Papers by Dr. Jibanananda Mehena
This paper presents a unified derivation of rotation-based recursive least squares (RLS) algorith... more This paper presents a unified derivation of rotation-based recursive least squares (RLS) algorithms based on QR decomposition. They solve the adaptive least squares problems of the linear combiner without a desired signal, the single and multichannel linear prediction and transversal filtering. All algorithms derived in this paper are based on Givens rotations. They offer superior numerical properties as shown by computer simulations. They are computationally efficient and highly concurrent. Parallel implementation of the resulting methods in the form of systolic array and its application to system identification is discussed in this paper.
Vehicle License Plate Segmentation and Extraction Based on Mathematical Morphology
Vehicle License plate extraction is one of the most important applications of intelligent transpo... more Vehicle License plate extraction is one of the most important applications of intelligent transportation systems. Extraction involves detection, localization, tracking, enhancement and recognition of the license plate from the vehicle images. However variation of text due to difference in size, style, orientation, alignment, low image contrast and complex background make the problem of automatic license plate extraction extremely challenging. Text extraction requires binarization which leads to loss of significant information contained in gray scale images. The images may contain noise and have complex structure which makes the extraction more difficult. Hence extracting the license plate in a vehicle image is considered to be the most crucial step of an intelligent transport system. This paper mainly deals with segmentation and extraction of license plate in Indian traffic conditions based on mathematical morphology. Proposed method aims at identifying region of interest by perform...
Uploads
Papers by Dr. Jibanananda Mehena