A local real-time bar detector based on the multiscale Radon transform

Oliva-García, Ricardo; Gómez-Cárdenes, Óscar; Marichal-Hernández, José G.; Martı́n-Hernández, Javier; Luke, J. P.; Rodríguez-Ramos, José Manuel

doi:10.1117/12.2617411

Cited by 3 publications

(18 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, we decided to quantitatively assess the bands found in the high-pass filter map with the Fourier Transform because it fits adequately in the study of periodic patterns like this, and many studies applied it to analyze collagen structures from different tissues 27 – 30 . Nevertheless, there is no unique method to assess this kind of pattern 37 , 39 , 41 , and one of our following goals will be to compare Fourier methods with others, such as the Radon Transform, which is also capable of automatically detecting and quantifying the band patterns 45 . We also plan to make use of Artificial Intelligence to label automatically and individually each of the bands for better quantification of the problem and subsequent classification between those subjects who presented this pattern and those who did not, as previous authors had worked with this tool with topography and tomography descriptors to diagnose and evaluate the studied disease 46 – 50 .…”

Section: Discussionmentioning

confidence: 99%

Comparing the clinical applicability of wavefront phase imaging in keratoconus versus normal eyes

Belda-Para,

Velarde-Rodríguez,

Velasco-Ocaña

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The aim of this work is to quantitatively assess the wavefront phase of keratoconic eyes measured by the ocular aberrometer t·eyede (based on WaveFront Phase Imaging Sensor), characterized by a lateral resolution of 8.6 µm without requiring any optical element to sample the wavefront information. We evaluated the parameters: root mean square error, Peak-to-Valley, and amplitude of the predominant frequency (Fourier Transform analysis) of a section of the High-Pass filter map in keratoconic and healthy cohorts. Furthermore, we have analyzed keratoconic eyes that presented dark–light bands in this map to assess their period and orientation with the Fourier Transform. There are significant statistical differences (p value < 0.001) between healthy and keratoconic eyes in the three parameters, demonstrating a tendency to increase with the severity of the disease. Otherwise, the quantification of the bands reveals that the width is independent of eye laterality and keratoconic stage as orientation, which tends to be oblique. In conclusion, the quantitative results obtained with t·eyede could help to diagnose and monitor the progression of keratoconus.

show abstract

Section: Discussionmentioning

confidence: 99%

Comparing the clinical applicability of wavefront phase imaging in keratoconus versus normal eyes

Belda-Para,

Velarde-Rodríguez,

Velasco-Ocaña

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Moreover, we decided to quantitatively assess the bands found in the high-pass filter map with the Fourier Transform because it fits adequately in the study of periodic patterns like this, and many studies applied it to analyze collagen structures from different tissues [21][22][23][24] . Nevertheless, there is no unique method to assess this kind of pattern 31,33,35 , and one of our following goals will be to compare Fourier methods with others, such as the Radon Transform, which is also capable of automatically detecting and quantifying the band patterns 39 . We also plan to make use of Artificial Intelligence to label automatically and individually each of the bands for better quantification of the problem and subsequent classification between those subjects who presented this pattern and those who did not, as previous authors had worked with this tool with topography and tomography descriptors to diagnose and evaluate the studied disease [40][41][42][43][44] .…”

Section: Discussionmentioning

confidence: 99%

Clinical applicability of the WaveFront Phase Imaging Sensor in the Keratoconus Disease

Belda-Para,

Velarde-Rodríguez,

Velasco-Ocaña

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

SignificanceThe analysis of the wavefront phase of keratoconus eyes has become increasingly important due to its impact on the assessment of visual quality loss, irrecoverable with conventional optical treatments, and the understanding of morphological changes in corneal structures.AimThe aim of this work is to quantitatively assess the wavefront phase of keratoconic eyes measured by the novel high-resolution ocular aberrometer t·eyede (based on WaveFront Phase Imaging Sensor).ApproachThe measurements with this device were taken on healthy and keratoconic eyes at the Hospital Universitario Fundación Jiménez Díaz (Madrid, Spain). The wavefront phase recovered is post-processed and displayed in different phase maps, using exclusively the high-pass filter map for this study. From this map, the Root Mean Square, the Peak-to-Valley, and the amplitude value of the predominant obtained from its Fourier Transform are the parameters to distinguish between healthy and keratoconic eyes. Furthermore, the banding pattern observed in most keratoconic eyes is quantitatively analyzed by means of its period and orientation calculated from the Fourier Transform.ResultsThe Control group was composed of 43 healthy eyes, and the Pathological group presented 43 keratoconic eyes. Regarding the first three parameters used to compare both groups, there were significant statistical differences between them in all parameters, where the values obtained with the keratoconic group were higher than those of the healthy group. Although the values cannot be statistically comparable between stages, they tended to increase according to the severity of the disease. On the other hand, analyzing the banding pattern, the mean value of the period was approximately 50 µm, and most orientations were obliquus, tending to be horizontal rather than vertical.ConclusionsThe present study demonstrates that the objective analysis of the high frequencies detected by this wavefront sensor is a potential tool to reliably advise in the keratoconus diagnosis. Furthermore, combining this achievement with the quantitative assessment of the banding pattern would be used to objectively monitor the internal corneal status throughout the disease and its treatment optimization and surgery time.

show abstract

“…To overcome the challenges mentioned above, this paper revises a modification of the discrete Radon transform [33], which makes the local detection of bar-shaped structures at a certain scale possible. This method presents a trade-off between the density of the grid on which it returns the results and the accuracy with which it determines the existence and orientation of the bars.…”

Section: Purpose Of This Workmentioning

confidence: 99%

“…See Figure 3. The method described by Oliva-García et al [33], consisting of the above method, works because the partial m stage of the modified DRT as described by Gómez-Cárdenes et al [39] computes the sums at 2 m+1 − 1 possible angles of line segments of length 2 m , starting at each position (2…”

Section: From a Line Detector To A Local Bar Detectormentioning

confidence: 99%

See 1 more Smart Citation

An Encoder–Decoder Architecture within a Classical Signal-Processing Framework for Real-Time Barcode Segmentation

Gómez-Cárdenes

Marichal-Hernández

Son

et al. 2023

Sensors

View full text Add to dashboard Cite

In this work, two methods are proposed for solving the problem of one-dimensional barcode segmentation in images, with an emphasis on augmented reality (AR) applications. These methods take the partial discrete Radon transform as a building block. The first proposed method uses overlapping tiles for obtaining good angle precision while maintaining good spatial precision. The second one uses an encoder–decoder structure inspired by state-of-the-art convolutional neural networks for segmentation while maintaining a classical processing framework, thus not requiring training. It is shown that the second method’s processing time is lower than the video acquisition time with a 1024 × 1024 input on a CPU, which had not been previously achieved. The accuracy it obtained on datasets widely used by the scientific community was almost on par with that obtained using the most-recent state-of-the-art methods using deep learning. Beyond the challenges of those datasets, the method proposed is particularly well suited to image sequences taken with short exposure and exhibiting motion blur and lens blur, which are expected in a real-world AR scenario. Two implementations of the proposed methods are made available to the scientific community: one for easy prototyping and one optimised for parallel implementation, which can be run on desktop and mobile phone CPUs.

show abstract

A local real-time bar detector based on the multiscale Radon transform

Cited by 3 publications

References 7 publications

Comparing the clinical applicability of wavefront phase imaging in keratoconus versus normal eyes

Comparing the clinical applicability of wavefront phase imaging in keratoconus versus normal eyes

Clinical applicability of the WaveFront Phase Imaging Sensor in the Keratoconus Disease

An Encoder–Decoder Architecture within a Classical Signal-Processing Framework for Real-Time Barcode Segmentation

Contact Info

Product

Resources

About