Distinctive curves: unified scale-invariant detection of edges, corners, lines and curves
(English)In: IEEE Transactions on Image Processing, ISSN 1057-7149, E-ISSN 1941-0042Article in journal (Refereed) Submitted
This paper aims to broaden the scope of shape related features including edges, corners, lines and curves: 1) Edges, corners, lines, curves are all shape related features. In the past, the detection of each type of feature is usually solved independently under certain hypotheses. Our proposed distinctive curve detection method (DICU) solves the detection of all these type of features together. 2) Compared to the development in scale-invariant interest point detectors which have adopted more objective robustness measures using repeatability score, the research in line and curve features is still limited to “true/false positive” measures. DICU detection utilizes the scale-space concept and proves that curve features can be as robust as scale-invariant interest points. DICU has three advantages: 1) DICU outputs multi-type features which can benefit future computer vision applications. At the same time, the computational efficiency is unaffected, after detecting edges, only 5% additional computation is needed to detect corners, lines, and curves. 2) It is robust under various image perturbations and transformations and outperforms state-of-the-art interest point detectors and line detectors. At the same time, all types of detected features are robust. 3) Curve features contains more geometric information than points. Our curve matching test shows that curve matching can outperform interest point matching.
curve, line, corner, feature matching, scale-invariance
Electrical Engineering, Electronic Engineering, Information Engineering
Research subject Signal Processing
IdentifiersURN: urn:nbn:se:umu:diva-111186OAI: oai:DiVA.org:umu-111186DiVA: diva2:867849