Artificial Urdu Text Detection and Localization from Individual Video Frames

Unar, Salahuddin; Jalbani, Akhtar Hussain; Jawaid, Muhammad Moazzam; Shaikh, Mohsin; Chandio, Asghar Ali

doi:10.22581/muet1982.1802.18

Cited by 13 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the contrary, the scientific research literature also reports several proposed methods to detect meaningful information from variety of data, such as text from video [40], clickstream data [37] relational database of criminal activities [38].…”

Section: The Building Blocks Of Proposed Frameworkmentioning

confidence: 99%

Bringing Shape to Textual Data – A Feasible Demonstration

Shaikh

Mahoto

Unar

2019

Mehran Univ. res. j. eng. technol.

View full text Add to dashboard Cite

The Internet has revolutionized the communication paradigm. This has led towards immense amount of unstructured data (i.e. textual data), which is a major source to get useful knowledge about people in several application domains. TM (Text Mining) extracts high quality information to discover knowledge by drawing patterns and relationships in textual data. This field has taken great attention of the research community. As a result, several attempts have been made to propose, introduce and refine techniques applied for uncovering knowledge from text data. This study aims at: (1) presenting existing TM techniques in the scientific literature, (2) reporting challenges/issues and gaps that still need attention, and (3) proposing a framework to bring shape to textual data. A prototype has been developed to demonstrate the effectiveness and potential worth of proposed approach to display how unstructured data (i.e. news articles in this study) has been brought to a shape representing interesting knowledge. The proposed framework implements basic NLP (Natural Language Processing) functions in combination of AYLIEN API (Application Programming Interface) functions. The results reveal the fact that how events, celebrities and popular news-items have been covered in the electronic media, and it also represents subjectivity of topical news events. The news coverage trends highlight the significance of daily news events, which may assist in getting insight about the media groups.

show abstract

Section: The Building Blocks Of Proposed Frameworkmentioning

confidence: 99%

Bringing Shape to Textual Data – A Feasible Demonstration

Shaikh

Mahoto

Unar

2019

Mehran Univ. res. j. eng. technol.

View full text Add to dashboard Cite

show abstract

“…It consists of 1000 video frames from news channels and is openly available. Table 1 summarizes the results of Detection on artificial Urdu text in video frames, and the highest result achieved so far, has a Precision of 0.83 [5].…”

Section: Introductionmentioning

confidence: 97%

Urdu-Text Detection and Recognition in Natural Scene Images Using Deep Learning

Arafat

Iqbal

2020

IEEE Access

View full text Add to dashboard Cite

Urdu text is a cursive script and belongs to a non-Latin family of other cursive scripts like Arabic, Chinese, and Hindi. Urdu text poses a challenge for detection/localization from natural scene images, and consequently recognition of individual ligatures in scene images. In this paper, a methodology is proposed that covers detection, orientation prediction, and recognition of Urdu ligatures in outdoor images. As a first step, the custom FasterRCNN algorithm has been used in conjunction with well-known CNNs like Squeezenet, Googlenet, Resnet18, and Resnet50 for detection and localization purposes for images of size 320 × 240 pixels. For ligature Orientation prediction, a custom Regression Residual Neural Network (RRNN) is trained/tested on datasets containing randomly oriented ligatures. Recognition of ligatures was done using Two Stream Deep Neural Network (TSDNN). In our experiments, five-set of datasets, containing 4.2K and 51K Urdu-text-embedded synthetic images were generated using the CLE annotation text to evaluate different tasks of detection, orientation prediction, and recognition of ligatures. These synthetic images contain 132, and 1600 unique ligatures corresponding to 4.2K and 51K images respectively, with 32 variations of each ligature (4-backgrounds and font 8-color variations). Also, 1094 real-world images containing more than 12k Urdu characters were used for TSDNN's evaluation. Finally, all four detectors were evaluated and used to compare them for their ability to detect/localize Urdu-text using average-precision (AP). Resnet50 features based FasterRCNN was found to be the winner detector with AP of.98. While Squeeznet, Googlenet, Resnet18 based detectors had testing AP of.65, .88, and .87 respectively. RRNN achieved and accuracy of 79% and 99% for 4k and 51K images respectively. Similarly, for characters classification in ligatures, TSDNN attained a partial sequence recognition rate of 94.90% and 95.20% for 4k and 51K images respectively. Similarly, a partial sequence recognition rate of 76.60% attained for real world-images. INDEX TERMS BLSTM, deep neural network, FasterRCNN, image classification, Nastalique, optical character recognition (OCR), regression residual neural network (RRNN), synthetic urdu text, text detection, two stream deep neural network (TSDNN).

show abstract

“…In recent years, the problem of text detection and localisation from the images has gained much attention [10–14]. Several methods have been proposed to detect the text from the images.…”

Section: Introductionmentioning

confidence: 99%