Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

A Novel Active Imaging Model to Design Visual Systems: A Case of Inspection System for Specular Surfaces.

ABSTRACT: The use of visual information is a very well known input from different kinds of sensors. However, most of the perception problems are individually modeled and tackled. It is necessary to provide a general imaging model that allows us to parametrize different input systems as well as their problems and possible solutions. In this paper, we present an active vision model considering the imaging system as a whole (including camera, lighting system, object to be perceived) in order to propose solutions to automated visual systems that present problems that we perceive. As a concrete case study, we instantiate the model in a real application and still challenging problem: automated visual inspection. It is one of the most used quality control systems to detect defects on manufactured objects. However, it presents problems for specular products. We model these perception problems taking into account environmental conditions and camera parameters that allow a system to properly perceive the specific object characteristics to determine defects on surfaces. The validation of the model has been carried out using simulations providing an efficient way to perform a large set of tests (different environment conditions and camera parameters) as a previous step of experimentation in real manufacturing environments, which more complex in terms of instrumentation and more expensive. Results prove the success of the model application adjusting scale, viewpoint and lighting conditions to detect structural and color defects on specular surfaces.

SUBMITTER: Azorin-Lopez J

PROVIDER: S-EPMC5539729 | biostudies-other | 2017 Jun

REPOSITORIES: biostudies-other

ACCESS DATA

Json Xml

Similar Datasets

Optimized multi-shot imaging inspection design.

Project description:The inspection of complex-shaped components, such as those enabled by additive manufacturing, is a major challenge in industrial quality assurance. A frequently adopted approach to volumetric non-destructive evaluation is X-ray computed tomography, but this has major drawbacks. Two-dimensional radiography can overcome some of these problems, but does not generally provide an inspection that is as capable. Moreover, designing a detailed inspection for a complex-shaped component is a labour-intensive task, requiring significant expert input. In response, a computational framework for optimizing the data acquisition for an image-based inspection modality has been devised. The initial objective is to advance the capabilities of radiography, but the algorithm is, in principle, also applicable to alternative types of imaging. The algorithm exploits available prior information about the inspection and simulations of the inspection modality to allow the determination of the optimal inspection configuration, including specifically component poses with respect to the imaging system. As an intermediate output, spatial maps of inspection performance are computed, for understanding spatially varying limits of detection. Key areas of innovation concern the defect detectability evaluation for arbitrarily complex indications and the creation of an application-specific optimization algorithm. Initial trials of the algorithm are presented, with good results.

| S-EPMC6127396 | biostudies-literature

Machine learning to analyze single-case graphs: A comparison to visual inspection.

Project description:Behavior analysts commonly use visual inspection to analyze single-case graphs, but studies on its reliability have produced mixed results. To examine this issue, we compared the Type I error rate and power of visual inspection with a novel approach-machine learning. Five expert visual raters analyzed 1,024 simulated AB graphs, which differed on number of points per phase, autocorrelation, trend, variability, and effect size. The ratings were compared to those obtained by the conservative dual-criteria method and two models derived from machine learning. On average, visual raters agreed with each other on only 75% of graphs. In contrast, both models derived from machine learning showed the best balance between Type I error rate and power while producing more consistent results across different graph characteristics. The results suggest that machine learning may support researchers and practitioners in making fewer errors when analyzing single-case graphs, but replications remain necessary.

| S-EPMC8596748 | biostudies-literature

Active confocal imaging for visual prostheses.

Project description:There are encouraging advances in prosthetic vision for the blind, including retinal and cortical implants, and other "sensory substitution devices" that use tactile or electrical stimulation. However, they all have low resolution, limited visual field, and can display only few gray levels (limited dynamic range), severely restricting their utility. To overcome these limitations, image processing or the imaging system could emphasize objects of interest and suppress the background clutter. We propose an active confocal imaging system based on light-field technology that will enable a blind user of any visual prosthesis to efficiently scan, focus on, and "see" only an object of interest while suppressing interference from background clutter. The system captures three-dimensional scene information using a light-field sensor and displays only an in-focused plane with objects in it. After capturing a confocal image, a de-cluttering process removes the clutter based on blur difference. In preliminary experiments we verified the positive impact of confocal-based background clutter removal on recognition of objects in low resolution and limited dynamic range simulated phosphene images. Using a custom-made multiple-camera system based on light-field imaging, we confirmed that the concept of a confocal de-cluttered image can be realized effectively.

| S-EPMC4417666 | biostudies-literature

Human visual cortical responses to specular and matte motion flows.

Project description:Determining the compositional properties of surfaces in the environment is an important visual capacity. One such property is specular reflectance, which encompasses the range from matte to shiny surfaces. Visual estimation of specular reflectance can be informed by characteristic motion profiles; a surface with a specular reflectance that is difficult to determine while static can be confidently disambiguated when set in motion. Here, we used fMRI to trace the sensitivity of human visual cortex to such motion cues, both with and without photometric cues to specular reflectance. Participants viewed rotating blob-like objects that were rendered as images (photometric) or dots (kinematic) with either matte-consistent or shiny-consistent specular reflectance profiles. We were unable to identify any areas in low and mid-level human visual cortex that responded preferentially to surface specular reflectance from motion. However, univariate and multivariate analyses identified several visual areas; V1, V2, V3, V3A/B, and hMT+, capable of differentiating shiny from matte surface flows. These results indicate that the machinery for extracting kinematic cues is present in human visual cortex, but the areas involved in integrating such information with the photometric cues necessary for surface specular reflectance remain unclear.

| S-EPMC4612507 | biostudies-literature

Automated design of freeform imaging systems.

Project description:The automated design of imaging systems involving no or minimal human effort has always been the expectation of scientists, researchers and optical engineers. In addition, it is challenging to choose an appropriate starting point for an optical system design. In this paper, we present a novel design framework based on a point-by-point design process that can automatically obtain high-performance freeform systems. This framework only requires a combination of planes as the input based on the configuration requirements or the prior knowledge of designers. This point-by-point design framework is different from the decades-long tradition of optimizing surface coefficients. Compared with the traditional design method, whereby the selection of the starting point and the optimization process are independent of each other and require extensive amount of human effort, there are no obvious differences between these two processes in our design framework, and the entire design process is mostly automated. This automated design process significantly reduces the amount of human effort required and does not rely on advanced design skills and experience. To demonstrate the feasibility of the proposed design framework, we successfully designed two high-performance systems as examples. This point-by-point design framework opens up new possibilities for automated optical design and can be used to develop automated optical design in the areas of remote sensing, telescopy, microscopy, spectroscopy, virtual reality and augmented reality.

| S-EPMC6061905 | biostudies-other

The root of anomalously specular reflections from solid surfaces on Saturn's moon Titan.

Project description:Saturn's moon Titan has a methane cycle with clouds, rain, rivers, lakes, and seas; it is the only world known to presently have a volatile cycle akin to Earth's tropospheric water cycle. Anomalously specular radar reflections (ASRR) from Titan's tropical region were observed with the Arecibo Observatory (AO) and Green Bank Telescope (GBT) and interpreted as evidence for liquid surfaces. The Cassini spacecraft discovered lakes/seas on Titan, however, it did not observe lakes/seas at the AO/GBT anomalously specular locations. A satisfactory explanation for the ASRR has been elusive for more than a decade. Here we show that the ASRR originate from one terrain unit, likely paleolakes/paleoseas. Titan observations provide ground-truth in the search for oceans on exoearths and an important lesson is that identifying liquid surfaces by specular reflections requires a stringent definition of specular; we propose a definition for this purpose.

| S-EPMC7298017 | biostudies-literature

Specular Microscopy of Human Corneas Stored in an Active Storage Machine.

Project description:PurposeUnlike corneas stored in cold storage (CS) which remain transparent and thin, corneas stored in organoculture (OC) cannot be assessed by specular microscopy (SM), because edema and posterior folds occur during storage and prevent from specular reflection. We previously developed an active storage machine (ASM) which restores the intraocular pressure while renewing the storage medium, thus preventing major stromal edema. Its transparent windows allow multimodal corneal imaging in a closed system.Aimto present SM of corneas stored in this ASM.MethodsAncillary study of two preclinical studies on corneas stored for one and three months in the ASM. A prototype non-contact SM was developed (CMOS camera, ×10 objective, collimated LED source, micrometric stage). Five non-overlapping fields (935 × 748 μm) were acquired in exactly the same areas at regular intervals. Image quality was graded according to defined categories (American Cornea Donor Study). The endothelial cell density (ECD) was measured with a center method. Finally, SMECD was also compared to Hoechst-stained cell nuclei count (HoechstECD).ResultsThe 62 corneas remained thin during storage, allowing SM at all time points without corneal deconditioning. Image quality varied depending on donors and days of control but, overall, in the 1100 images, we observed 55% of excellent and 30% of good quality images. SMECD did not differ from HoechstECD (p = 0.084).ConclusionsThe ASM combines the advantages of CS (closed system) and OC (long-term storage). Specular microscopy is possible at any time in the ASM with a large field of view, making endothelial controls easy and safe.

| S-EPMC9181187 | biostudies-literature

Projections as visual aids for classification system design.

Project description:Dimensionality reduction is a compelling alternative for high-dimensional data visualization. This method provides insight into high-dimensional feature spaces by mapping relationships between observations (high-dimensional vectors) to low (two or three) dimensional spaces. These low-dimensional representations support tasks such as outlier and group detection based on direct visualization. Supervised learning, a subfield of machine learning, is also concerned with observations. A key task in supervised learning consists of assigning class labels to observations based on generalization from previous experience. Effective development of such classification systems depends on many choices, including features descriptors, learning algorithms, and hyperparameters. These choices are not trivial, and there is no simple recipe to improve classification systems that perform poorly. In this context, we first propose the use of visual representations based on dimensionality reduction (projections) for predictive feedback on classification efficacy. Second, we propose a projection-based visual analytics methodology, and supportive tooling, that can be used to improve classification systems through feature selection. We evaluate our proposal through experiments involving four datasets and three representative learning algorithms.

| S-EPMC6131729 | biostudies-other

Raptor: A Design of a Drain Inspection Robot.

Project description:Frequent inspections are essential for drains to maintain proper function to ensure public health and safety. Robots have been developed to aid the drain inspection process. However, existing robots designed for drain inspection require improvements in their design and autonomy. This paper proposes a novel design of a drain inspection robot named Raptor. The robot has been designed with a manually reconfigurable wheel axle mechanism, which allows the change of ground clearance height. Design aspects of the robot, such as mechanical design, control architecture and autonomy functions, are comprehensively described in the paper, and insights are included. Maintaining the robot's position in the middle of a drain when moving along the drain is essential for the inspection process. Thus, a fuzzy logic controller has been introduced to the robot to cater to this demand. Experiments have been conducted by deploying a prototype of the design to drain environments considering a set of diverse test scenarios. Experiment results show that the proposed controller effectively maintains the robot in the middle of a drain while moving along the drain. Therefore, the proposed robot design and the controller would be helpful in improving the productivity of robot-aided inspection of drains.

| S-EPMC8434159 | biostudies-literature

Pressure vessel-oriented visual inspection method based on deep learning.

Project description:The detection of surface parameters of pressure vessel welds guarantees safe operation. To address the problems of low efficiency and poor accuracy of traditional manual inspection methods, a method for welding morphological parameters combined with vision and structured light is proposed in this study. First, a feature point extraction algorithm for weld parameters based on deep convolution was proposed. An accurate extraction method of weld image feature point coordinates was designed based on the combination of the loss function via seam undercut feature recognition and weld feature point extraction network structure. Second, a training data enhancement method based on the third-order non-uniform rational B-spline (NURBS) curve was proposed to reduce the amount of data collection for training. Finally, a pressure vessel measurement device was designed, and the feature point extraction performance of the deep network and common feature point extraction networks, DeepLabCut and HR-net, proposed in this study were compared to analyze the theoretical accuracy of the surface parameter measurement. The results indicated that the theoretical accuracy of the parameter measurements was within 0.065 mm.

| S-EPMC9060373 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data