Reliably detecting or tracking 3D features is challenging. It often requires preprocessing and filtering stages, along with fine-tuned heuristics for reliable detection. Alternatively, artificial intelligence-based strategies have recently been proposed; however, these typically require many manually labeled images for training. We introduce a method for 3D feature detection by using a convolutional neural network and a single 3D image obtained by fringe projection profilometry. We cast the problem of 3D feature detection as an unsupervised detection problem. Hence, the goal is to use a neural network that learns to detect specific features in 3D images using a single unlabeled image. Therefore, we implemented a deep-learning method that exploits inherent symmetries to detect objects with few training data and without ground truth. Subsequently, using a pyramid methodology of rescaling each image to be processed, we achieved feature detections of different sizes. Finally, we unified the detections using a non-maximum suppression algorithm. Preliminary results show that the method provides reliable detection under different scenarios with a more flexible training procedure than other competing methods.
White Light Scanning Interferential Microscopy (WLSI) is a widely used technique for determining the 3D topography of surfaces with nanometer resolution. However, despite obtaining the topography with adequate resolution, the precise information of the object’s reflectance is lost due to a degrading of the microscopy images with interference fringes. These fringes make it challenging to obtain an extended focus image (EFI) to inspect details of the entire surface, as is done in standard microscopy. The typical procedure to estimate the reflected intensity of the object is to perform an averaging of the depth interference intensity signal. However, for many samples of the intensity signal, the effect of blurring becomes noticeable. Alternatively, in the case of few samples, remnant artifacts of the interference fringe patterns remain. In this work, we determine an adequate axial range that represents an optimal window for averaging and estimating the intensity of an EFI. A series of WLSI interference images were simulated, and EFI images were calculated by averaging over axial lengths normalized relative to the depth of field. Each EFI was compared with the reference image using the signal-to-noise ratio (SNR) and the universal quality index (UQI) metrics with the highest values obtained of 44.332 and 0.9997, respectively, for an axial range of 0.28DOF.
This paper proposes an approach to facilitate the process of individualization of patients from their medical images, without compromising the inherent confidentiality of medical data. The identification of a patient from a medical image is not often the goal of security methods applied to image records. Usually, any identification data is removed from shared records, and security features are applied to determine ownership. We propose a method for embedding a QR-code containing information that can be used to individualize a patient. This is done so that the image to be shared does not differ significantly from the original image. The QR-code is distributed in the image by changing several pixels according to a threshold value based on the average value of adjacent pixels surrounding the point of interest. The results show that the code can be embedded and later fully recovered with minimal changes in the UIQI index - less than 0.1% of different.
This paper describes a region growing segmentation algorithm for medical ultrasound images. The algorithm
starts with anisotropic diffusion filtering to reduce speckle noise without blurring the edges. Then, region growing
is performed starting from a seed point, using a merging criterion that compares intensity gradients to the noise
level inside the region. Finally, the boundaries are smoothed using morphological closing. The algorithm was
evaluated with two simulated images and eleven phantom images and converged in 10 of them with accurate
region delimitation. Preliminary results show that the proposed method can be used for ultrasound image
segmentation and does not require previous knowledge of the anatomy of the structures.
We propose a method for calculating appropriate α-band limited diffusers using the fractional Fourier transform. In order to do this, we implement a method for performing a numerical interpolation in the fractional Fourier domain. Such diffusers with compact support in the Fresnel regime may be used in fractional Fourier optical systems where the use of diffusers produce speckles, e.g. digital holography or optical encryption. Numerical simulations are presented.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.