Low-dose shift- and rotation-invariant diffraction recognition imaging.
Ontology highlight
ABSTRACT:
SUBMITTER: Latychevskaia T
PROVIDER: S-EPMC9249920 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The utilization of scale invariant feature transform algorithm in synthetic-aperture radar images (SAR-SIFT) to match image features may lead to principal orientation assignments of descriptors being affected by speckle noise, thereby diminishing accuracy. In this study, we propose using the Fourier histogram of oriented ratio gradient (Fourier HORG) descriptor for robust matching of SAR images. This method is based on the SAR-SIFT algorithm framework. During feature description, the rotation-invariant Fourier HORG descriptor is established by performing Fourier analysis on the ratio gradient in the polar coordinate system, whereby the principal orientation assignment process is avoided and the robustness of SAR image registration improved. A matching experiment was conducted involving four sets of SAR image pairs, and the results demonstrated that our method exhibited higher accuracy and robustness compared to image matching based on the Fourier histogram of oriented gradient (Fourier HOG) descriptor and the SAR-SIFT algorithm, thus confirming the effectiveness of our proposed method.
| S-EPMC10477315 | biostudies-literature
Project description:Accurate and on-demand animal population counts are the holy grail for wildlife conservation organizations throughout the world because they enable fast and responsive adaptive management policies. While the collection of image data from camera traps, satellites, and manned or unmanned aircraft has advanced significantly, the detection and identification of animals within images remains a major bottleneck since counting is primarily conducted by dedicated enumerators or citizen scientists. Recent developments in the field of computer vision suggest a potential resolution to this issue through the use of rotation-invariant object descriptors combined with machine learning algorithms. Here we implement an algorithm to detect and count wildebeest from aerial images collected in the Serengeti National Park in 2009 as part of the biennial wildebeest count. We find that the per image error rates are greater than, but comparable to, two separate human counts. For the total count, the algorithm is more accurate than both manual counts, suggesting that human counters have a tendency to systematically over or under count images. While the accuracy of the algorithm is not yet at an acceptable level for fully automatic counts, our results show this method is a promising avenue for further research and we highlight specific areas where future research should focus in order to develop fast and accurate enumeration of aerial count data. If combined with a bespoke image collection protocol, this approach may yield a fully automated wildebeest count in the near future.
| S-EPMC4881999 | biostudies-literature
Project description:Two-dimensional (2D) materials have attracted interest because of their excellent properties and potential applications. A key step in realizing industrial applications is to synthesize wafer-scale single-crystal samples. Until now, single-crystal samples, such as graphene domains up to the centimeter scale, have been synthesized. However, a new challenge is to efficiently characterize large-area samples. Currently, the crystalline characterization of these samples still relies on selected-area electron diffraction (SAED) or low-energy electron diffraction (LEED), which is more suitable for characterizing very small local regions. This paper presents a highly efficient characterization technique that adopts a low-energy electrostatically focused electron gun and a super-aligned carbon nanotube (SACNT) film sample support. It allows rapid crystalline characterization of large-area graphene through a single photograph of a transmission-diffracted image at a large beam size. Additionally, the low-energy electron beam enables the observation of a unique diffraction pattern of adsorbates on the suspended graphene at room temperature. This work presents a simple and convenient method for characterizing the macroscopic structures of 2D materials, and the instrument we constructed allows the study of the weak interaction with 2D materials.
| S-EPMC5580878 | biostudies-literature
Project description:We present a new technology for super-resolution fluorescence imaging, based on conical diffraction. Conical diffraction is a linear, singular phenomenon, taking place when a laser beam is diffracted through a biaxial crystal. We use conical diffraction in a thin biaxial crystal to generate illumination patterns that are more compact than the classical Gaussian beam, and use them to generate a super-resolution imaging modality. While there already exist several super-resolution modalities, our technology (biaxial super-resolution: BSR) is distinguished by the unique combination of several performance features. Using BSR super-resolution data are achieved using low light illumination significantly less than required for classical confocal imaging, which makes BSR ideal for live-cell, long-term time-lapse super-resolution imaging. Furthermore, no specific sample preparation is required, and any fluorophore can be used. Perhaps most exciting, improved resolution BSR-imaging resolution enhancement can be achieved with any type of objective no matter the magnification, numerical aperture, working distance, or the absence or presence of immersion medium. In this article, we present the first implementation of BSR modality on a commercial confocal microscope. We acquire and analyze validation data, showing high quality super-resolved images of biological objects, and demonstrate the wide applicability of the technology. We report live-cell super-resolution imaging over a long period, and show that the light dose required for super-resolution imaging is far below the threshold likely to generate phototoxicity.
| S-EPMC4594584 | biostudies-literature
Project description:MOTIVATION:Neural networks have been widely used to analyze high-throughput microscopy images. However, the performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Highly relevant to the goal of automated cell phenotyping from microscopy image data is rotation invariance. Here we consider the application of two schemes for encoding rotation equivariance and invariance in a convolutional neural network, namely, the group-equivariant CNN (G-CNN), and a new architecture with simple, efficient conic convolution, for classifying microscopy images. We additionally integrate the 2D-discrete-Fourier transform (2D-DFT) as an effective means for encoding global rotational invariance. We call our new method the Conic Convolution and DFT Network (CFNet). RESULTS:We evaluated the efficacy of CFNet and G-CNN as compared to a standard CNN for several different image classification tasks, including simulated and real microscopy images of subcellular protein localization, and demonstrated improved performance. We believe CFNet has the potential to improve many high-throughput microscopy image analysis applications. AVAILABILITY AND IMPLEMENTATION:Source code of CFNet is available at: https://github.com/bchidest/CFNet. SUPPLEMENTARY INFORMATION:Supplementary data are available at Bioinformatics online.
| S-EPMC6612823 | biostudies-other
Project description:Key properties of inferior temporal cortex neurons are described, and then, the biological plausibility of two leading approaches to invariant visual object recognition in the ventral visual system is assessed to investigate whether they account for these properties. Experiment 1 shows that VisNet performs object classification with random exemplars comparably to HMAX, except that the final layer C neurons of HMAX have a very non-sparse representation (unlike that in the brain) that provides little information in the single-neuron responses about the object class. Experiment 2 shows that VisNet forms invariant representations when trained with different views of each object, whereas HMAX performs poorly when assessed with a biologically plausible pattern association network, as HMAX has no mechanism to learn view invariance. Experiment 3 shows that VisNet neurons do not respond to scrambled images of faces, and thus encode shape information. HMAX neurons responded with similarly high rates to the unscrambled and scrambled faces, indicating that low-level features including texture may be relevant to HMAX performance. Experiment 4 shows that VisNet can learn to recognize objects even when the view provided by the object changes catastrophically as it transforms, whereas HMAX has no learning mechanism in its S-C hierarchy that provides for view-invariant learning. This highlights some requirements for the neurobiological mechanisms of high-level vision, and how some different approaches perform, in order to help understand the fundamental underlying principles of invariant visual object recognition in the ventral visual stream.
| S-EPMC4572081 | biostudies-literature
Project description:A DigitalMicrograph script, InsteaDMatic, has been developed to facilitate rapid automated 3D electron diffraction/microcrystal electron diffraction data acquisition by continuous rotation of a crystal with a constant speed, denoted as continuous rotation electron diffraction. The script coordinates microscope functions, such as stage rotation, and camera functions relevant for data collection, and stores the experiment metadata. The script is compatible with any microscope that can be controlled by DigitalMicrograph and has been tested on both JEOL and Thermo Fisher Scientific microscopes. A proof of concept has been performed through employing InsteaDMatic for data collection and structure determination of a ZSM-5 zeolite. The influence of illumination settings and electron dose rate on the quality of diffraction data, unit-cell determination and structure solution has been investigated in order to optimize the data acquisition procedure.
| S-EPMC7534539 | biostudies-literature
Project description:Single-crystal electron diffraction (SCED) is emerging as an effective technique to determine and refine the structures of unknown nano-sized crystals. In this work, the implementation of the continuous rotation electron diffraction (cRED) method for high-throughput data collection is described. This is achieved through dedicated software that controls the transmission electron microscope and the camera. Crystal tracking can be performed by defocusing every nth diffraction pattern while the crystal rotates, which addresses the problem of the crystal moving out of view of the selected area aperture during rotation. This has greatly increased the number of successful experiments with larger rotation ranges and turned cRED data collection into a high-throughput method. The experimental parameters are logged, and input files for data processing software are written automatically. This reduces the risk of human error, and makes data collection more reproducible and accessible for novice and irregular users. In addition, it is demonstrated how data from the recently developed serial electron diffraction technique can be used to supplement the cRED data collection by automatic screening for suitable crystals using a deep convolutional neural network that can identify promising crystals through the corresponding diffraction data. The screening routine and cRED data collection are demonstrated using a sample of the zeolite mordenite, and the quality of the cRED data is assessed on the basis of the refined crystal structure.
| S-EPMC6276279 | biostudies-literature
Project description:Multispectral palmprint recognition has shown broad prospects for personal identification due to its high accuracy and great stability. In this paper, we develop a novel illumination-invariant multispectral palmprint recognition method. To combine the information from multiple spectral bands, an image-level fusion framework is completed based on a fast and adaptive bidimensional empirical mode decomposition (FABEMD) and a weighted Fisher criterion. The FABEMD technique decomposes the multispectral images into their bidimensional intrinsic mode functions (BIMFs), on which an illumination compensation operation is performed. The weighted Fisher criterion is to construct the fusion coefficients at the decomposition level, making the images be separated correctly in the fusion space. The image fusion framework has shown strong robustness against illumination variation. In addition, a tensor-based extreme learning machine (TELM) mechanism is presented for feature extraction and classification of two-dimensional (2D) images. In general, this method has fast learning speed and satisfying recognition accuracy. Comprehensive experiments conducted on the PolyU multispectral palmprint database illustrate that the proposed method can achieve favorable results. For the testing under ideal illumination, the recognition accuracy is as high as 99.93%, and the result is 99.50% when the lighting condition is unsatisfied.
| S-EPMC5448787 | biostudies-literature
Project description:Invariant stimulus recognition is a challenging pattern-recognition problem that must be dealt with by all sensory systems. Since neural responses evoked by a stimulus are perturbed in a multitude of ways, how can this computational capability be achieved? We examine this issue in the locust olfactory system. We find that locusts trained in an appetitive-conditioning assay robustly recognize the trained odorant independent of variations in stimulus durations, dynamics, or history, or changes in background and ambient conditions. However, individual- and population-level neural responses vary unpredictably with many of these variations. Our results indicate that linear statistical decoding schemes, which assign positive weights to ON neurons and negative weights to OFF neurons, resolve this apparent confound between neural variability and behavioral stability. Furthermore, simplification of the decoder using only ternary weights ({+1, 0, -1}) (i.e., an "ON-minus-OFF" approach) does not compromise performance, thereby striking a fine balance between simplicity and robustness.
| S-EPMC8764697 | biostudies-literature