Search

Technologies currently used for cotton contaminant assessment suffer from some fundamental limitations. These limitations result in the misassessment of the cotton quality, and have a serious impact on its economic value. Through our research, we have shown that X-ray microtomographic image analysis may be applied with a high degree of success to noninvasive evaluation of cotton for the recognition of contaminants. We believe that this procedure, when realized in real time, will have a serious impact on the cotton cleaning process, and indeed on the economic value of cotton. Index Terms--Cotton trash, fuzzy classifier, image analysis, pattern classification, volumetric data, X-ray tomography.

Identification of cell death mechanisms, particularly distinguishing between apoptotic versus nonapoptotic pathways, is of paramount importance for a wide range of applications related to cell signaling, interaction with pathogens, therapeutic processes, drug discovery, drug resistance, and even pathogenesis of diseases like cancers and neurogenerative disease among others. Here, we present a novel high‐throughput method of identifying apoptotic versus necrotic versus other nonapoptotic cell death processes, based on lensless digital holography. This method relies on identification of the temporal changes in the morphological features of mammalian cells, which are unique to each cell death processes. Different cell death processes were induced by known cytotoxic agents. A deep learning‐based approach was used to automatically classify the cell death mechanism (apoptotic vs necrotic vs nonapoptotic) with more than 93% accuracy. This label free approach can provide a low cost (<$250) alternative to some of the currently available high content imaging‐based screening tools. [ABSTRACT FROM AUTHOR]

A unifying approach to the derivation and implementation of a shift-invariant wavelet transform of one- and two-dimensional discrete signals is presented. An analytical process generates a shift-invariant orthogonal, discrete wavelet transform called the multiscale wavelet representation (MSWAR). The derived MSWAR is invertible which makes it particularly useful in image registration and fusion and object recognition. Its implementation is equivalent to filter upsampling technique while its computational complexity is quantified in terms of required convolution.

Node‐by‐node boll mapping has been used to determine the effects of several environmental and management strategies, including irrigation rate and cultivar, on cotton (Gossypium hirsutum L.) boll distribution. The advent of consumer 3D digital imaging may make rapid node‐by‐node mapping of greater acreage possible in the future. Effects of irrigation rate and cultivar on boll distribution were determined from line plots of node‐specific boll distribution and boll accumulation estimate data and from vertical box and whisker plots of boll fraction using data collected by a 3D sensor system to rapidly detect open bolls before harvest over three seasons. Differences were observed between the dryland (2018 only), low irrigation, and high irrigation rates in terms of boll fraction and boll accumulation for each cultivar. The low irrigation tended to produce bolls more toward the bottom of the plant, while the high irrigation produced bolls towards the top of the plant. Yield correlation between sensor obtained and manually counted measurements was strong, with r2 values as high as 0.87. Results obtained indicated that differences among irrigation rate and cultivar were identifiable using the sensor system during the 3 yr research study. Similar systems may allow rapid, broad‐scale identification of boll distribution and yield in breeding and physiology research in the future, leading to improved identification of elite cultivars and improved management practices in cotton. [ABSTRACT FROM AUTHOR]

Three-dimensional (3-D) high-throughput crop phenotyping may benefit plant research and breeding programs by providing a rapid, nondestructive method of determining in-season crop growth and development. In this study, a set of three inexpensive, structured, near-infrared laser projectors mounted on a robotic platform were used to generate high-density color point clouds (PCs) in cotton (Gossypium hirsutum L.) in 2016 and 2017. The PCs were calibrated based on destructive leaf area measurements, and the transformed PCs were analyzed to quantify leaf area by canopy height in 1-cm intervals. We conducted weekly scans of 8-m plots throughout the growing season for two cotton cultivars and two irrigation treatments during the 2 yr. The calibrated PCs were used to accurately measure leaf area index and leaf area index by canopy height. The analysis of leaf area distribution throughout the growing season indicated significant cultivar and irrigation effects by canopy height as well as significant interactions between cultivar and irrigation. Based on the results, it is possible to use a 3-D sensor system to distinguish growth habits that are not easily measured using traditional growth measurements. The information obtained from 3-D measurements may provide additional information about several canopy characteristics that are currently difficult to measure, including radiation capture parameters and biomass partitioning. [ABSTRACT FROM AUTHOR]

This paper describes a vision-based fabric inspection system that accomplishes on-loom inspection of the fabric under construction with 100% coverage. The inspection system, which offers a scalable open architecture, can be manufactured at relatively low cost using off-the-shelf components. While synchronized to the motion of the loom, the developed system first acquires very high-quality vibration-free images of the fabric using either front or backlighting. Then, the acquired images are subjected to a novel defect segmentation algorithm, which is based on the concepts of wavelet transform, image fusion, and the correlation dimension. The essence of this segmentation algorithm is the localization of those events (i.e., defects) in the input images that disrupt the global homogeneity of the background texture. The efficacy of this algorithm, as well as the overall inspection system, has been tested thoroughly under realistic conditions. The system was used to acquire and to analyze more than 3700 images of fabrics that were constructed with two different types of yarn. In each case, the performance of the system was evaluated as an operator introduced defects from 26 categories into the weaving process. The overall detection rate of the presented approach was found to be 89% with a localization accuracy of 0.2 in (i.e., the minimum defect size) and a false alarm rate of 2.5%. Index Terms--Computer vision, defect detection, fabric inspection, wavelet transform.

This paper presents a novel transfer learning regression method that utilizes data from an older instrument to train a new instrument to assess the same measurement. The method assumes that the instruments measure the same property but by different methodologies, and that samples presented to one apparatus are not available to the other. The algorithm makes use of a single feature common to both instruments to create a link with which to transfer information regarding the distribution of the resulting measurements, or labels. The goal is to generate a model in the domain of the new instrument that maps data from analyzed samples to an output measurement. This modeling process is accomplished through an iterative algorithm that supports many types of regression schemes. Results are shown using both synthetic and real world data sets, which demonstrate the effectiveness of the proposed method. Finally, we present how this technique is used to train a new instrument designed to measure cotton fiber maturity. [ABSTRACT FROM PUBLISHER]

Moisture transport properties of fabrics are of key interest within the textile industry. This paper introduces a new method to measure horizontal wicking and drying properties of a fabric using a thermal imaging machine vision system. By tracking the area of the wet region of a fabric specimen over time, five new features are measured that characterize key periods of the wicking and drying process. Experimental results show significant differences in these measurements for fabrics that have been treated with a proprietary formula known to improve wicking properties of fabrics. Furthermore, analysis shows that the repeatability of this new method shows marked improvement over current industry standards. [ABSTRACT FROM PUBLISHER]

The article discusses the use of confocal microscopy and image analysis to measure the maturity of individual cotton fibers. Topics include the use of the level set method to process virtual fiber cross-sections extracted from microscopic images of the cotton fibers, the segmentation of the cross-section volumes, and the comparison of mature cotton fibers to a set of 104 reference cottons, measured according to American Association of Textile Chemists and Colorists (AATCC) standards.

We introduce a novel Maximum Entropy (MaxEnt) framework that can generate 3D scenes by incorporating objects' relevancy, hierarchical and contextual constraints in a unified model. This model is formulated by a Gibbs distribution, under the MaxEnt framework, that can be sampled to generate plausible scenes. Unlike existing approaches, which represent a given scene by a single And-Or graph, the relevancy constraint (defined as the frequency with which a given object exists in the training data) require our approach to sample from multiple And-Or graphs, allowing variability in terms of objects' existence across synthesized scenes. Once an And-Or graph is sampled from the ensemble, the hierarchical constraints are employed to sample the Or-nodes (style variations) and the contextual constraints are subsequently used to enforce the corresponding relations that must be satisfied by the And-nodes. To illustrate the proposed methodology, we use desk scenes that are composed of objects whose existence, styles and arrangements (position and orientation) can vary from one scene to the next. The relevancy, hierarchical and contextual constraints are extracted from a set of training scenes and utilized to generate plausible synthetic scenes that in turn satisfy these constraints. After applying the proposed framework, scenes that are plausible representations of the training examples are automatically generated. [ABSTRACT FROM AUTHOR]

Dimensional changes and soil release are important functional attributes of fabrics that impact their pricing in the marketplace. This paper presents the underlying principles of a machine vision system that creates a framework for making both measurements in a simultaneous and automatic fashion from digitized fabric images. In addition, the proposed approach is equipped to operate on solid color, as well as printed/patterned fabrics. This system, using image analysis, can (i) measure dimensional changes, which include shrinkage and skew, and (ii) localize stains on the fabric image, which can then be evaluated for soil release. Robust extraction of the above measurements on printed fabric images are made possible using a sequence of customized image registration and background-subtraction techniques. The system was validated using a set of 623 fabric images that involved the detection of 1868 shrinkage dots which were used to make 934 shrinkage measurements, 467 skew measurements, and detect 240 potential stains. The system produced excellent results with a successful shrinkage dot detection rate of 98.9% and an average stain segmentation accuracy of 0.87 using the dice metric. [ABSTRACT FROM PUBLISHER]

Soil release is an important attribute of fabrics that impacts their pricing on the marketplace. Currently, stain release is evaluated manually and hence its assessment tends to be subjective. This paper introduces a novel approach based on image analysis for objective evaluation of stain release in fabrics. This system has the capability to accurately detect, localize and grade stains with minimal human intervention. The grades assigned by the system are based on a digitized version of the AATCC soil release replica. The stain detection performance of the system was validated on a large dataset of 360 stain images. The system produced excellent results with a sensitivity (true positive rate) of around 93 percent and specificity (1 — false positive rate) of around 95 percent. Further, a correlation study and analysis of variance were performed using the system assigned grades and the technician assigned grades, and these initial results are very promising. [ABSTRACT FROM AUTHOR]

In this research, we validate an imaging system for automatic grading of fabric smoothness, developed at Texas Tech University. This system consists of a sheet-of-light, laser-line projector; a smart CMOS camera; a moving platform; and a PC. Its purpose is to provide the textile industry with a tool for rapid, objective evaluation of fabric smoothness after home laundering. The validation study involves two cotton fabrics treated with increasing amounts of a textile-finishing agent to impart durable press properties. The UATR-FTIR is used as a rapid and nondestructive technique to determine the amount of the crosslinking agent linked to the cellulose after the required laundering cycles. To demonstrate the potential of our newly developed imaging system, we extract five features from the acquired images and relate them to AATCC grading and to the amount of finish as evaluated by FTIR. Our results demonstrate that this new wrinkle measurement technology has the potential to discriminate between different levels of fabric treatments and different fabrics. [ABSTRACT FROM AUTHOR]

This paper presents a detailed description of a vision system that detects and localizes the nonuniformities that appear on the paper slurry (wood fiber and water mixture) at the wet end of a paper machine. Specifically, the system monitors the paper slurry as it exits the headbox and alerts the operators of any event (e.g., streaks) that disrupts the otherwise homogeneous background. These events affect crucial product properties such as formation. A poor formation results in thick and thin spots on the sheet and impacts its strength and printability. This paper describes the vision system in terms of its hardware modules, as well as the image processing algorithms that it utilizes to perform its function. The system acquires intensity and topographic information from the scene. It uses texture-based features for the detection and facet-based descriptors for the localization of the nonuniformities. In addition to being tested in a laboratory environment, a prototype of this system was constructed and deployed to a paper mill, where its performance was evaluated under realistic conditions. Installed on a fourdrinier paper machine, running at 480 m/min and producing linerboard material, the vision system monitored about a 1 m wide area and successfully detected and localized slurry streaks. Published 2001 John Wiley & Sons, Inc. Int J Imaging Syst Technol, 11, 231–242, 2000 [ABSTRACT FROM AUTHOR]

We present a machine vision system for simultaneous and objective evaluation of two important functional attributes of a fabric, namely, soil release and shrinkage. Soil release corresponds to the efficacy of the fabric in releasing stains after laundering and shrinkage essentially quantifies the dimensional changes in the fabric postlaundering. Within the framework of the proposed machine vision scheme, the samples are prepared using a prescribed procedure and subsequently digitized using a commercially available off-the-shelf scanner. Shrinkage measurements in the lengthwise and widthwise directions are obtained by detecting and measuring the distance between two pairs of appropriately placed markers. In addition, these shrinkage markers help in producing estimates of the location of the center of the stain on the fabric image. Using this information, a customized adaptive statistical snake is initialized, which evolves based on region statistics to segment the stain. Once the stain is localized, appropriate measurements can be extracted from the stain and the background image that can help in objectively quantifying stain release. In addition, the statistical snakes algorithm has been parallelized on a graphical processing unit, which allows for rapid evolution of multiple snakes. This, in turn, translates to the fact that multiple stains can be detected and segmented in a computationally efficient fashion. Finally, the aforementioned scheme is validated on a sizeable set of fabric images and the promising nature of the results help in establishing the efficacy of the proposed approach. [ABSTRACT FROM AUTHOR]