings: The proposed two stage multi modal deep learning provides 89% recognition accuracy which is at least 6% higher compared to existing works. The false positives in proposed solution are at least10% lower compared to existing works. Novelty: A novel sector intensity distribution feature specific to curve structure of Kannada characters for deciding the number of groups of characters. Classifier is designed for each group of characters. Classification is done using convolutional neural network with a novel morphological/structural difference maximization convolution kernel to solve the structural similarity problem in Kannada character recognition.

show abstract

Handwritten Font Image Design System Based on Deep Learning Algorithm

Lin¹

2021

The 2021 International Conference on Machine Learning and Big Data Analytics for IoT Security and Privacy

View full text Add to dashboard Cite

A self controlled RDP approach for feature extraction in online handwriting recognition using deep learning

Cited by 11 publications

References 55 publications

Sports Action Recognition Based on Deep Learning and Clustering Extraction Algorithm

Sports Action Recognition Based on Deep Learning and Clustering Extraction Algorithm

Two Stage Multi Modal Deep Learning Kannada Character Recognition Model Adaptive to Discriminative Patterns of Kannada Characters

Handwritten Font Image Design System Based on Deep Learning Algorithm

Contact Info

Product

Resources

About