Inhibition-augmented trainable COSFIRE filters for keypoint detection and object recognition

Guo, Jiapan; Shi, Chenyu; Azzopardi, George; Petkov, Nicolai

doi:10.1007/s00138-016-0777-3

Cited by 5 publications

(6 citation statements)

References 60 publications

(83 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…That type of inhibition allows to discriminate between patterns that are parts of others; e.g. the letter F is part of the letter E. A computational model for this phenomenon was implemented in [42], [43]. The two types of inhibition serve different purposes: push-pull inhibition that we implement in RUSTICO serves to suppress noise, while the other serves to distinguish better between patterns of interest.…”

Section: Rationale and Contributionsmentioning

confidence: 99%

Robust Inhibition-Augmented Operator for Delineation of Curvilinear Structures

Strisciuglio

Azzopardi

Petkov

2019

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Delineation of curvilinear structures in images is an important basic step of several image processing applications, such as segmentation of roads or rivers in aerial images, vessels or staining membranes in medical images, and cracks in pavements and roads, among others. Existing methods suffer from insufficient robustness to noise. In this paper, we propose a novel operator for the detection of curvilinear structures in images, which we demonstrate to be robust to various types of noise and effective in several applications. We call it RUSTICO, which stands for RobUST Inhibition-augmented Curvilinear Operator. It is inspired by the push-pull inhibition in visual cortex and takes as input the responses of two trainable B-COSFIRE filters of opposite polarity. The output of RUSTICO consists of a magnitude map and an orientation map. We carried out experiments on a data set of synthetic stimuli with noise drawn from different distributions, as well as on several benchmark data sets of retinal fundus images, crack pavements, and aerial images and a new data set of rose bushes used for automatic gardening. We evaluated the performance of RUSTICO by a metric that considers the structural properties of line networks (connectivity, area, and length) and demonstrated that RUSTICO outperforms many existing methods with high statistical significance. RUSTICO exhibits high robustness to noise and texture.

show abstract

Section: Rationale and Contributionsmentioning

confidence: 99%

Robust Inhibition-Augmented Operator for Delineation of Curvilinear Structures

Strisciuglio

Azzopardi

Petkov

2019

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Gecer et al (36) proposed a method that can recognize objects with the same shape but different colors, by configuring different COSFIRE filters in different color channels. Guo et al (37,38) further developed the COSFIRE method, by configuring the COSFIRE filter with the inhibition mechanism to recognize architectural and electrical symbols and to detect key points and recognize objects.…”

Section: Related Workmentioning

confidence: 99%

Retinal Vessel Segmentation Based on B-COSFIRE Filters in Fundus Images

Xiao

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

Retinal vessel extraction plays an important role in the diagnosis of several medical pathologies, such as diabetic retinopathy and glaucoma. In this article, we propose an efficient method based on a B-COSFIRE filter to tackle two challenging problems in fundus vessel segmentation: (i) difficulties in improving segmentation performance and time efficiency together and (ii) difficulties in distinguishing the thin vessel from the vessel-like noise. In the proposed method, first, we used contrast limited adaptive histogram equalization (CLAHE) for contrast enhancement, then excerpted region of interest (ROI) by thresholding the luminosity plane of the CIELab version of the original RGB image. We employed a set of B-COSFIRE filters to detect vessels and morphological filters to remove noise. Binary thresholding was used for vessel segmentation. Finally, a post-processing method based on connected domains was used to eliminate unconnected non-vessel pixels and to obtain the final vessel image. Based on the binary vessel map obtained, we attempt to evaluate the performance of the proposed algorithm on three publicly available databases (DRIVE, STARE, and CHASEDB1) of manually labeled images. The proposed method requires little processing time (around 12 s for each image) and results in the average accuracy, sensitivity, and specificity of 0.9604, 0.7339, and 0.9847 for the DRIVE database, and 0.9558, 0.8003, and 0.9705 for the STARE database, respectively. The results demonstrate that the proposed method has potential for use in computer-aided diagnosis.

show abstract

“…The proposed ridge-ending detector is based on the trainable bar-selective COSFIRE (B-COSFIRE) filter approach [29]. We augment the B-COSFIRE filters by adding a brain-inspired inhibition mechanism, which increases the selectivity of such filters without compromising generalization [30,31]. We configure such an inhibition-augmented B-COSFIRE filter by using two different types of prototype, a positive and a set of negative patterns.…”

Section: Ridge-ending Detectormentioning

confidence: 99%

“…Here we use η equals to 5 pixels which is twice the standard deviation σ of the outer Gaussian function. For further comments on the choice of the value of η we refer the reader to [30]. We repeat this procedure for each tuple in the set N f 1 .…”

Section: Configuration Of An Inhibition-augmented B-cosfire Filtermentioning

confidence: 99%