Engr. Safia Shabbir | Bahria University, Islamabad-Pakistan (original) (raw)
Expertise in artificial intelligence, machine learning, document analysis and recognition, and computer vision.
Supervisors: Dr. Imran Ahmed Siddiqi
less
Uploads
Papers by Engr. Safia Shabbir
2017 13th International Conference on Emerging Technologies (ICET), 2017
Clustering is a pivotal step in any Optical Character Recognition (OCR) or Word Spotting system. ... more Clustering is a pivotal step in any Optical Character Recognition (OCR) or Word Spotting system. It serves as a base for the classification and indexing of different words or characters depending upon the level of segmentation. Various clustering methodologies have been applied by different researchers on Latin script based document images. However for Urdu language, which belongs to the family of Arabic and Persian, clustering based indexing systems have not been extensively researched. In this paper, we present a comprehensive study of various known clustering techniques applied on printed Urdu Document Images. The images are segmented into ligatures or partial words and then they are grouped together using different clustering methods. Performance of these methods is evaluated using Calinski-Harabasz, Davis-Bouldin and Dunn indexes.
of society. Modern Information and communication technologies have huge potential to benefit the ... more of society. Modern Information and communication technologies have huge potential to benefit the working
processes of such organizations but deploying software application in such settings is quite challenging. These
challenges emerge due to shortage of skilled employees, limited funds and weak organizational structures. In
order to further understand the technological implications in such settings this paper explores the websites of
different nonprofit organizations of Pakistan to understand usability problems. In order to gather empirical
data, it prepared questionnaire mainly focusing on Jakob Nielson’s heuristics. These questionnaires were
distributed to final year undergraduate students taking a Human Computer Interaction module. The findings
highlight serious usability issues in these websites. These findings are helpful for the nonprofit organizations
to improve these websites for better information access.
2017 13th International Conference on Emerging Technologies (ICET), 2017
Clustering is a pivotal step in any Optical Character Recognition (OCR) or Word Spotting system. ... more Clustering is a pivotal step in any Optical Character Recognition (OCR) or Word Spotting system. It serves as a base for the classification and indexing of different words or characters depending upon the level of segmentation. Various clustering methodologies have been applied by different researchers on Latin script based document images. However for Urdu language, which belongs to the family of Arabic and Persian, clustering based indexing systems have not been extensively researched. In this paper, we present a comprehensive study of various known clustering techniques applied on printed Urdu Document Images. The images are segmented into ligatures or partial words and then they are grouped together using different clustering methods. Performance of these methods is evaluated using Calinski-Harabasz, Davis-Bouldin and Dunn indexes.
of society. Modern Information and communication technologies have huge potential to benefit the ... more of society. Modern Information and communication technologies have huge potential to benefit the working
processes of such organizations but deploying software application in such settings is quite challenging. These
challenges emerge due to shortage of skilled employees, limited funds and weak organizational structures. In
order to further understand the technological implications in such settings this paper explores the websites of
different nonprofit organizations of Pakistan to understand usability problems. In order to gather empirical
data, it prepared questionnaire mainly focusing on Jakob Nielson’s heuristics. These questionnaires were
distributed to final year undergraduate students taking a Human Computer Interaction module. The findings
highlight serious usability issues in these websites. These findings are helpful for the nonprofit organizations
to improve these websites for better information access.