A Partial Intensity Invariant Feature Descriptor for Multimodal Retinal Image Registration

By Jian Chen, Jie Tian, N. Lee, Jian Zheng, R. T. Smith, Andrew F. Laine. IEEE Transactions on Biomedical Engineering, 2010

307 citations recorded by the source corpus.

Detection of vascular bifurcations is a challenging task in multimodal retinal image registration. Existing algorithms based on bifurcations usually fail in correctly aligning poor quality retinal image pairs. To solve this problem, we propose a novel highly distinctive local feature descriptor named partial intensity invariant feature descriptor (PIIFD) and describe a robust automatic retinal image registration framework named Harris-PIIFD. PIIFD is invariant to image rotation, partially invariant to image intensity, affine transformation, and viewpoint/perspective change. Our Harris-PIIFD framework consists of four steps. First, corner points are used as control point candidates instead of bifurcations since corner points are sufficient and uniformly distributed across the image domain. Second, PIIFDs are extracted for all corner points, and a bilateral matching technique is applied to identify corresponding PIIFDs matches between image pairs. Third, incorrect matches are removed and inaccurate matches are refined. Finally, an adaptive transformation is used to register the image pairs. PIIFD is so distinctive that it can be correctly identified even in nonvascular areas. When tested on 168 pairs of multimodal retinal images, the Harris-PIIFD far outperforms existing algorithms in terms of robustness, accuracy, and computational efficiency.

Subfields: Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/064c3c2c7bf823e14209dd836907949f065baa49

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Jiayi Ma
2. Zhenfeng Shao
3. Xiaojie Guo
4. Guobao Xiao
5. Xingyu Jiang
6. Junjun Jiang
7. Junchi Yan
8. Aoxiang Fan

In Radiology, Nuclear Medicine and Imaging

1. Xiaojie Guo
2. Junjun Jiang
3. Jiayi Ma

Citations in the corpus

• A review of multimodal image matching: Methods and applications (2021, methodology): “[140] Fundus-FA Feature-based Affine Retina Harris + PIIFD”
• RIFT: Multi-Modal Image Matching Based on Radiation-Variation Insensitive Feature Transform (2019, background): “For example, local self-similarity descriptor (LSS) [37], partial intensity invariant feature descriptor (PIIFD) [38], distinctive order-based self-similarity descriptor (DOBSS) [39], ARRSI [40], histogram of orien-tated phase congruency (HOPC) [41], and phase congruency structural descriptor…”
• Retinal Imaging and Image Analysis (2010, unknown): “proposed the detection of corner points using a Harris detector followed by use of a partial intensity invariant feature descriptor (PIIFD) [182].”
• Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “For example, Chen et al. (2010) developed the partial intensity invariant feature descriptor (PIIFD) to register retinal images, whereas Wang et al. (2015) extended PIIFD in a more robust registration framework with SURF detector (Bay et al. 2008) and a single Gaussian point matching model.”