Corner Detection Algorithms in Text of Natural Scene Images

Corners in images represent a lot of important information. Extracting corners accurately is significant to image processing, which can reduce much of the calculations. In this paper, three widely used corner detection algorithms, FAST (Features from Accelerated Segment Test), Eigen Value and Harris corner detection algorithms which are all based on intensity, were compared in stability, noise immunity and complexity via stability factor η, anti-noise factor ρ and the runtime of each algorithm. It concluded that FAST corner detection algorithm was superior to Harris and Eigen Value corner detection algorithm on the whole. Moreover, FAST, Eigen Value and Harris detection algorithms were improved by selecting an adaptive gray difference threshold and by changing directional differentials, respectively, and compared using these three criterions. In addition, FAST, Eigen Value and Harris corner detectors were applied to text detection experiment. It was verified that the quantitative evaluations of the corner detection algorithms were valid through calculating efficiency, which can reflect the performances of a corner detection algorithm comprehensively. Furthermore, the better corner detector was used into image mosaic experiment, and the result was satisfied. The work of this paper can provide a direction to the improvement and the utilization of these three corner detection algorithms. Keywords—Corner detection algorithms; comparison of algorithms.