• Citations Per Year
Learn More
Edge Detection is a primary but one of the most essential segmentation tasks of image processing. Though numerous techniques are available for edge detection, it is hard to find a generalized version adaptive to all situations. Edge detection challenge gets stiffer in case of noisy images, because most of the derivative based edge detectors are very(More)
In this paper a combined algorithm and architectural design of real time hill climbing based watershed segmentation has been proposed. We have modified the classical hill climbing algorithm in a Finite State Machine (FSM) based parallel cell network. In our approach, each cell representing a pixel propagates label of the corresponding basin to its steepest(More)
Velocity prediction is a crucial task for dynamic object tracking. Over the years many conventional methods have been used for this purpose but their performance remains unsatisfactory in case of jerky motion profile due to their high convergence time. In this paper we have used Cubic B-Spline for velocity prediction for a real time tracking system, which(More)
Edge detection is a fundamental and important operation in image processing. In this paper, we propose a VLSI architecture for detecting edges from real time monochrome video sequences. We have adopted a local threshold and global variance based method to extract initial edge map and then different edge orientations have been applied to extract true edge(More)
  • 1