Novel Geometrical Shape Feature Extraction Techniques for Multilingual Character Recognition

Soora, Narasimha Reddy; Deshpande, Parag S.

doi:10.1080/02564602.2016.1229583

Cited by 18 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, OCR systems are capable of achieving better performance for scanned documents or images when compared with the images captured by the cameras. In general, several issues are present in the various OCR systems which suffer from different types of issues such as scene complexity [22], uneven lighting conditions [23], document text skewness [24] and multilingual environment [25] resulting in poor performance of OCR applications.…”

Section: A Issues and Challenges In Ocr Systemsmentioning

confidence: 99%

“…Based on the touching character segmentation study, Xu et al [38] proposed feature extraction-based character segmentation method for Chinese handwritten documents. As discussed in [25], [35] this method also uses contour tracing and skeletonization process which helps to identify the character separation. Later, a filter is designed with the help of the supervised learning scheme which helps to remove the unwanted cuts resulting in improved precision.…”

Section: Literature Surveymentioning

confidence: 99%

See 1 more Smart Citation

An Experimental Technique for OCR Line and Word Segmentation using Probability Distribution Estimation

2019

ijrte

View full text Add to dashboard Cite

Segmentation is always an important step in designing an Optical Character Recognition (OCR) of any script. In this paper, we focus on the line and word segmentation in typewritten Gurmukhi script documents. In order to perform this task, we consider OCR based methodology where several processing steps are implemented. The typewritten documents suffer from several issues such as noise, skew, and quality of the document. In this work, we present a combined pre-processing scheme where document thresholding and skew detection and correction schemes are implemented where image thresholding is obtained using Niblack’s method and skew correction is carried out using gradient histogram algorithm and uniform orientation is obtained. Later, line segmentation scheme is applied where probability density function is applied to generate the text distribution in the probability map. Here, identifying the relation of the text to the exact line is a challenging task hence, we present a 2D-Gaussian modelling which helps to identify the text boundaries in the x and y direction. The proposed methodology is applied for typewritten Gurmukhi documents and an experimental study is carried out to show that the proposed approach achieves better performance when compared with the existing techniques

show abstract

Section: A Issues and Challenges In Ocr Systemsmentioning

confidence: 99%

Section: Literature Surveymentioning

confidence: 99%

An Experimental Technique for OCR Line and Word Segmentation using Probability Distribution Estimation

2019

ijrte

View full text Add to dashboard Cite

show abstract

“…A novel feature extraction technique is proposed by Soora and Deshpande [8] towards multilingual character recognition of Indian scripts namely, English, Devanagari, and Marathi. They present a set of feature vectors (FVs) based on shape geometry.…”

Section: Introductionmentioning

confidence: 99%

Recognition of compound characters in Kannada language

Narasimhaiah

Rangarajan

2022

IJECE

View full text Add to dashboard Cite

<p><span lang="EN-US">Recognition of degraded printed compound Kannada characters is a challenging research problem. It has been verified experimentally that noise removal is an essential preprocessing step. Proposed are two methods for degraded Kannada character recognition problem. Method 1 is conventionally used histogram of oriented gradients (HOG) feature extraction for character recognition problem. Extracted features are transformed and reduced using principal component analysis (PCA) and classification performed. Various classifiers are experimented with. Simple compound character classification is satisfactory (more than 98% accuracy) with this method. However, the method does not perform well on other two compound types. Method 2 is deep convolutional neural networks (CNN) model for classification. This outperforms HOG features and classification. The highest classification accuracy is found as 98.8% for simple compound character classification. The performance of deep CNN is far better for other two compound types. Deep CNN turns out to better for pooled character classes.</span></p>

show abstract

“…A study was done in [14] showed the bundle of feature extraction techniques and were evaluated using the benchmark datasets available publically; the methods [15] and [16] outperformed the other methods available in the literature by showing the accuracy of 99.03% and 98.75% respectively. The following research methods are applied in the paper.…”

mentioning

confidence: 99%

Analysis of machine learning algorithms for character recognition: a case study on handwritten digit recognition

Khandy

Dadvandipour

2021

IJEECS

View full text Add to dashboard Cite

show abstract

Novel Geometrical Shape Feature Extraction Techniques for Multilingual Character Recognition

Cited by 18 publications

References 12 publications

An Experimental Technique for OCR Line and Word Segmentation using Probability Distribution Estimation

An Experimental Technique for OCR Line and Word Segmentation using Probability Distribution Estimation

Recognition of compound characters in Kannada language

Analysis of machine learning algorithms for character recognition: a case study on handwritten digit recognition

Contact Info

Product

Resources

About