Automatic false edge elimination using locally adaptive regression kernel

作者：Abu Samah Hafizi; Isa Nor Ashidi Mat^*; Toh Kenny Kal Vin

来源：Signal, Image and Video Processing, 2015, 9(6): 1339-1351.

DOI：10.1007/s11760-013-0579-2

• Edge detection
• Edge discrimination
• Locally adaptive regression kernel
• Edge sensitivity
• Image representation

The discrimination of true and false edges in edge images is a challenging yet important problem that has not attracted the mainstream research community in image processing. Existing approaches often emphasize on detecting true edges while neglecting the handling of false edges. In addition, many existing techniques are complicated in nature, non-robust for handling different type of images, and suitable only for specific applications. In this paper, we proposed a technique that eliminates false edges from a binary edge image. We employed locally adaptive regression kernel (LARK) as descriptor of the detected edge. By using LARK, we identified false edges by comparing their descriptors with those from the reference flat region. All edges with descriptors similar to the reference flat region were labeled as false edges and eliminated. We tested our algorithm on edge images obtained from the widely used Canny edge detector and conducted qualitative and quantitative analysis on the proposed method. Extensive simulation results show that the proposed method successfully eliminates most false edges. Comparison between the proposed method with some famous edge detectors shows that our algorithm quantitatively outperforms others with an average Baddeley's delta metric of 23.37.

• 出版日期2015-9