Language-invariant novel feature descriptors for handwritten numeral recognition

Ghosh, Soulib; Chatterjee, Agneet; Singh, Pawan Kumar; Bhowmik, Showmik; Sarkar, Ram

doi:10.1007/s00371-020-01938-x

Cited by 17 publications

(8 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this end, the proposed algorithm is compared with several different algorithms. For example, shape features (SF) [ 25 ] using random forest and MLP for classification are considered in the comparison based on Arabic numeral recognition. In addition, convolutional neural network (CNN), which is proposed in [ 19 ] for Arabic handwritten numerals, is also used here in the comparison.…”

Section: Resultsmentioning

confidence: 99%

“…To this end, a regional weighted run length feature (RWRLF) [ 28 ] algorithm, wherein the SVM and MLP classifier are employed for classification, is used here for comparison. The rest of the methods that are compared here are similar to those already used with the Roman and Arabic numeral recognition, which are MF-based MLP and SVM classifiers [ 6 ], SF [ 25 ] with random forest and MLP classifier, and STFC with SVM classifier [ 26 ]. Table 5 presents the accuracy comparison of different recognition with their corresponding classifiers.…”

Section: Resultsmentioning

confidence: 99%

“…Two shape-based feature descriptors, which are termed as a Point-Light Source-based Shadow (PLSS) and Histogram of Oriented Pixel Positions (HOPP), have been proposed in [ 25 ]. The proposed framework has been implemented using ten of the available datasets of handwritten digits, which are written in eight different languages and one numeric string recognition dataset.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

A Robust Handwritten Numeral Recognition Using Hybrid Orthogonal Polynomials and Moments

Abdulhussain

Mahmmod

Naser

et al. 2021

Sensors

View full text Add to dashboard Cite

Numeral recognition is considered an essential preliminary step for optical character recognition, document understanding, and others. Although several handwritten numeral recognition algorithms have been proposed so far, achieving adequate recognition accuracy and execution time remain challenging to date. In particular, recognition accuracy depends on the features extraction mechanism. As such, a fast and robust numeral recognition method is essential, which meets the desired accuracy by extracting the features efficiently while maintaining fast implementation time. Furthermore, to date most of the existing studies are focused on evaluating their methods based on clean environments, thus limiting understanding of their potential application in more realistic noise environments. Therefore, finding a feasible and accurate handwritten numeral recognition method that is accurate in the more practical noisy environment is crucial. To this end, this paper proposes a new scheme for handwritten numeral recognition using Hybrid orthogonal polynomials. Gradient and smoothed features are extracted using the hybrid orthogonal polynomial. To reduce the complexity of feature extraction, the embedded image kernel technique has been adopted. In addition, support vector machine is used to classify the extracted features for the different numerals. The proposed scheme is evaluated under three different numeral recognition datasets: Roman, Arabic, and Devanagari. We compare the accuracy of the proposed numeral recognition method with the accuracy achieved by the state-of-the-art recognition methods. In addition, we compare the proposed method with the most updated method of a convolutional neural network. The results show that the proposed method achieves almost the highest recognition accuracy in comparison with the existing recognition methods in all the scenarios considered. Importantly, the results demonstrate that the proposed method is robust against the noise distortion and outperforms the convolutional neural network considerably, which signifies the feasibility and the effectiveness of the proposed approach in comparison to the state-of-the-art recognition methods under both clean noise and more realistic noise environments.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Robust Handwritten Numeral Recognition Using Hybrid Orthogonal Polynomials and Moments

Abdulhussain

Mahmmod

Naser

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…14). In a more recent work, [99] proposed a single light source-based shadow feature named Point Light Sourcebased Shadow (PLSS). The shadow changes if the position of the light source is changed (Fig.…”

Section: F: Projection Histogrammentioning

confidence: 99%

“…Pixel density is another statistical feature that is often used in different image classification tasks. It counts the number of black pixels within a region of interest; be it the whole image Reference [99] divided the image into eight octants and created a histogram called Histogram of Oriented Pixel Positions (HOPP), counting the number of black pixels within the region. HOPP feature is combined with the PLSS feature to achieve 98.5% accuracy on CMATERdb 3.1.1 dataset.…”

Section: C: Pixel Densitymentioning

confidence: 99%

Two Decades of Bengali Handwritten Digit Recognition: A Survey

et al. 2022

View full text Add to dashboard Cite

Handwritten Digit Recognition (HDR) is one of the most challenging tasks in the domain of Optical Character Recognition (OCR). Irrespective of language, there are some inherent challenges of HDR, which mostly arise due to the variations in writing styles across individuals, writing medium and environment, inability to maintain the same strokes while writing any digit repeatedly, etc. In addition to that, the structural complexities of the digits of a particular language may lead to ambiguous scenarios of HDR. Over the years, researchers have developed numerous offline and online HDR pipelines, where different image processing techniques are combined with traditional Machine Learning (ML)-based and/or Deep Learning (DL)-based architectures. Although evidence of extensive review studies on HDR exists in the literature for languages, such as English, Arabic, Indian, Farsi, Chinese, etc., few surveys on Bengali HDR (BHDR) can be found, which lack a comprehensive analysis of the challenges, the underlying recognition process, and possible future directions. In this paper, the characteristics and inherent ambiguities of Bengali handwritten digits along with a comprehensive insight of two decades of the state-of-the-art datasets and approaches towards offline BHDR have been analyzed. Furthermore, several real-life applicationspecific studies, which involve BHDR, have also been discussed in detail. This paper will also serve as a compendium for researchers interested in the science behind offline BHDR, instigating the exploration of newer avenues of relevant research that may further lead to better offline recognition of Bengali handwritten digits in different application areas.

show abstract

Genetic Algorithm Based Global and Local Feature Selection Approach for Handwritten Numeral Recognition

Chowdhury

Majumdar

Kumar

et al. 2021

Metaheuristics in Machine Learning: Theory and Applications

View full text Add to dashboard Cite

Language-invariant novel feature descriptors for handwritten numeral recognition

Cited by 17 publications

References 55 publications

A Robust Handwritten Numeral Recognition Using Hybrid Orthogonal Polynomials and Moments

A Robust Handwritten Numeral Recognition Using Hybrid Orthogonal Polynomials and Moments

Two Decades of Bengali Handwritten Digit Recognition: A Survey

Genetic Algorithm Based Global and Local Feature Selection Approach for Handwritten Numeral Recognition

Contact Info

Product

Resources

About