Wyniki wyszukiwania - BazTech

1

Template chart detection for stoma telediagnosis

Szwoch Mariusz, Zawiślak Rafał, Granosik Grzegorz, Mik-Wojtczak Joanna, Mik Michał

International Journal of Applied Mathematics and Computer Science

|

2022

|

Vol. 32, no. 1

147--160

EN

The paper presents the concept of using color template charts for the needs of telemedicine, particularly telediagnosis of the stoma. Although the concept is not new, the current popularity and level of development of digital cameras, especially those embedded in smartphones, allow common and reliable remote advice on various medical problems, which can be very important in the case of limitations in a physical contact with a doctor. The article focuses on the initial stages of photo processing for the needs of telemedicine, i.e., on the assumptions and the process of designing the appropriate template and detecting it in photos for stoma telediagnosis. Research on the developed algorithms for the location of fiducial markers and reference color fields, carried out on the basis of over 2,000 photos, showed a very high tolerance to scene exposure, lighting conditions and the camera used. The obtained results allowed the initial image intensity normalization of the stoma area as well as correct localization and measurement of changes detected on the skin and the mucosa, which, in the opinion of doctors, significantly increased the diagnostic value of the photographs.

2

A study of distortion correction algorithms based on aspheric fisheye lens design

Li Dan, Zhang Baolong, Zhu Jiawei, Wang Qi, Zhu Zhenwei

Optica Applicata

|

2020

|

Vol. 50, nr 4

579--592

EN

A design method of aspheric fisheye lens has been proposed in this paper, based on the requirements of automobile surround view system. The study has designed a kind of ultra-wide-angle fisheye lens, which only consists of a spherical glass lens and three aspherical plastic lenses. The maximum diameter of imaging aperture is 15. 3 mm; the working distance behind is 2.158 mm; the total length of system is 11.44 mm; the focal length is 0.97 mm; the viewing angle is 210°, and the modulation transfer function (MTF) curve is 0.35 at 60 lp/mm. Furthermore, a kind of a distortion correction algorithm for fisheye lens has been created, which calculates the position of the ideal image point with the actual image point and the obtained distortion curve and distortion model. The algorithm can correct the distorted image taken by a fisheye lens to an image without distortion, which is suitable for the human eye. The algorithm, which is simple and effective, has been applied to the automobile surround view system. It has been verified to be accurate and reasonable, after the comparison is made between the real image taken by a fisheye lens and the corrected image.

3

Accuracy analysis of automatic distortion correction

Kolecki J., Rzonca A.

Geodesy and Cartography

|

2015

|

Vol. 64, no. 1

3--14

EN

The paper addresses the problem of the automatic distortion removal from images acquired with non-metric SLR camera equipped with prime lenses. From the photogrammetric point of view the following question arises: is the accuracy of distortion control data provided by the manufacturer for a certain lens model (not item) sufficient in order to achieve demanded accuracy? In order to obtain the reliable answer to the aforementioned problem the two kinds of tests were carried out for three lens models. Firstly the multi-variant camera calibration was conducted using the software providing full accuracy analysis. Secondly the accuracy analysis using check points took place. The check points were measured in the images resampled based on estimated distortion model or in distortion-free images simply acquired in the automatic distortion removal mode. The extensive conclusions regarding application of each calibration approach in practice are given. Finally the rules of applying automatic distortion removal in photogrammetric measurements are suggested.

PL

Publikacja ma na celu przedstawienie wyników automatycznego usuwania dystorsji dla niemetrycznej kamery z obiektywem stałoogniskowym. Z punktu widzenia fotogrametrii pojawia się zasadnicze pytanie, czy dokładność określenia dystorsji dla danego typu obiektywu (a nie egzemplarza) jest wystarczająca, żeby otrzymać oczekiwane dokładności pomiaru fotogrametrycznego. W tym celu wykonano dwa rodzaje obliczeń kontrolnych. Pierwsze obliczenia to kalibracja kamery w wariantach zapewniających szeroką dyskusję wyników, wykonana w oprogramowaniu zapewniającym podanie pełnej analizy dokładności. Dodatkowo każdy wariant został sprawdzony poprzez kalibrację kontrolną, którą policzono na podstawie pomiaru zdjęć z fizycznie usuniętym wpływem dystorsji. Drugi etap obliczeń – analiza dokładności – polegał na wykonaniu pomiarów sprawdzających punktów kontrolowanych na zdjęciach dla wszystkich 3 zestawów przyjętych lub obliczonych elementów orientacji wewnętrznej oraz dystorsji usuniętej automatycznie lub programem, na podstawie wyników kalibracji. W publikacji zamieszczono obszerny komentarz dotyczący praktycznych aspektów stosowania każdej z tych metod kalibracji. Wniosek ostateczny podaje zasady stosowania wyników automatycznej redukcji dystorsji w zastosowaniach fotogrametrycznych.

4

System for 3D localisation of malformations in the human brain

Ostergaard L. R., Lind J., Larsen O. V., Nielsen H., Bartholdy N. J., Haase J.

Machine Graphics and Vision

|

1998

|

Vol. 7, No. 1/2

159-167

EN

A 3D localisation system for pre-operating planning is presented. The developed localisation system is able to estimate the 3D position of a target, e.g. an AVM (Arterio-Venous Malformation), based on a set of digital X-ray images. Distortion correction and camera calibrations is performed in order to obtain accurate 3D estimates. The system is tested on a plexiglass phantom with embedded steel pellets offering 126 test points with known 3D positions. The test has shown that the system is able to estimate 3D positions with a mean error of 0.33 mm and a maximum error of 1.18 mm. The required accuracy is 0.16 mm and the test showed that more than 90% of the 3D position estimates fulfilthis requirement.