Exploiting features from triangle geometry for digit recognition

Azmi, Mohd Sanusi; Nasrudin, Mohammad Faidzul; Omar, Khairuddin; Ahmad, Che Wan Shamsul Bahri Che; Ghazali, Khadijah Wan Mohd

doi:10.1109/codit.2013.6689658

Cited by 9 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reference [109] used the global centroid to divide the image vertically into two regions. A scalene triangle was created using the three centroids (one global centroid and two centroids of two regions) as the corner points.…”

Section: B: Centroidsmentioning

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

Section: B: Centroidsmentioning

confidence: 99%

Two Decades of Bengali Handwritten Digit Recognition: A Survey

et al. 2022

View full text Add to dashboard Cite

show abstract

“…There are some segmentation techniques for Arabic and Jawi characters [2]. One of the techniques has categorised the preprocessing phase for the Arabic/Jawi character recognition Frame Removal For Mushaf Al-Quran Using Irregular Binary Region into Binarisation, Edge Detection, Thinning, and Segmentation before Feature Extraction takes place [2]- [6]. In [7], they used the triangle features to the feature extraction method for better classification.…”

Section: Related Workmentioning

confidence: 99%

Frame Removal For Mushaf Al-Quran Using Irregular Binary Region

Melhem¹

2019

IJATCSE

View full text Add to dashboard Cite

Segmentation is a process to remove frame or frame exists in each page of some releases of mushaf Al-Quran. The fault in segmentation process affects the holiness of Al-Quran. The difficulty to identify the appearance of frame around text areas as well as noisy black stripes has caused the segmentation process to be improperly carried out. In this paper, an algorithm for detecting the frame on Al-Quran page without affecting its content is proposed. Firstly, preprocessing was carried out by using the binarisation method. Then, it was followed with the process of detecting the frame in each page. In this stage, the proposed algorithm was applied by calculating the percentage of black pixel of binary from vertical (column) to horizontal (row). The results, based on experiments on several Al-Quran pages from different Al-Quran styles, demonstrate the effectiveness of the proposed technique.

show abstract

“…Using ConvNet as Learning features prove to be successful in handwritten recognition and recently object recognition [10][11] [12]. Learning features optimize the data representation of specific tasks.…”

Section: F Learning Features and Multi-classifiermentioning

confidence: 99%

Multi-Classifier Jawi Handwritten Sub-Word Recognition

Hasan

Omar

Nasrudin

2018

Int. J. Adv. Sci. Eng. Inf. Technol.

Self Cite

View full text Add to dashboard Cite

The problems and challenges in Jawi handwritten recognition are inherited from Arabic script which consists of cursive natures, large variety of writing styles due to its morphologically rich, ligature, overlapping characters, dialects and the low quality of the manuscripts images. The word segmentation is difficult because the existence of sub words due to the presence of space within words when contain disconnect characters. The performance of previous Jawi handwritten recognition still consider sub-par. There are three main problem of previous approach. First, the recognizer consist of multiple independent components where the improvement of performance in one component not shared across the systems. Secondly, the features extraction using features engineering approach only works on specific subsets of training data and is less capable to handle broader variants of testing data. Finally, the classifier used implicit segmentation where target class is sub-word with limited lexicon. This paper propose use of Deep Learning approach to address the first problem where training is conducted end-to-end from input to class output which enable the improvement of each component to improve overall performance. Secondly, Convolutional Network is use as learning features optimizes the data representation through end-to-end training of the parameters from raw input data to target class. Finally, A multiclassifier implicitly segments the sub-word into sequences of characters are proposed. The classifiers consists of one sub-word length classifier and seven character classifiers. This approach is lexicon-free to address absent of lexicon data. Experiments conducted on a Jawi handwritten standard dataset showed an accuracy of up to 92.20% and suggest that the approach used is superior to state-ofthe-art methods of Jawi handwriting recognition.

show abstract

Exploiting features from triangle geometry for digit recognition

Cited by 9 publications

References 9 publications

Two Decades of Bengali Handwritten Digit Recognition: A Survey

Two Decades of Bengali Handwritten Digit Recognition: A Survey

Frame Removal For Mushaf Al-Quran Using Irregular Binary Region

Multi-Classifier Jawi Handwritten Sub-Word Recognition

Contact Info

Product

Resources

About