Information content analysis in automated microscopy imaging using an adaptive autofocus algorithm for multimodal functions

In MRI, a trade-off exists between resolution and signal-to-noise ratio, since different fractions of the available scan time can be used to acquire data at higher spatial frequencies and to perform signal averaging. By comparing a wide variety of 3D isotropic MR scans with different combinations of SNR, resolution, and scan duration, the impact of this trade-off on the image information content was assessed. The information content of mouse brain, mouse whole-body, and human brain images was evaluated using a simple numerical approach, which sums the information contribution of each individual k-space data point. Results show that, with a fixed receiver bandwidth and field of view, the information content of trade-off images is always maximized when the SNR is equal to about 16. The optimal imaging resolution is dependent on the scan duration, as well as certain MR system properties, such as field strength and coil sensitivity. These properties are, however, easily accounted for with the acquisition of a single scout MR image, and the optimal imaging resolution can then be calculated using a simple mathematical relationship. If the imaging task is approached with a predetermined resolution requirement, the same scout scan can be used to calculate the scan duration that will provide the maximum possible information. Using these relationships to maximize the image information content is an excellent technique for guiding the initial selection of imaging parameters.

EBCOT, as the baseline algorithm of JPEG-2000 final draft, is an efficient image coding technique. It is inherently more error resilient than many other wavelet-based schemes due to its independent coding of blocks in each subband. However, the loss of data of a block, in any lower frequency subband, in EBCOT can still degrade the perceptual image quality considerably. As robust entropy codes are used, the information of image content can help recover damaged regions of blocks. This paper discusses the use of reversible variable length codes (RVLC) and data partitioning for coding lower frequency subbands in EBCOT, instead of arithmetic codes. The selection of RVLC is based on content of images, which is classified as active and shape. We have observed that the proposed approach has very little additional bit-rate overhead and improved performance in the presence of errors from the help of content.

This study investigates the relation between objective and subjective parameters which relate to the quality of magnetic-resonance images, with a view to developing procedures for minimizing imaging time. The investigation uses high-resolution images of the thumb as example. Detection thresholds for an artificial lesion and ratings of image quality were obtained for a variety of images, with several experienced observers. In addition, the information content was calculated for each image, using the method developed by Fuderer (1988 IEEE Trans. Med. Imaging 7 368–80). Results suggest that information content can be used as a predictor of either detection threshold or quality rating, with a critical information content beyond which there is no significant improvement in either of these aspects of image quality. Since it is possible to estimate the effect of imaging variables on information content, it is possible to predict the effect of time-saving imaging strategies on image quality. A procedure is suggested for determining the combination of imaging variables which gives the shortest possible imaging time whilst retaining image quality.

Image-based abstraction (or summarization) of a Web site is the process of extracting the most characteristic (or important) images from it. The criteria for measuring the importance of images in Web sites are based on their frequency of occurrence, characteristics of their content and Web link information. As a case study, this work focuses on logo and trademark images. These are important characteristic signs of corporate Web sites or of products presented there. The proposed method incorporates machine learning for distinguishing logo and trademarks from images of other categories (e.g., landscapes, faces). Because the same logo or trademark may appear many times in various forms within the same Web site, duplicates are detected and only unique logo and trademark images are extracted. These images are then ranked by importance taking frequency of occurrence, image content and Web link information into account. The most important logos and trademarks are finally selected to form the image-based summary of a Web site. Evaluation results of the method on real Web sites are also presented. The method has been implemented and integrated into a fully automated image-based summarization system which is accessible on the Web (www.intelligence.tuc.gr/websummarization)

A method for processing microfocus X-ray images is described. It is based on high-frequency filtration and morphological image processing, which increases the contrast of the X-ray details. One of the most informative X-ray techniques is microfocus X-ray. In some cases, microfocus X-ray images cannot be reliably analyzed due to the peculiarities of the shooting method. So, the main disadvantages of microfocus X-ray images are most often an uneven background, distorted brightness characteristics and the presence of noise. The proposed method for enhancing the contrast of fine image details is based on the idea of combining high-frequency filtering and morphological image processing. The method consists of the following steps: noise suppression in the image, high-frequency filtering, morphological image processing, obtaining the resulting image. As a result of applying the method, the brightness of the contours in the image is enhanced. In the resulting image, all objects will have double outlines. The method was tested in the processing of 50 chest radiographs of patients with various pathologies. Radiographs were performed at the Mariinsky Hospital of St. Petersburg using digital stationary and mobile X-ray machines. In most of the radiographs, it was possible to improve the images contrast, to highlight the objects boundaries. Besides, the method was applied in microfocus X-ray tomography to improve the information content of projection data and improve the reconstruction of the 3D image of the research object. In both the first and second cases, the method showed satisfactory results. The developed method makes it possible to significantly increase the information content of microfocus X-ray images. The obtained practical results make it possible to count on broad prospects for the method application, especially in microfocus X-ray.

The objective of this paper is to present a promising technology for quantifying the surface condition of seal coated pavements and thus, assisting pavement maintenance engineers in prioritizing pavement preservation projects on a basis of measured condition rather than qualitative ratings. It details a computer analysis of over 100 Texas seal coat projects using digital imaging techniques based on information theory which permits the derivation of an objective measurement of a digital image's information content utilizing the two-dimensional Fourier transform. The information content is governed by the pavement's surface texture. This metric allows seal coat surface conditions to be quantitatively rated and for satisfactory and unsatisfactory surface textures to be differentiated. Presently, a qualitative rating system is used to program and budget seal coat maintenance projects. The paper concludes that this system provides an improved surface condition evaluation, thus, permitting a more efficient distribution of limited maintenance and construction budgets.

A fast simulated annealing algorithm is developed for automatic object recognition. The object recognition problem is addressed as the problem of best describing a match between a hypothesized object and an image. The normalized correlation coefficient is used as a measure of the match. Templates are generated on-line during the search by transforming model images. Simulated annealing reduces the search time by orders of magnitude with respect to an exhaustive search. The algorithm is applied to the problem of how landmarks, e.g., traffic signs, can be recognized by a navigating robot. We illustrate the performance of our algorithm with real-world images of complicated scenes with traffic signs. False positive matches occur only for templates with very small information content. To avoid false positive matches, we propose a method to select model images for robust object recognition by measuring the information content of the model images. The algorithm works well in noisy images for model images with high information content.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Spectral dimensionality reflects the intrinsic information content of imaging spectroscopy data. Prior work investigating spectral dimensionality has mostly either focused within a limited study area or at a single spatial resolution. Despite multiple spectrometer satellite missions in the development, the inherent information content of imaging spectroscopy images is still largely unknown. Leveraging data collected by the Global Airborne Observatory (GAO), we investigated the spectral dimensionality of common landscape types (i.e., urban, suburban, rural, agriculture, forest, shrub/grass, and wetland) across several spatial resolutions (i.e., 1 to 5, 10, 20, and 30 m). The results corresponded well to the size of the objects in the target landscape. At native spatial resolution (1 to 5 m), anthropogenic images dominated by fine-scale spectrally diverse objects usually had higher dimensionalities than natural images. But as resolution coarsened, the spectral dimensionality of images containing natural landscapes outranked anthropogenic ones, except for large-scale agriculture. Besides, there was a surprising difference in the magnitude of dimensionality decreasing trend between anthropogenic and natural scenes. Urban, suburban and rural cover types experienced dramatic drops at coarser resolutions, whereas vegetated landscapes preserved most of their dimensionality at 30-m spatial sampling. In addition to revealing the typical spectral dimensionalities of common landscapes, we provided insights into how much information might be achievable from spectroscopic analyses. Results of this study guide future imaging spectroscopy data collection and scientific applications.

Ensuring the safety and reliability of AI-based perception systems for autonomous maritime navigation critically depends on validating these systems under realistic and diverse conditions. However, the maritime sector currently lacks standardized, comprehensive datasets that capture the variability of real-world operational and environmental scenarios. To address this gap, we propose a novel approach for systematically evaluating the visual quality of maritime image datasets using a Gabor filter-based metric. This method assesses the structural information content in images and effectively distinguishes between high and low visibility conditions, which is essential for testing perception systems’ robustness. We demonstrate the approach on a large dataset collected aboard a ferry operating in the Øresund, highlighting its ability to automatically score and rank images by visibility. Our results show that the proposed metric facilitates the creation of more representative and challenging datasets, thereby supporting the development and validation of safer and more reliable autonomous maritime perception systems.

We present a new image search technique that, given a background image, returns compatible foreground objects for image compositing tasks. The compatibility of a foreground object and a background scene depends on various aspects such as semantics, surrounding context, geometry, style and color. However, existing image search techniques measure the similarities on only a few aspects, and may return many results that are not suitable for compositing. Moreover, the importance of each factor may vary for different object categories and image content, making it difficult to manually define the matching criteria. In this paper, we propose to learn feature representations for foreground objects and background scenes respectively, where image content and object category information are jointly encoded during training. As a result, the learned features can adaptively encode the most important compatibility factors. We project the features to a common embedding space, so that the compatibility scores can be easily measured using the cosine similarity, enabling very efficient search. We collect an evaluation set consisting of eight object categories commonly used in compositing tasks, on which we demonstrate that our approach significantly outperforms other search techniques.

The electrical impulses, known as electrogastrograms (EGGs), originate from the muscles of the stomach and are due to the physiological activity of the digestive system. The characteristics of these signals can be used to diagnose various human gastrointestinal disorders. Although the recording of EGG signals is a well-recognized diagnostic procedure, acquiring these signals from human subjects is difficult due to movement artifacts, and difficulties in electrode placement, and is also a time-consuming technique. Infrared thermography (IRT) is a non-contact and non-invasive technique used to detect various pathologies in humans. In this work, an attempt was made to establish the correlation between the information content (IC) of electrogastrograms and the information content of abdominal thermal images, in both normal and bradygastric subjects using Rényi entropy. The results show a strong correlation between the entropy of EGG signals and abdominal IRT images, in both normal and bradygastric subjects, with a correlation coefficient of 0.95 and 0.92, respectively. Since the information in the EGG signals and IRT images are strongly correlated, IRT can therefore be proposed as a diagnostic technique to replace EGG in the assessment of digestive diseases.

We discuss the application of harmonic analysis in second-harmonic generation microscopy in developing useful quantitative metrics for assessing tissue morphology. A comparison between the information content in forward and backward SHG images is also presented.

Principal components analysis (PCA) is effective at compressing information in multivariate data sets by computing orthogonal projections that maximize the amount of data variance. Unfortunately, information content in hyper spectral images does not always coincide with such projections. We propose an application of projection pursuit (pp), which seeks to find a set of projections that are "interesting" in the sense that they deviate from the Gaussian distribution assumption.&#x0D; Once these projections are obtained, they can be used for image compression, segmentation, or enhancement for visual analysis. To find these projections, a two –step iterative process is followed where we first search for a projection that maximizes a projection index based on the information divergence of the projections estimated probability distribution from the Gaussian distribution and then reduce the rank by projections the data on to the subspace orthogonal to the previous projection . To calculate each projections, we use a simplified approach to maximizing the projection index, which does not require optimization algorithm. It searches for a solution by obtaining a set of candidate projections from the data and choosing the one with the highest projection index. The effectiveness of the method is demonstrated through simulated examples as well as data from the hyper spectral digital imagery collection experiment and the spatially enhanced broadband and array spectrograph system.

Guidelines for the digital conversion of transmissive content (negatives and positive slides) in the cultural heritage community have lagged behind those for print content. The primary reasons for this are twofold. Unlike print material, transmissive content is generally an intermediate format (as with negatives) or requires a viewing mechanism (such as a projector). In either case, there is no standard for the viewing of the object. The second challenge for digitization of transmissive content is, in large part, a result of the ambiguity of the visual output for slides or negatives. Typical guidelines for the resolution in digitizing transmissive content have concentrated either on the limits inherent in scanning equipment or attempted to base resolution on the microstructure (e.g., grain) of the negatives or slides, and not on the actual image information content in the film.With special regard to the latter and in response to a project to digitize negatives from the Farm Security Administration (FSA) collection at the Library of Congress, the first part of this study investigated methods for establishing scanning resolution requirements for B&amp;W silver-gelatin film negatives from the early to mid 20th Century based on defined use cases. The use case described by the curators of the FSA collection for resolution was based on the information content of the original photographic image and not on a film's granular microstructure. In other words, actual image information captured and not the inherent grain structure itself. This study describes the methodology used for determining the limiting resolution of film capture, and presents the results of the study for the FSA collection, as well as the application to all similar transmissive content. Examples will be provided to demonstrate the utility of this approach.In addition to silver-gelatin B&amp;W film negatives, the second category of transmissive photographic originals studied was early color positive processes, specifically Autochrome and Dufaycolor. The nature and perception of the image for these processes is very different than the typical image and silver grain structures of typical B&amp;W negatives. In addition to the color information, these photographs represent a very distinct class of original and different use case requirements. Investigation of these materials provided an opportunity to expand the research methodology used for determining appropriate scanning resolution.

Principal Components Analysis is very effective at compressing information in multivariate data sets by computing orthogonal projections that maximize the amount of signal variance. Unfortunately, information content in hyperspectral images does not always coincide with such projections. We propose the application of Projection Pursuit, which seeks to find a set of orthogonal projections that are 'interesting' in the sense that they deviate from the Gaussian distribution assumption. Once these projections are obtained, they can be used for image compression, segmentation, or enhancement for visual analysis. To find these projections we follow a 2-step iterative process where we first search for a projection that maximizes a projection index based on the divergence of the projection's estimated probability distribution from the Gaussian distribution, and then reduce the rank by projecting the data onto the subspace orthogonal to the previous projections. To find the projection that maximizes the index, a novel approach is taken which does not use an optimization algorithm, but rather searches for a solution by obtaining a set of candidate projections from the data and choosing the one with the highest projection index. This method is shown to work with simulated examples as well as data for the Hyperspectral Digital Imagery Collection Experiment.