An Affine Invariant Region Detector Using the 4th Differential Invariant
Nat. Univ. of Defense Technol., ChangshaDOI: 10.1109/ICTAI.2007.112 Conference: Tools with Artificial Intelligence, 2007. ICTAI 2007. 19th IEEE International Conference on, Volume: 1
Source: IEEE Xplore
A novel affine invariant region detector based on the 4th differential invariant (DI4) is proposed in this paper. The detector combines scale-space theory with an autocorrelation matrix. Since it is proved that DI4 is a scale- space selection function, feature points and their characteristic scales are first detected by the local maxima of the normalized DI4 over scale-space. Then, the auto-correlation matrices, which are used to describe the affine shapes, are estimated on the characteristic scales of the feature points. The ellipse regions given by the auto-correlation matrices are affine invariant. In order to verify the affine invariance, we build up a simulation experiment to test affine invariance using two single- parameter transforms. The experimental results show the detected regions are invariant to rotation, scale and affine transforms as well as robust to illumination changes.
- [Show abstract] [Hide abstract]
ABSTRACT: In this paper, a derivative estimator is introduced to obtain differential information of images. Experiments show that differentials obtained by this estimator outperform the traditional Sobel operator and this estimator is practical for extracting differential image information. A new image representation in this differential space is also proposed. Differential sign sequences of images are used as the signature of image patterns. The Hamming distance is used for template matching. The proposed representation is invariant to brightness and contrast and is robust to noise because of the low pass property of the estimator. Template matching is used as an example to exhibit the advantage of this representation. Experiments demonstrate good performance of the proposed method.12/2008: pages 624-633;
- [Show abstract] [Hide abstract]
ABSTRACT: Affine-invariant region detection is the basic technique for visual matching and has been widely applied in many areas. In this paper, we propose a simple yet effective method to detect the affine-invariant regions from gray image, which is called enclosedregion. The enclosed region is detected based on the observation that one physical object is enclosed by the same region before and after affine transformation. The proposed method is a three-step method. Firstly, we segment the initial regions by using thresholds on the image. Secondly, external enclosing region (EER) and internal enclosed region (IER) are defined for each initial region, and we select the enclosed regions from the initial regions through applying histogram constraints on EER and IER. Thirdly, the largely overlapping regions are removed. Experiments on typical images exhibit the robustness of the proposed enclosed region detector. Extensively quantitative evaluation and comparison demonstrate that the proposed method outperforms state-of-the-art methods.Journal of Visual Communication and Image Representation 05/2010; 21(4-21):271-282. DOI:10.1016/j.jvcir.2009.11.001 · 1.22 Impact Factor
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.