Bad Contrast Research Articles

Assessing the interplay of contrast, defocus, and resolution in cryo-EM: a benchmark experiment for limited dataset screening

The selection of defocus ranges for small datasets in cryo-electron microscopy (cryo-EM) is under-researched. We present a comprehensive benchmark experiment that aimed to evaluate the relationship between contrast, defocus, and resolution, particularly in the context of limited datasets. We conducted a detailed analysis of beta-galactosidase, apo-ferritin, and connexin-46/50 datasets to optimize pre-screening strategies for cryo-EM. Our approach involved classifying micrographs based on image contrast using an artificial intelligence (AI) model without considering the defocus level. This method allowed us to investigate the optimal defocus range for pre-screening in a limited dataset and its impact on the overall image processing. The micrographs were categorized into good, moderate, and bad contrast groups. Subsequent analysis revealed that, contrary to the prevailing assumption that lower contrast (associated with lower defocus) leads to higher resolution, in scenarios with limited datasets higher contrast images yield superior resolution. This finding was consistent across all three protein samples, underscoring the critical role of contrast in determining the quality of 3D reconstructions in limited datasets. This significant finding challenges conventional cryo-EM methodologies. In conclusion, our study provides new benchmarks for selecting appropriate contrast and defocus levels in cryo-EM, particularly for screening approaches that use limited datasets. This strategy promises to enhance the data quality and efficiency in structural biology research, particularly in resource-constrained scenarios.

Iris Recognition based on Statistically Bound Spatial Domain Zero Crossing and Neural Networks

Purpose The iris pattern is an important biological feature of the human body. The recognition of an individual based on an iris pattern is gaining more popularity due to the uniqueness of the pattern among the people. Iris recognition systems have received attention very much due to their rich iris texture which gives robust standards for identifying individuals. Notwithstanding this, there are several challenges in unrestricted recognition environments. Methods This article discusses a highly error-resistant technique to implement a biometric recognition system based on the iris portion of the human eye. All iris recognition algorithms of the current day face a major problem of localization errors and the enormous time involved in this localization process. Spatial domain zero crossing may be the simplest and least complex method for localization. Yet, it has not been used due to its high sensitivity to erroneous edges, as a consequence of which more complex and time-consuming algorithms have taken its place. Appropriate statistical bounds imposed on this process help this method to be the least erroneous and time-consuming. Errors were reduced to 0.022% using this approach on the CASIA v1 & v2 datasets. Time consumption in this stage was the least compared to other algorithms. At the comparison stage, most algorithms use multiple comparisons to account for translation and rotation errors. This is time-consuming and very resource-hungry. Results The current approach discusses a robust method based on a single comparison, which works with a correct recognition of over 99.78% which is clearly demonstrated by tests. Conclusions The technique is to use a neural network trained to recognize special statistical and regional parameters unique to every person’s iris. The algorithm also gives sufficient attention to consider illumination errors, elliptical pupils, excess eyelash errors and bad contrast.

A Novel AI-Based Approach for Better Segmentation of the Fungal and Bacterial Leaf Diseases of Rice Plant

Rice is the most consumed food for more than half the world. All over the world, approximately 15% of the rice get wasted because of leaf diseases. A computer-aided system needs a clear segmented lesion to detect such diseases, but blurriness, bad contrast, and dust particles on leaves are the challenge in proper segmentation and, further, for better feature extraction. In this work, first, SegNet deep learning model was trained to separate the weed from the images captured from the field; then, in the next step, a novel automated segmentation technique named RPK-means proposed combining random path (RP) and K-means clustering to separate lesion spots from the leaf images. The work of the model is multifold. First, the SegNet model is trained for weed separation; then, two clusters of the image are generated by K -means clustering to find out pixel coordinates lying on the lesion spot and healthy part of the leaves. Thereafter, to separate the lesion part from the background, automatic segmentation is performed by the novel random path K -means (RPK-means) method using coordinate positions obtained at the last stage. Fungal and bacterial diseases like brown spot, rice blast, sheath blight, leaf scaled, and bacterial blight have been collected from the field to perform the experiments. Experimental result shows that the performance of the deep learning classifier increased by approximately 2-6% while applying to RPK-means preprocessed images, rather than the traditional K -means segmentation technique.

A Smart Visual Sensing Concept Involving Deep Learning for a Robust Optical Character Recognition under Hard Real-World Conditions.

In this study, we propose a new model for optical character recognition (OCR) based on both CNNs (convolutional neural networks) and RNNs (recurrent neural networks). The distortions affecting the document image can take different forms, such as blur (focus blur, motion blur, etc.), shadow, bad contrast, etc. Document-image distortions significantly decrease the performance of OCR systems, to the extent that they reach a performance close to zero. Therefore, a robust OCR model that performs robustly even under hard (distortion) conditions is still sorely needed. However, our comprehensive study in this paper shows that various related works can somewhat improve their respective OCR recognition performance of degraded document images (e.g., captured by smartphone cameras under different conditions and, thus, distorted by shadows, contrast, blur, etc.), but it is worth underscoring, that improved recognition is neither sufficient nor always satisfactory—especially in very harsh conditions. Therefore, in this paper, we suggest and develop a much better and fully different approach and model architecture, which significantly outperforms the aforementioned previous related works. Furthermore, a new dataset was gathered to show a series of different and well-representative real-world scenarios of hard distortion conditions. The new OCR model suggested performs in such a way that even document images (even from the hardest conditions) that were previously not recognizable by other OCR systems can be fully recognized with up to 97.5% accuracy/precision by our new deep-learning-based OCR model.

One-shot beam-forming with adaptively weighted compound of multiple transmission angles and subbands

We previously proposed a beamformer that adaptively compounds echoes for different subbands and transmission angles. This methodology requires the transmission and reception of multiple plane waves. Thus, in the present study, we examine a method that approximates the previous method with one transmission and reception. We assign different subbands to each transmission direction angle and simultaneously transmit one shot as a chirp signal; hence, echoes for all subbands can be received simultaneously. Then, through pulse compression, the received echo is separated into each subband, and we apply our previously proposed compound procedure to achieve imaging using one-shot beamforming. The evaluation of the method performance was conducted by finite element simulation. The results show that the obtained image is almost the same resolution as the original beamformer, but with a worse contrast. The cause and solution of the contrast deterioration are also reported in this paper.

Convolution neural network model for fundus photograph quality assessment

<span>The excellent quality of color fundus photograph is crucial for the ophthalmologist to process the correct diagnosis and for convolutional neural network (CNN) models to optimize output classification. As a result of main causes as acquire devises efficiency and experience of a physician most fundus photographs can have uneven illuminance, blur, and bad contrast, in addition to micro-features of retinal diseases, which need to force their contrast. Fundus photograph quality assessment method is proposed to find out the perfect enhanced color fundus Technique in fundoscopy photographs-based CNN model. Five photograph quality measurements, in addition to five CNN metrics, were used as standard in this study. In this research innovative approach combining photograph quality measurement and CNN metrics analysis is proposed to find out the best enhance method that is set for the multiclass CNN model. The contrast enhancement techniques are evaluated using 267 color fundus photographs divided into three retina diseases cases were downloaded from the open-source database “FIGSHARE”. The study outcome showed that the presented system (single-CNN) can determine well the contrast enhancement method, as well as the low-quality fundus photograph then it can boost CNN metrics to achieve superior.</span>

Real-time clipper tip visibility detection using computer vision

Abstract Objective Laparoscopic cholecystectomy is one of the most common laparoscopic procedures. The critical phase of this intervention consists in dissecting the hepatocystic triangle and clipping the cystic artery and duct. Poor visibility of the clipper tips can result in unintentional clipping of neighboring tissues (“past-pointing”) or improper enclosing of the artery or duct, leading to hemorrhage or bile leaks. To improve patient safety during this clipping phase, we propose real-time intraoperative feedback to alert a surgeon when departing from safe behavior, i.e., losing visibility of the clipper tip. This is achieved using a deep learning model which classifies the clipper tip visibility in each frame. Methods We tailored a dataset for our application by selecting frames containing a clipper that were selected from 300 laparoscopic cholecystectomy videos. These 122k frames were annotated with binary labels: clipper tip visible/invisible. A frame was labelled as tip visible when the tips of both clipper jaws were visible. Frames in which the clipper tip was occluded (e.g. by tissue) or frames with poor image quality (e.g., bad contrast, blurriness/smoke) were labelled as tip invisible. Frames from 29 videos were set aside for a test set; the remaining frames were used for training/validation (80%, 20% resp.). Using a 5-fold cross-validation scheme, convolutional neural networks (Resnet50 architecture) were trained to classify the clipper tip visibility in each frame. Finally, 5 neural networks trained in the cross-validation were ensembled into a single model by averaging their predictions. Results On the test set, the ensembled model achieved an AUROC of 0.906 and a specificity of 64.5% at 95% sensitivity. Looking at per video performance, the median specificity across videos raised to 76.6% (at 95% sensitivity). That is, the model would correctly detect 95% of the clipper tip not visible cases; in the majority of the interventions, 7 out of 10 warnings would be justified. Conclusion We propose a novel safety feedback which warns on poor visibility of the clipper while clipping the cystic duct or artery. While being accurate, our technical solution runs in real-time, a requirement for intraoperative use. We believe this feedback can raise surgeons’ attentiveness when departing from safe visibility during this critical phase of laparoscopic cholecystectomy.

The relationship between neurovascular coupling, vision and sensory performance, and concussion history in Special Operations Forces combat soldiers

Objective To determine the relationship between neurovascular coupling (NVC), vision and sensory performance in Special Operations Forces (SOF) combat soldiers with and without concussion history. Methods We studied 61 SOF combat soldiers (male, age = 33.8 ± 3.7 years, n = 40 with concussion history [Median = 3; range = 1–10+]). We instrumented our participants with transcranial Doppler to quantify NVC response during reading and visual search tasks. All participants completed vision and sensory performance testing (Senaptec Sensory Station). We performed separate multiple regressions to determine if relationships between NVC and vision and sensory performance testing existed while controlling for concussion history, and to investigate the interaction between NVC and concussion history. Results Those with higher visual search NVC response magnitudes demonstrated significantly worse contrast sensitivity when controlling for concussion history (F 1,60=4.57, ß = 0.03, p = .04, R 2 = 12.6%). We did not observe any other significant relationships between NVC and visual and sensory performance tests nor did we observe any significant interactions between NVC and concussion history (p > .05). Conclusions Heightened NVC response magnitudes are related to reduced contrast sensitivity in SOF combat soldiers. Because concussion history does not impact the relationships between outcomes, these measures may be utilized for performance evaluation at any point in a soldier’s career. The lack of relationships between NVC response magnitude and some of the other vision and sensory performance outcomes suggests that implementing NVC assessment may add unique information and enable clinicians to detect physiological deficits that may otherwise go undetected.

Deep Convolutional Network for Stereo Depth Mapping in Binocular Endoscopy

Depth mapping from binocular endoscopy images plays an important role in stereoscopic surgical treatment. Owing to the development of deep convolutional neural networks (CNNs), binocular depth estimation models have achieved many exciting results in the fields of autonomous driving and machine vision. However, the application of these methods to endoscopic imaging is greatly limited by the fact that binocular endoscopic images not only are rare, but also have unsatisfying features such as no texture, no ground truth, bad contrast, and high gloss. Aiming at solving the above-mentioned problems, we have built a precise gastrointestinal environment by the open-source software blender to simulate abundant binocular endoscopy data and proposed a 23-layer deep CNNs method to generate real-time stereo depth mapping. An efficient scale-invariant loss function is introduced in this paper to accommodate the characteristics of endoscope images, which improves the accuracy of achieved depth mapping results. Regarding the considerable training data for typical CNNs, our method requires only a few images ($960\times 720$ resolution) at 45 frames per second on an NVIDIA GTX 1080 GPU module, then the depth mapping information is generated in real-time with satisfactory accuracy. The effectiveness of the developed method is validated by comparing with state-of-the-art methods on processing the same datasets, demonstrating a faster and more accurate performance than other model frames.

Adaptive enhancement of underwater images using multi-objective PSO

Underwater images have poor clarity and bad contrast due to low illumination in deep water. Moreover, underwater images are bluish-green in appearance due to inherent wavelength absorption property of water. Therefore, the study of underwater images is a difficult task. Being computationally simple, histogram-based enhancement techniques are obvious choice for improvement of contrast and color of underwater images. However, due to lack of any guidance mechanism, these techniques can overstretch the histogram leading to artifacts in the image. Hence, an adaptive method named ‘Contrast and Information Enhancement of Underwater Images’ (CIEUI) is proposed, which enhances underwater images by improving their contrast and information content using Multi-Objective Particle Swarm Optimization (MOPSO). Objective functions of MOPSO are chosen to act as guiding mechanism to ensure color & contrast correction and information enhancement respectively without introducing artifacts. Computed results not only have good contrast and color performance but also have better information content. The proposed CIEUI technique performs quantitatively and qualitatively better as compared to state-of-the-art algorithms.

Segmentation and Vein Extraction in Sclera for Human Identification

In this paper the main contribution is statistical approaches based image segmentation method, and is able to pointout the circular pupil and sclera area, occluding eyelashes and eyelids, and reflections by a technique Image cropping. Proposed segmentation method is followed with investigation of five feature extraction techniques, viz. Statistical approaches, Glare Area Detection, Wavelet transforms, Lifting wavelet transforms and finally Contour let transform to extract features and to encode and decode the particular parameters of the iris into a bit-wise biometric template. A comparative analysis is done for these techniques with the proposed segmentation method. The green channel extraction measure and Separable Power was employed for classification, finally for classification adopting train iris image deviated output image methods is imported out. The proposed iris recognition method that uses Glare Area Detection and database identification for feature extraction performed with a near-perfect identification in different sclera pictures. This proposed system demonstrates that combination of proposed segmentation approach and feature extraction method in this work helps to improve overall performance and significant increase in the sclera recognition accuracy. The algorithm is robust for noisy conditions such as errors, elliptical pupils, excess eyelash occlusion errors and bad contrast.

Combination of fixative agents and fixation times to visually differentiate the cortical from the medullary layer in bovine adrenal glands.

Chronic stress exposure commonly increases adrenals weight and changes their morphology. This study aimed to compare four methods to delimitate the cortical and medullary layers of adrenals glands in Nelore bulls. Fresh adrenals did not present differentiation between layers. Then, frozen adrenals were distributed in plastics bags with fixative Bouin (G1), 96ºGL ethylic alcohol (G2), 10% formaldehyde (G3), or 2.5% glutaraldehyde (G4). After 12 hours of fixation, the G1 adrenal glands did not show the entire cortical layer marked by Bouin's solution. For G2 and G3 there was a poor contrast, while for G4 there was a reasonable contrast. After 24 hours of fixation, G1 had an excellent contrast between layers, while G2 and G4 had a reasonable contrast and G3 a very bad contrast. After 48 hours it was difficult to differentiate cortical and medullar layers for G1; for Group 2 we get a reasonable contrast; and for G3 the contrast was bad. For G4 the contrast was not as sharp due to the medulla became dark. It was concluded that fixation of adrenals must be done in Bouin's solution for 24 hours to obtain an effective evaluation of the adrenals' morphometry.

Local Histogram Equalization Based on OTSU

Histogram equalization is a precondition for an accurate extraction of image features. This paper is to find an appropriate image enhancement method for images with bad contrast features and small target regions. In two different application cases, by analyzing and comparing the results and gray value features, three local histogram equalization methods based on gray segment are evaluated. The local histogram equalization method based on OTSU is then proved to be good in considering its property of emphasizing details while ensuring the overall image’s uniformity.

Problems of Bad Contrast in Conventional Microscopy Solution and Speckle Elimination with a Laser Fourier Holographic Microscope

The problem of bad contrast in conventional microscopy is well-known and was solved in part by colouring the samples. It is shown theoretically that a laser Fourier holographic microscope produces images undisturbed by speckle-noise. A laser holographic microscope (LHM) is investigated experimentally. The instrument uses visible radiation of λ = 0.514 µm, Mach – Zehnder scheme optical setup, and CCD detector of the hologram. Images are reconstructed digitally. The standard slide of Parascaris Univalens Iarva (ascaris) is studied without any drying as for electron microscope. Comparison of the pictures of the same ascaris cell, observed by the LHM and high-quality Nikon conventional optical microscope with immersion oil and green filter indicates dramatically different contrast. The ultrahigh contrast of the LHM gives much more micromorphological information.

Automated Link Generation for Sensor-Enriched Smartphone Images

The ubiquity of the smartphones makes them ideal platforms for generating in-situ content. In well-attended events, photos captured by attendees have diverse views that could be subjected to occlusion and abnormal lighting effects that could obscure the view. Such unstructured photo collections also have significant redundancy. Thus, a scene that is partially occluded or has bad contrast in one photo may be captured in another photo, possibly with higher details. We propose an application called Autolink that automatically establishes content-based links between sensor-annotated photos in unstructured photo collections captured using smartphones, such that users could navigate between high-context and high-detail images. This hierarchically structured image collection facilitates the design of applications for navigation and discovery, analytics about user photography patterns, user taste, and content/event popularity. Autolink includes a framework that constructs this hierarchy efficiently and with little content-specific training data by combining photo content processing with associated sensor logs obtained from multiple participants. We evaluated the performance of Autolink on two real-world sensor tagged photo datasets. The result shows that Autolink is able to efficiently cluster photos at 20 times faster than candidate algorithms, into the appropriate hierarchy with at least 70% precision and 37% better recall than candidate algorithms.

Image Enhancement Techniques: A Study

Image enhancement is considered as one of the most important techniques in image research. The main aim of image enhancement is to enhance the quality and visual appearance of an image, or to provide a better transform representation for future automated image processing. Many images like medical images, satellite, aerial images and also real life photographs suffer from poor and bad contrast and noise. It is necessary to enhance the contrast and remove the noise to increase image quality. One of the most important stages in medical images detection and analysis is Image Enhancement Techniques. It improves the clarity of images for human viewing, removing blurring and noise, increasing contrast, and revealing details. These are examples of enhancement operations. The enhancement technique differs from one field to another depending on its objective. The existing techniques of image enhancement can be classified into two categories: Spatial Domain and Frequency Domain Enhancement. In this paper, we present an overview of Image Enhancement Processing Techniques in Spatial Domain. More specifically, we categorise processing methods based representative techniques of Image enhancement. Thus the contribution of this paper is to classify and review Image Enhancement Processing Techniques as well as various noises has been applied to the image. Also we applied various filters to identify which filter is efficient in removing particular noises. This is identified by comparing the values obtained in PSNR and MSE values. From this we can get an idea about which filters is best for removing which types of noises. It will be useful and easier to detect the filters for future research.

Associations Between Falls, Balance Confidence, Driving Speed, Braking, and Other Driving Practices in Parkinson's Disease

ABSTRACTAims: Factors related to fall risk (balance confidence, motor, visual, and cognitive deficits) may also affect the driving practices of people with Parkinson's disease (PD). The purpose of this study was to explore these potential associations. Methods: A sample of 11 self-reported fallers (mean age 72.3 ± 6.0 years; 55% men) and 16 non-fallers (mean age 71.1 ± 7.2 years; 100% men) were assessed on a battery of clinical measures and brake reaction and response time. Electronic devices were installed in vehicles to examine naturalistic driving practices. Results: In the sample overall, lower balance confidence scores were associated with worse contrast sensitivity, higher levodopa equivalency dosage, and more reported driving avoidance. Fallers had significantly lower balance confidence (p < 0.01), more episodes of hard braking (p < 0.05), and drove at slower speeds (km/hour) on most roadways (p < 0.05). Conclusions: Researchers and clinicians should consider mobility problems, particularly recurrent falls and balance confidence, which may influence driving practices.

Adaptive De-Noising Approach for Underwater Side Scan Sonar Image

It is difficult to detect the edges of objects in side scan sonar images due to the complex background, bad contrast and deteriorate edges. Therefore, it is important to remove noise from side scan sonar images. The traditional de-noising methods for optical images may not work well on the sonar image. In this paper, an adaptive de-noising approach is used. The side scan sonar image is first filtered using mean filter to remove the rough noise, then a weighted function is generated using spatial distance filter and intensity distance filter. The parameters are adaptive according to the sonar image. The experimental results indicate that it is an effective de-noising method for underwater sonar image.

Associations Between Contrast Sensitivity and Aging

The aim of this study was to assess age-related visual functions (visual acuity and contrast sensitivity) and compare the results by different age groups. A total of 231 patients were examined. The patients were divided into 5 age groups: 10 patients in group 1, 30-39 years; 40 patients in the group 2, 40-49 years; 77 patients in the group 3, 50-59 years; 71 patients in the group 4, 60-70 years; and 33 patients in the group 5, 71-85 years. A typical Snellen's chart (the direction of the gap in Landolt C) was used for noncorrected and best-corrected visual acuity testing. Contrast sensitivity was evaluated by employing a Ginsburg Box, VSCR-CST-6500. Noncorrected visual acuity was significantly better in the group 2 than the group 3 (0.86 [0.28] vs. 0.69 [0.33], P=0.018). Moreover, noncorrected and best-corrected visual acuity was significantly better in the group 4 than the group 5 (0.52 [0.35] vs. 0.35 [0.28], P<0.001; and 0.9 [0.21] vs. 0.69 [0.27], P<0.005, respectively). Contrast sensitivity at the nighttime without glare was significantly worse in the group 2 than the group 1 at the spatial frequencies of 3, 12, and 18 cycles per degree (P=0.001, P=0.05, and P=0.01, respectively). The patients in the group 2 had significantly worse contrast sensitivity at the nighttime and daytime with glare at the spatial frequencies of 1.5, 12, and 18 cycles per degree (P=0.054, P=0.04, and P=0.01 and P=0.011, P=0.031, and P=0.011, respectively). The greatest differences in contrast sensitivity were observed between the groups 4 and 5, and it was 2 to 4 times better in the group 4. Comparing these groups, all the differences at the nighttime and daytime with and without glare were significant. Contrast sensitivity was worst among the oldest persons (71-85 years), and it began to worsen already in the persons aged 40-49 years. Contrast sensitivity was very similar in the age groups of 40-49 and 50-59 years.

A novel method for blood vessel detection from retinal images

BackgroundThe morphological changes of the retinal blood vessels in retinal images are important indicators for diseases like diabetes, hypertension and glaucoma. Thus the accurate segmentation of blood vessel is of diagnostic value.MethodsIn this paper, we present a novel method to segment retinal blood vessels to overcome the variations in contrast of large and thin vessels. This method uses adaptive local thresholding to produce a binary image then extract large connected components as large vessels. The residual fragments in the binary image including some thin vessel segments (or pixels), are classified by Support Vector Machine (SVM). The tracking growth is applied to the thin vessel segments to form the whole vascular network.ResultsThe proposed algorithm is tested on DRIVE database, and the average sensitivity is over 77% while the average accuracy reaches 93.2%.ConclusionsIn this paper, we distinguish large vessels by adaptive local thresholding for their good contrast. Then identify some thin vessel segments with bad contrast by SVM, which can be lengthened by tracking. This proposed method can avoid heavy computation and manual intervention.