Bangla handwritten numeral character recognition using directional pattern

Aziz, Talha Ibn; Rubelt, Al Shahriar; Salekin, Sirajus; Kushol, Rafsanjany

doi:10.1109/iccitechn.2017.8281820

Cited by 15 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reference [51] investigated the performance of both GDP and LDP. Authors claimed that an ensemble of both features yields maximum accuracy of 95.62% on the CMATERdb dataset.…”

Section: A Feature Extractionmentioning

confidence: 99%

“…Majority of the ML-based works achieved the best results using Support Vector Machine [30], [43], [51]- [53], [60], [66], [72], [110], [114], [114] and Artificial Neural Networks [28], [44], [45], [49], [65], [75]. Apart from these two, other works on Bengali handwritten digit recognition employed Probabilistic Neural Networks [97], Hierarchical Bayesian Network [46], Bayesian Discriminant [119], k-Nearest Neighbor [48], Sparse Representation Classifier [47], Random Forests [99], Decision Tree (DT) [112], [113], Modified Quadratic Discriminant Function (MQDF) [118], etc.…”

Section: Classificationmentioning

confidence: 99%

“…Before applying SVM, it is important to normalize the feature vector to avoid the attributes having a very large numeric range so that all features get equal importance [66]. The most commonly used kernels in Bengali digit classification are linear kernel [30], [114], Gaussian kernel [30], Polynomial kernel [30], [51], [60], and RBF kernel [43], [66], [72], [110]. Reference [52] showed that linear kernels work better for a large number of features.…”

Section: ) Support Vector Machine (Svm)mentioning

confidence: 99%

See 2 more Smart Citations

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

“…Reference [51] investigated the performance of both GDP and LDP. Authors claimed that an ensemble of both features yields maximum accuracy of 95.62% on the CMATERdb dataset.…”

Section: A Feature Extractionmentioning

confidence: 99%

Section: Classificationmentioning

confidence: 99%

Section: ) Support Vector Machine (Svm)mentioning

confidence: 99%

See 1 more Smart Citation

Two Decades of Bengali Handwritten Digit Recognition: A Survey

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Researchers have presented different types of feature extraction techniques and proposed some new feature extraction techniques for recognizing handwritten Bengali characters. Since Bengali consists of differ-Ì ISSN: 2252-8938 ent parts such as the upper part, middle part, lower part, and disjunctive part, many researchers have developed anatomical feature extraction techniques [5], [6]. Since the characters can be divided into different zones, researchers have used a zone-based feature extraction method [7].…”

Section: Introductionmentioning

confidence: 99%

A machine learning approach for Bengali handwritten vowel character recognition

Ahsan

Nawaz

Sarwar

et al. 2022

IJ-AI

View full text Add to dashboard Cite

Recognition of handwritten characters is complex because of the different shapes and numbers of characters. Many handwritten character recognition strategies have been proposed for both English and other major dialects. Bengali is generally considered the fifth most spoken local language in the world. It is the official and most widely spoken language of Bangladesh and the second most widely spoken among the 22 posted dialects of India. To improve the recognition of handwritten Bengali characters, we developed a different approach in this study using face mapping. It is quite effective in distinguishing different characters. The real highlight is that the recognition results are more efficient than expected with a simple machine learning technique. The proposed method uses the Python library Scikit-Learn, including NumPy, Pandas, Matplotlib, and support vector machine (SVM) classifier. The proposed model uses a dataset derived from the BanglaLekha isolated dataset for the training and testing part. The new approach shows positive results and looks promising. It showed accuracy up to 94% for a particular character and 91% on average for all characters.

show abstract

“…Our goal is to detect these cooking state properly and provide a good knowledge of object states and manipulation to robots. Various kinds of image descriptors, specially pattern oriented descriptors [8], [9] have been popular for feature extraction in computer vision related problems. But recently, different types of Convolutional Neural Networks (CNN) [10] are producing very good results in image analysis such as object detection.…”

Section: Introductionmentioning

confidence: 99%

Cooking State Recognition from Images Using Inception Architecture

Salekin

Jelodar

Kushol

2019

2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)

Self Cite

View full text Add to dashboard Cite

A kitchen robot properly needs to understand the cooking environment to continue any cooking activities. But object's state detection has not been researched well so far as like object detection. In this paper, we propose a deep learning approach to identify different cooking states from images for a kitchen robot. In our research, we investigate particularly the performance of Inception architecture and propose a modified architecture based on Inception model to classify different cooking states. The model is analyzed robustly in terms of different layers, and optimizers. Experimental results on a cooking dataset demonstrate that proposed model can be a potential solution to the cooking state recognition problem.

show abstract

Bangla handwritten numeral character recognition using directional pattern

Cited by 15 publications

References 17 publications

Two Decades of Bengali Handwritten Digit Recognition: A Survey

Two Decades of Bengali Handwritten Digit Recognition: A Survey

A machine learning approach for Bengali handwritten vowel character recognition

Cooking State Recognition from Images Using Inception Architecture

Contact Info

Product

Resources

About