Search for Articles:

MECS Press Menu

Ekta Walia

Work place: Department of Computer Science, University of Saskatchewan, Saskatoon, Canada

E-mail: wekta@yahoo.com

Website:

Research Interests: Pattern Recognition, Image Compression, Image Manipulation, Image Processing, Information Retrieval

Biography

Dr. Ekta Walia received her Bachelors degree in Computer Science from Kurukshetra University, India and Masters in Computer Applications as well as Ph.D. (Computer Science) from Punjabi University, Patiala, India respectively. After starting her professional career as a software consultant with DCM DataSystems, New Delhi, India, in 1998, she served as Lecturer and Senior Lecturer in the National Institute of Technical Teachers Training and Research (NITTTR), Chandigarh, India for 07 years, where she was primarily involved in conducting short term courses for teachers of various engineering colleges and conduct of research. In 2011, she joined the Department of Computer Science in South Asian University, New Delhi, India, where she has been serving as Associate Professor and Chairperson till May 2014. She joined the Department of Computer Science, University of Saskatchewan to work as Professional research associate in DADAISM project in June 2014. Her academic achievements include University Gold medals in Graduation as well as in Post-Graduation. Her research interests include 3D Rendering, Digital Image Watermarking, Content Based Image Retrieval and Face Recognition using orthogonal radial moments, in particular. She has a number of international journal and conference publications in these areas. She has been on the reviewing board of reputed image processing journals and conferences. She has also chaired sessions in International Conferences of repute.

Author Articles
Time and Accuracy Analysis of Skew Detection Methods for Document Images

By Sunita Mehta Ekta Walia Maitreyee Dutta

DOI: https://doi.org/10.5815/ijitcs.2015.11.06, Pub. Date: 8 Oct. 2015

Detecting skew angle in a document image has been an area of research interest for a long time. This paper presents an experimental analysis of various existing skew detection techniques involving methods such as Radon transform, Hough transform, Principal Component Analysis (PCA), PCA with Wavelet transform and Moments with Wavelet transform. Detailed analysis of existing skew detection method against the parameters time complexity, space complexity, robustness, accuracy, flexibility, etc. has been carried out for seven different categories of digital documents. The categories of these documents spans from those containing handwritten text in different languages, to the ones with both text and pictures. Radon transform is observed to be the fastest method when the image size is small and works with virtually all types of documents. It is an accurate method as well as works faster, even with the document containing pictures. PCA method is also faster than Hough transform for machine printed documents but used less for real time skew distortion due to its limitations. If the document image size is large, then Moments with Wavelet transform has better time complexity than other methods, but do not work well with documents containing images. Hough transform is the most accurate method, though it is computationally expensive.

[...] Read more.
Other Articles

Subscribe to receive issue release notifications and newsletters from MECS Press journals