Arabic Writer Identification System Using the Histogram of Oriented Gradients (HOG) of Handwritten Fragments

Hannad, Yaâcoub; Siddiqi, Imran; Merabet, Youssef El; Kettani, Mohamed El Youssfi El

doi:10.1145/3038884.3038900

Cited by 10 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The system evaluated on the 411 writers of the IFN/ENIT database achieved an identification rate of 94.89%. The work was later extended [43] to investigate the effectiveness of HOG as a descriptor of small writing fragments. Al-Maadeed et al [48] proposed a set of geometrical features to characterise writer.…”

Section: Related Workmentioning

confidence: 99%

“…The writing fragments in these studies are compared either directly on pixel values (cross correlation) or by representing these fragments using a set of features. Based on the same idea, the authors investigated the effectiveness of textural measures to represent fragments in the writing [4, 43]. Descriptors including LBP, local ternary patterns (LTP), LPQ, and histogram of oriented gradients (HOG) were explored in these studies and realised promising results on writer identification from Arabic handwriting images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Arabic writer identification using score‐level fusion of textural descriptors

et al. 2019

Self Cite

View full text Add to dashboard Cite

This paper investigates the problem of writer identification from handwriting samples in Arabic. The proposed technique relies on extracting small fragments of writing which are characterised using two textural descriptors, Histogram of Oriented Gradients (HOG) and Gray Level Run Length (GLRL) Matrices. Similarity scores realised using HOG and GLRL features are combined using a number of fusion rules. The system is evaluated on three well-known Arabic handwriting databases, the IFN/ENIT database with 411 writers, the KHATT database with 1000 writers, and QUWI database with 1,017 writers. Fusion using the 'sum' rule reports the highest identification rates reading 96.86, 85.40, and 76.27% on IFN/ENIT, KHATT, and QUWI databases, respectively. The results realised on the KHATT database are comparable to the state of the art while those reported on the IFN/ENIT and QUWI databases are the highest to the best of authors' knowledge.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improving Arabic writer identification using score‐level fusion of textural descriptors

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Many methods have been proposed to tackle the writer identification problem in document images. In [10], the Histogram of Oriented Gradients (HOG) was applied to Arabic written document images. In [11], a bagged discrete cosine transform (BDCT) descriptor was used to identify the authorship of English written document images.…”

Section: Related Workmentioning

confidence: 99%

“…In contrast, this work proposes the use of a CNN to learn the feature extractor and the classifier jointly, which is an approach that has already given satisfactory results in problems belonging to a wide variety of areas [7] [2] [4]. Another approach that has been explored in recent works, similar to those presented by [10] and [13], is based on the analysis of local characteristics of images by extracting patches. The patch extraction strategy also presented good results on medical image analysis [14].…”

Section: Related Workmentioning

confidence: 99%

Patch-Based Convolutional Neural Network for the Writer Classification Problem in Music Score Images

Hattori¹,

Gutoski²,

Aquino³

et al. 2018

Proceeding XIII Brazilian Congress on Computational Inteligence

View full text Add to dashboard Cite

The Writer Identification Problem has been largely studied in the field of image processing. Music score writer identification is a particular type of the problem that requires identifying the writer of a music score, which is a complex task even for musicologists. Addressing this issue, this paper presents a novel Deep Learning approach based on a Convolutional Neural Network (CNN) for classifying music score images according to their writer. The classification is accomplished by dividing a music score image into patches that are fed to the CNN, which provides classification results for each patch. A voting system is then applied to obtain the final prediction of the model. This approach allows to learn local features of each music score in order to improve the final classification result. Results show that the proposed approach allows to obtain satisfactory results for the dataset used in this work, reaching 84%, 94% and 98% for the top-1, top-3 and top-5 accuracies, respectively.

show abstract

“…The proposed system used two databases, one in Arabic and one for English in Arabic database IFN/ENIT the result for writer identification rate of 94.89. "Hannad, Y., Siddiqi, I., El Merabet, Y., & El Youssfi El Kettani, M [7] proposed a system for Writer Recognition System by Using the Histogram of Oriented Gradients (HOG) of Handwritten. In proposed system using IFN/ENIT database on 411 writers, the system result identification rate of 86.62% .Sheikh, A., & Khotanlou, H [8] have suggested a system for Writer Identity Recognition particularly at the feature extraction stage (since, manual feature extraction has taken long time) this study included two basic steps: the first was dedicated to training and the second concerned testing.…”

Section: Introductionmentioning

confidence: 99%

Writer Identification Based on Arabic Handwriting Recognition by using Speed Up Robust Feature and K- Nearest Neighbor Classification

Hassan

Mahdi

Mohammed

2019

JUBPAS

View full text Add to dashboard Cite

In a writer recognition system, the system performs a “one-to-many” search in a large database with handwriting samples of known authors and returns a possible candidate list. In this paper proposed method for writer identification handwritten Arabic word without segmentation to sub letters based on feature extraction speed up robust feature transform (SURF) and K nearest neighbor Classification (KNN) to enhance the writer identification accuracy. After feature extraction can be clustered by K-means algorithm to standardize the number of features the feature extraction and feature clustering called to gather Bag of Word (BOW), it converts arbitrary number of image feature to uniform length feature vector the proposed method experimented using (IFN/ENIT) database. The experiment result is (96.666) recognition rate.

show abstract

Arabic Writer Identification System Using the Histogram of Oriented Gradients (HOG) of Handwritten Fragments

Cited by 10 publications

References 14 publications

Improving Arabic writer identification using score‐level fusion of textural descriptors

Improving Arabic writer identification using score‐level fusion of textural descriptors

Patch-Based Convolutional Neural Network for the Writer Classification Problem in Music Score Images

Writer Identification Based on Arabic Handwriting Recognition by using Speed Up Robust Feature and K- Nearest Neighbor Classification

Contact Info

Product

Resources

About