Evil method: A deep CNN model for Bangla handwritten numeral classification

Sharif, S. M. A.; Mahboob, Mahdin

doi:10.1109/icaee.2017.8255356

Cited by 5 publications

(13 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…9(b)). Hence, the existing literature on BHDR rotated the digit images by a randomly chosen rotation angle within a range of 0 to 50 degrees on either direction [36], [39], [42], [61]- [63], [73], [77], [82]. One key consideration is that, after performing rotation, additional pixels are padded to preserve the original dimension of the image [73].…”

Section: A Geometric Transformation 1) Rotation and Flippingmentioning

confidence: 99%

“…Shearing in this manner can help the model learn to recognize slanted texts. Apart from that, application elastic transform [62] and grid distortions [39] are also used to distort the digit images (Fig. 9(g)).…”

Section: ) Distortionmentioning

confidence: 99%

“…Reference [39] proposed an image augmentation method on the ISI-HBN dataset with a CNN model, which achieved 99.42% validation accuracy. The augmentation method downsamples the images into lower dimensions and then upsamples them again into the original dimension.…”

Section: ) Custom Cnn-based Modelsmentioning

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

Section: A Geometric Transformation 1) Rotation and Flippingmentioning

confidence: 99%

Section: ) Distortionmentioning

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

“…The first augmentation method is a random rotation of the training sample, where source image (I ) has been randomly rotated between (−50, +50) degree. Another augmentation has been done by applying block effect, thus the source image can lose some image quality [37]. The third augmentation considered as a wrapping operation, where the location information has been shifted between (−5, +5) pixels horizontally or (−5, +5) pixels vertically [37].…”

Section: Data Augmentationmentioning

confidence: 99%

“…Another augmentation has been done by applying block effect, thus the source image can lose some image quality [37]. The third augmentation considered as a wrapping operation, where the location information has been shifted between (−5, +5) pixels horizontally or (−5, +5) pixels vertically [37]. As a result, three versions of each training image has been obtained by the augmentation.…”

Section: Data Augmentationmentioning

confidence: 99%

Deep Hog: A Hybrid Model to Classify Bangla Isolated Alpha-Numerical Symbols

Sharif¹,

Mahboob²

2019

NNW

Self Cite

View full text Add to dashboard Cite

Bangla is known to be the second most widely used script in the South Asian region. Despite its wide usage, a complete study with all available Bangla handwritten image classes is still due. This work proposes a hybrid model to classify all available handwritten image classes and unifying the existing benchmark datasets. The feasibility of the different handcrafted features in the hybrid model also has been demonstrated. Moreover, the proposed hybrid model obtain a maximum accuracy of 89.91 % in validation phase with a total of 259 Bangla alpha-numerical image classes. With the same number of image classes, the proposed hybrid model shows a testing accuracy of 89.28 % on 15,175 testing samples. The comparison results demonstrate that the proposed hybrid-HOG model can outperform the existing state-of-the-art classification models in Bangla handwritten alpha-numerical image classification. The code will be available on https://github.com/sharif-apu/hybrid-259.

show abstract

Optimizing Malware Detection for IoT and Edge Environments With Quantization Awareness

Alandjani

2024

IEEE Access

View full text Add to dashboard Cite

Evil method: A deep CNN model for Bangla handwritten numeral classification

Cited by 5 publications

References 21 publications

Two Decades of Bengali Handwritten Digit Recognition: A Survey

Two Decades of Bengali Handwritten Digit Recognition: A Survey

Deep Hog: A Hybrid Model to Classify Bangla Isolated Alpha-Numerical Symbols

Optimizing Malware Detection for IoT and Edge Environments With Quantization Awareness

Contact Info

Product

Resources

About