Offline arabic handwritten text recognition

Parvez, Mohammad Tanvir; Mahmoud, Sabri A.

doi:10.1145/2431211.2431222

Cited by 117 publications

(58 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The handwriting problem has been investigated since many years using different types of NN [13,14] for both online and offline cases [1] and even also for alphabets different from Latin (e.g., Arabic in [15]). …”

Section: Related Workmentioning

confidence: 99%

Gender and Handedness Prediction from Offline Handwriting Using Convolutional Neural Networks

et al. 2018

View full text Add to dashboard Cite

Demographic handwriting-based classification problems, such as gender and handedness categorizations, present interesting applications in disciplines like Forensic Biometrics. This work describes an experimental study on the suitability of deep neural networks to three automatic demographic problems: gender, handedness, and combined gender-and-handedness classifications, respectively. Our research was carried out on two public handwriting databases: the IAM dataset containing English texts and the KHATT one with Arabic texts. The considered problems present a high intrinsic difficulty when extracting specific relevant features for discriminating the involved subclasses. Our solution is based on convolutional neural networks since these models had proven better capabilities to extract good features when compared to hand-crafted ones. Our work also describes the first approach to the combined gender-and-handedness prediction, which has not been addressed before by other researchers. Moreover, the proposed solutions have been designed using a unique network configuration for the three considered demographic problems, which has the advantage of simplifying the design complexity and debugging of these deep architectures when handling related handwriting problems. Finally, the comparison of achieved results to those presented in related works revealed the best average accuracy in the gender classification problem for the considered datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Gender and Handedness Prediction from Offline Handwriting Using Convolutional Neural Networks

et al. 2018

View full text Add to dashboard Cite

show abstract

“…For text images containing handwritten text, a more complicated algorithm involving image-blobs processing and segmentation is needed. For more details on such algorithms, readers are referred to [10]. In our work, we have utilized the method discussed in [9].…”

Section: Procedure: Extracttextlinesmentioning

confidence: 99%

Image Processing Based Computational Tools for Assisting and Assessing Memorization and Learning Tasks

Parvez¹,

Otri²

2017

IJEME

View full text Add to dashboard Cite

In this paper, we present a novel computational framework for assisting and assessing memorization tasks. Such a framework can be used in any cases where certain level of memorization is needed, like in memorizing words/sentences, learning (programming) language structures, etc. We aim to identify the common memorization steps followed in various disciplines and then automate some of these steps to enhance memorization process. Particularly, we focus on annotation of texts (used for memorization) based on state of the art image processing techniques. Once texts are annotated and optionally commented, personalized tests can be automatically generated, focusing on the weakness of a particular student. These tests can further enhance the memorization process. As a case study, we have implemented the framework for a classical example of memorization: memorizing the Qur'an, the sacred book in Islam. Qur'an memorization is a well-known process since the early days of Islam and represents an ideal case for implementing the proposed framework.Index Terms: Memorization tools, image processing, computational learning framework.

show abstract

“…In addition, although the o®-line digit code identi¯cation technology is relatively mature, [17][18][19] the online digit code identi¯cation has been an imperative demanding issue in automation system due to the uncertainty of the working environments such as image distortion, gray inequality problem which is caused by the variation of light intensity, uneven illumination, di®erent shooting angles and the random position of the code resulted by uncertain moments.…”

Section: Introductionmentioning

confidence: 99%

An online identity authentication method for blood smear

Feng

Cao

Kuang

et al. 2016

J. Innov. Opt. Health Sci.

View full text Add to dashboard Cite

Blood smear test is the basic method of blood cytology and is also a standard medical test that can help diagnose various conditions and diseases. Morphological examination is the gold standard to determine pathological changes in blood cell morphology. In the biology and medicine automation trend, blood smears' automated management and analysis is very necessary. An online blood smear automatic microscopic image detection system has been constructed. It includes an online blood smear automatic producing part and a blood smear automatic microscopic image detection part. Online identity authentication is at the core of the system. The identi¯ers printed online always present dot matrix digit code (DMDC) whose stroke is not continuous. Considering the particularities of DMDC and the complexities of online application environment, an online identity authentication method for blood smear with heterological theory is proposed. By synthesizing the certain regional features according to the heterological theory, high identi¯cation accuracy and high speed have been guaranteed with few features required. In the experiment, the su±cient correct matches between the tube barcode and the identi¯cation result veri¯ed its feasibility and validity.

show abstract

Offline arabic handwritten text recognition

Cited by 117 publications

References 98 publications

Gender and Handedness Prediction from Offline Handwriting Using Convolutional Neural Networks

Gender and Handedness Prediction from Offline Handwriting Using Convolutional Neural Networks

Image Processing Based Computational Tools for Assisting and Assessing Memorization and Learning Tasks

An online identity authentication method for blood smear

Contact Info

Product

Resources

About