Grayscale Imagery Research Articles

Quantifying the spatial heterogeneity of topsoil microstructure in a horticultural cover cropping system from Southwestern Ontario, Canada

Cover crops (CC) are promoted to enhance soil structure and aggregation, but little is known about their impact on the spatial variability of soil microstructure. This study was conducted to assess the effects of medium-term (4-yr) annual CC systems, including oat (Avena sativa L.), winter cereal rye (rye; Secale cereale L.), oilseed radish (OSR; Raphanus sativus L. var. oleoferus Metzg. Stokes), as well as a mixture of OSR and winter cereal rye (OSR + Rye), against a control (no cover crop, no-CC), on topsoil microstructure utilizing 3D semivariance analysis, as influenced by soil depth (0–5 and 5–10 cm) in a tile-drained Orthic Humic Gleysol in Ridgetown, Ontario, Canada. Replicate undisturbed topsoil core samples were collected manually in plexiglass tubes from each plot. All soil cores were dried at 40 °C, then imaged at 20 μm pixel size using GE MS8-130× CT scanner (120kv, 0.5 mm Cu filter). The whole core greyscale imagery (representing radiodensity on the Hounsfield Scale) was subjected to a three-phase segmentation (solids, voids, and remaining soil matrix). For the whole soil and the soil matrix imagery, 16-bit histograms and 3D orthogonal semivariograms were generated. Directional anisotropy and four semivariogram parameters close to the origin, including the ratio between the values of the total variance and the semivariance at first lag (RVF), the ratio between semivariance values at second and first lag (RSF), first derivative near the origin (FDO), and second derivative at the third lag (SDT), were calculated to explain spatial variability in the soil microstructure. The results exhibited lower radiodensities for whole soil samples from the 0–5 cm than 5–10 cm layers. All CCs, other than oats, showed lower radiodensities than the control (no-CC). For both the whole soil and soil matrix, more variability was encountered in the vertical than the horizontal dimensions of all soils. Comparing the whole soil and the soil matrix in different CC systems and layers, more anisotropy was pronounced in the soil matrix than the whole soil imagery. The highest and the lowest anisotropy, calculated for the whole soil and soil matrix of different CC systems, were observed in oat and rye plots, respectively. There were no significant differences among CCs systems in terms of RVF, RSF, and SDT values, suggesting similarity of the structure at the scale slightly above image resolution. The results illustrated that soils under different CC systems showed only significant differences in the whole soil for FDO values (P ≤ 0.08). All four near-origin semivariogram parameters showed significant differences between 0 and 5 and 5–10 cm layers in both the whole soil and the soil matrix, suggesting more complexity in the microstructure of the uppermost soil layers.

Product Sorting System In Checker Sorting Process Using The Template Matching Method

In supporting the production activities of a company, an infrastructure unit is needed that is capable of supporting the production activities of a company. Several companies that produce animal feed and processed food have problems related to the failure of the sorting process. The sorting process for checking packaged products is still carried out by human power, so errors often occur due to human negligence in sorting packaged products. Therefore a tool is designed to sort automatically and be able to distinguish differences from packaged products using image processing with the Template Matching method. Then, proceed with looking for accurate calculations using the Template Matching algorithm, which will help detect differences between packaging products A and B. The technique used in the method is the calculation of values using greyscale imagery and image segmentation with ten trials based on the labels on the template features used. After testing, the best accuracy results, namely 59% obtained on image segmentation

K-Nearest Neighbor Algorithm to Identify Cucumber Maturity with Extraction of One-Order Statistical Features and Gray-Level Co-Occurrence

Determination of the maturity of cucumber fruit after harvest is subjective. The level of thoroughness of each individual’s cucumber selection is different. The maturity of cucumbers is seen from the age of the fruit, the resemblance of ripe cucumbers or old, raw or young is difficult to distinguish in terms of the texture of the fruit skin. The use of red, green, blue, and grayscale color modes from the cucumber imagery, is then processed using the extraction of the statistical features of the Order-One and Order-Two GLCM methods. Imagery using a 13 megapixels smartphone camera. Texture parameter values are used in the first order: mean, variance, skewness, kurtosis, entropy. Second order: energy, contrast, correlation, inverse different moments, angular second moments, variance 2, and entropy 2. The classification of the texture parameters of both order uses an algorithm from K-Nearest Neighbors as a comparison of test data values and training data. So that the system is made can identify the maturity of cucumbers old and young. The highest accuracy is found in grayscale imagery with a combination of two skewness and kurtosis parameters and euclidean distance calculation in K-Nearest Neighbor classification of 96.05%.

Grey Scale Image Multi-Thresholding Using Moth-Flame Algorithm and Tsallis Entropy

In the current era, image evaluations play a foremost role in a variety of domains, where the processing of digital images is essential to identify vital information. The image multi-thresholding is a vital image pre-processing field in which the available digital image is enhanced by grouping similar pixel values. Normally, the digital test images are available in RGB/greyscale format and the appropriate processing methodology is essential to treat the images with a chosen methodology. In the proposed approach, Tsallis Entropy (TE) supported multi-level thresholding is planned for the benchmark greyscale imagery of dimension 512x512x1 pixels using a chosen threshold values (T=2,3,4,5). This work suggests the possible Cost Value (CV) that can be considered during the optimization search and the proposed work is executed by considering the maximization of the TE as the CV. The entire thresholding task is executed using Moth-Flame Algorithm (MFA) and the accomplished results are validated based on the image quality measures of various thresholds. The attained result with MFO is better compared to the result of CS, BFO, PSO, and GA.

Semantic segmentation and colorization of grayscale aerial imagery with W‐Net models

AbstractThe semantic segmentation of remotely sensed aerial imagery is nowadays an extensively explored task, concerned with determining, for each pixel in an input image, the most likely class label from a finite set of possible labels. Most previous work in the area has addressed the analysis of high‐resolution modern images, although the semantic segmentation of historical grayscale aerial photos can also have important applications. Examples include supporting the development of historical road maps, or the development of dasymetric disaggregation approaches leveraging historical building footprints. Following recent work in the area related to the use of fully‐convolutional neural networks for semantic segmentation, and specifically envisioning the segmentation of grayscale aerial imagery, we evaluated the performance of an adapted version of the W‐Net architecture, which has achieved very good results on other types of image segmentation tasks. Our W‐Net model is trained to simultaneously segment images and reconstruct, or predict, the colour of the input images from intermediate representations. Through experiments with distinct data sets frequently used in previous studies, we show that the proposed W‐Net architecture is quite effective in colouring and segmenting the input images. The proposed approach outperforms a baseline corresponding to the U‐Net model for the segmentation of both coloured and grayscale imagery, and it also outperforms some of the other recently proposed approaches when considering coloured imagery.

Klasifikasi Kanker Kulit Berdasarkan Fitur Tekstur, Fitur Warna Citra Menggunakan SVM dan KNN

Skin cancer is one type of cancer that is quite serious that can not be controlled completely, so that many still result in death, disability and high medical costs. The diagnosis process carried out by dermatologists generally uses the Biopi process which is expensive, painful and requires a long recovery time for the wound, due to taking body tissue that scratches a small piece of tissue or by using a syringe to get a sample. Therefore we need a tool or system that can speed up helping to find out the type of skin cancer suffered, so that it can find out its treatment early by using digital image processing techniques. The purpose of this study is to classify the types of skin cancer based on texture and color image features using the SVM and KNN algorithm. The benefits are expected to help the skin medicine team in diagnosing skin cancer early. The features used are grayscale imagery taken by the average value, standard deviation, skewness, entropy, variance, contrast, energy, correlation, and homogeneity. Furthermore, the value of these features is trained and classified. The classification results using the SVM algorithm have an accuracy value of 69.85%. And accuracy using the KNN algorithm, with a value of K = 2 67.27%, K = 3 67.88%, K = 4 70.15%, K = 5 70.61%, K = 6 69.55%. Thus the best K on KNN is 5, the accuracy is 70.61%. Where the data used are 2637 training dataset images, and 660 test data images. And classified as a class of malignant, benign skin cancer.

Digital Image Processing for Detecting Industrial Machine Work Failure with Quantization Vector Learning Method

Todays, digital image processing is widely used in various fields to facilitate humans in doing work by analyzing videos or images for use in decision making in the industrial world. The use of industrial machine technology is one of the most important factors in efforts to facilitate human work, but an industrial machine is inseparable from work failure that can hinder the production process and cause harm to the industry. This study aims to detect a failure in industrial machinery by using video data of industrial machine movements recorded using a webcam camera. For the preprocessing stage, the image is resized then converted to grayscale imagery and segmented using the thresholding method, then morphological operations are performed with an opening operation, feature extraction is done by changing the binary image into a vector data that is used as input data in the classification process using the Learning Vector Quantization Neural Network Algorithm (LVQ NN) version 1. The results showed the results of the detection of machine working errors can be done well with an accuracy value of 94.24% in training and 92.38% in the testing phase.

On the Information Advantage of Sidescan Sonar Three-Frequency Colour over Greyscale Imagery

A prototype three-frequency (114, 256, and 410 kHz) colour sidescan sonar system, built by Kongsberg Underwater Mapping Ltd. (Great Yarmouth, UK), was previously described, and preliminary results presented, in Tamsett, McIlvenny, and Watts. The prototype system has subsequently been modified, and in 2017, new data were acquired in a resurvey of the Inner Sound of the Pentland Firth, North Scotland. An image texture characterisation and image classification exercise demonstrates considerably greater discrimination between different seabed classes in a three-frequency colour sonar image of the seabed, than in a multi-frequency colour image reduced to greyscale display, or in a single-frequency greyscale image, with readily twice the number of classes of seabed discriminated between, in the colour image. The information advantage of colour acoustic imagery over greyscale acoustic imagery is analogous to the information advantage of colour television images over black-and-white television images. A three-frequency colour sonar image contains a theoretical maximum of a factor of 3 times the information in a corresponding greyscale image, for independent seabed responses at the three frequencies. Estimates of the average information per pixel (information entropy) in the colour image, and in corresponding greyscale images, reveal an actual information advantage of colour sonar imagery over greyscale, to be in practice approximately a factor of 2.5, empirically confirming the greater information based utility of three-frequency colour sonar over greyscale sonar. Reference: Tamsett, D.; McIlvenny, J.; Watts, A. J. Mar. Sci. Eng. 2016, 4(26).

Characterization of soil aggregate structure by virtual erosion of X-ray CT imagery

The characterization of soil aggregates and structure has been tedious and intrusive in the past. A typical analysis of soil structure is done through bulk density, aggregate density or manual aggregate erosion. X-ray computed tomography (CT), is a non-invasive technique that can be used to understand the spatial configuration and nature of soil components, and how they are related to soil processes and behaviour. The objectives of this research were to evaluate the utility of virtual erosion/distance mapping, combined with analysis of the 3D semivariance of CT imagery, for quantifying the internal structure of soil aggregates and, specifically, to determine its applicability for comparing the impact of management practices on soil structure. Samples were collected from the long-term rotation experimental plots at the University of Guelph's Elora Research Station, in Elora, Ontario Canada. This research focused on Continuous Corn Mouldboard Plough (CCMP); Complex Rotation Mouldboard Plough (RotMP); Continuous Corn No-Till (CCNT); and Complex Rotation No-Till (RotNT). A total of 16 plots (four from each treatment) were utilized, for a total of 32 core samplings and 96 aggregates. An average histogram, mean radiodensity, distance mapping and semivariance analysis were run on the greyscale imagery. Aggregates from CC, regardless of tillage, had higher aggregate density and radiodensity overall, as well as at the centroid (the central layer determined from the distance mapping technique) and surface layers, coherent with reduced void space. Aggregates from both RotMP and RotNT had the lowest aggregate radiodensity, suggesting that crop rotation is a key factor in lowering bulk density/radiodensity. Distance mapping and aggregate peeling techniques were useful to distinguish differences in aggregate structure when considering soil management, as it enabled the quantification of aggregate layering and structural formation. Eroded aggregates were found to be more isotropic and homogeneous at the surface when compared to uneroded aggregates, showing the erosion technique allows for an analysis of the aggregates in a more in depth analytical way. The Balaguar parameters were also able to determine significant differences between the eroded and uneroded aggregates as well as between practices.

COLORIZING SENTINEL-1 SAR IMAGES USING A VARIATIONAL AUTOENCODER CONDITIONED ON SENTINEL-2 IMAGERY

Abstract. In this paper, we have shown an approach for the automatic colorization of SAR backscatter images, which are usually provided in the form of single-channel gray-scale imagery. Using a deep generative model proposed for the purpose of photograph colorization and a Lab-space-based SAR-optical image fusion formulation, we are able to predict artificial color SAR images, which disclose much more information to the human interpreter than the original SAR data. Future work will aim at further adaption of the employed procedure to our special case of multi-sensor remote sensing imagery. Furthermore, we will investigate if the low-level representations learned intrinsically by the deep network can be used for SAR image interpretation in an end-to-end manner.

Hatching for 3D prints: Line-based halftoning for dual extrusion fused deposition modeling

This work presents a halftoning technique to manufacture 3D objects with the appearance of continuous grayscale imagery for Fused Deposition Modeling (FDM) printers. While droplet-based dithering is a common halftoning technique, this is not applicable to FDM printing, since FDM builds up objects by extruding material in semi-continuous paths. The line-based halftoning principle called ‘hatching’ is applied to the line patterns naturally occurring in FDM prints, which are built up in a layer-by-layer fashion. The proposed halftoning technique is not limited by the challenges existing techniques face; existing FDM coloring techniques greatly influence the surface geometry and deteriorate with surface slopes deviating from vertical or greatly influence the basic parameters of the printing process and thereby the structural properties of the resulting product. Furthermore, the proposed technique has little effect on printing time. Experiments on a dual-nozzle FDM printer show promising results. Future work is required to calibrate the perceived tone.

Main Road Extraction from ZY-3 Grayscale Imagery Based on Directional Mathematical Morphology and VGI Prior Knowledge in Urban Areas.

Main road features extracted from remotely sensed imagery play an important role in many civilian and military applications, such as updating Geographic Information System (GIS) databases, urban structure analysis, spatial data matching and road navigation. Current methods for road feature extraction from high-resolution imagery are typically based on threshold value segmentation. It is difficult however, to completely separate road features from the background. We present a new method for extracting main roads from high-resolution grayscale imagery based on directional mathematical morphology and prior knowledge obtained from the Volunteered Geographic Information found in the OpenStreetMap. The two salient steps in this strategy are: (1) using directional mathematical morphology to enhance the contrast between roads and non-roads; (2) using OpenStreetMap roads as prior knowledge to segment the remotely sensed imagery. Experiments were conducted on two ZiYuan-3 images and one QuickBird high-resolution grayscale image to compare our proposed method to other commonly used techniques for road feature extraction. The results demonstrated the validity and better performance of the proposed method for urban main road feature extraction.

Robust super-resolution by fusion of interpolated frames for color and grayscale images

Multi-frame super-resolution (SR) processing seeks to overcome undersampling issues that can lead to undesirable aliasing artifacts. The key to effective multi-frame SR is accurate subpixel inter-frame registration. This accurate registration is challenging when the motion does not obey a simple global translational model and may include local motion. SR processing is further complicated when the camera uses a division-of-focal-plane (DoFP) sensor, such as the Bayer color filter array. Various aspects of these SR challenges have been previously investigated. Fast SR algorithms tend to have difficulty accommodating complex motion and DoFP sensors. Furthermore, methods that can tolerate these complexities tend to be iterative in nature and may not be amenable to real-time processing. In this paper, we present a new fast approach for performing SR in the presence of these challenging imaging conditions. We refer to the new approach as Fusion of Interpolated Frames (FIF) SR. The FIF SR method decouples the demosaicing, interpolation, and restoration steps to simplify the algorithm. Frames are first individually demosaiced and interpolated to the desired resolution. Next, FIF uses a novel weighted sum of the interpolated frames to fuse them into an improved resolution estimate. Finally, restoration is applied to deconvolve the modeled system PSF. The proposed FIF approach has a lower computational complexity than most iterative methods, making it a candidate for real-time implementation. We provide a detailed description of the FIF SR method and show experimental results using synthetic and real datasets in both constrained and complex imaging scenarios. The experiments include airborne grayscale imagery and Bayer color array images with affine background motion plus local motion.

Variation in Spectral and Mass Dimension on Three-Dimensional Soil Image Processing

A quantitative characterization of the three-dimensional soil pore architecture is important for understanding soil processes as it relates to the control of biological, chemical, and physical processes across scales. Recent advances in nondestructive imaging, such as X-ray computed tomography (CT), provide an opportunity to analyze pore space features from direct visualization of soil structure. At the same time that these techniques provide new opportunities, they also introduce new processing steps on which the final results depend. Fractal formalism has been shown to be a useful tool in cases where highly complex and heterogeneous media are studied. One of these quantifications is mass dimension (Dm) and spectral dimension (d) applied for water and gas diffusion in soil. In this work, intact soil samples were collected from four horizons of a Brazilian soil, and three-dimensional images, of 45.1-μm resolution (256 × 256 × 256 voxels), were obtained. Four different threshold criteria were used to transform CT grayscale imagery in binary imagery (pore/solid), based on the frequency of CT units. We calculated the sensitivity of a geometrical parameter (the mass fractal dimension, Dm), a topological parameter (the spectral dimension, d), and the ratio of the two (Dm), which relates to the scaling property of dynamic processes in soil such as diffusion. Each threshold criterion had a direct influence on the measured porosity and on the value of Dm, showing a clear logarithmic increase in Dm with porosity. Meanwhile, d increased faster, that is, linearly with measured porosity. In all cases, the detailed dependence on porosity was different for each horizon. In contrast, the ratio for each horizon was less sensitive to the thresholding criteria applied to the image. Thus, the results based on our soil samples suggest that thresholding has a strong influence on parameters that relate to geometrical and topological properties of structure but may have a less important impact on parameters relevant to dynamic processes such as diffusion.

Imaging-based detection of AAR induced map-crack damage in concrete structure

Imaging-based inspection methods are increasingly being employed for crack detection in concrete structures, because they provide quantitative information compared to inspections based solely on conventional visual approaches. However, efficient image analysis methods are needed. This study proposes the application of the grey level co-occurrence matrix (GLCM) texture analysis approach and an artificial neural network (ANN) classifier to obtain surface damage information, such as the total amount of superficial cracking, as well as the total length, and range of crack widths. These methods were applied to thermographic, visual colour and greyscale images of concrete blocks from CANMET that were exposed outdoors for ten years, as well as slabs from GRAI that were kept indoors, all specimens exhibiting various levels of alkali-aggregate reaction (AAR) damage. Results of the classifications show that the greyscale imagery performed fairly well, with an overall classification accuracy range of 72.3–76.5% for the CANMET blocks, and 68.7–75.3% for the GRAI slabs. Classifications using the colour imagery were slightly better than the greyscale imagery, with accuracies ranging from 71.4% to 75.2% for CANMET blocks and 70.9–72.0% for the GRAI slabs. The thermographic imagery, however, produced the highest overall classification accuracies, which range from 73.1% to 76.3% for the CANMET blocks and 74.2–76.9% for the GRAI slabs. The results show that all three types of imagery are relatively effective in characterizing and quantifying crack damage; however, the infrared thermography produced more accurate results compared to the visual colour, and greyscale images.

The Tradeoff of Frame Rate and Resolution in a Route Clearing Task: Implications for Human-Robot Interaction

The implications of bandwidth allocation are described for teleoperation in a military task that involved navigation, target detection, and target identification. Color versus grayscale imagery was manipulated. Participants themselves traded off resolution and frame rate settings. Participants minimized switching between resolution/frame rate settings and tended to use settings with high resolution/low frame rate. Courses completed with the highest resolution (and lowest frame rate) had the fastest target identification times, but no other differences were observed between settings. Color imagery offered advantages for overall course time and the time to identify a tank as friendly or enemy.

The Tradeoff of Frame Rate and Resolution in a Route Clearing Task: Implications for Human-Robot Interaction

The implications of bandwidth allocation are described for teleoperation in a military task that involved navigation, target detection, and target identification. Color versus grayscale imagery was manipulated. Participants themselves traded off resolution and frame rate settings. Participants minimized switching between resolution/frame rate settings and tended to use settings with high resolution/low frame rate. Courses completed with the highest resolution (and lowest frame rate) had the fastest target identification times, but no other differences were observed between settings. Color imagery offered advantages for overall course time and the time to identify a tank as friendly or enemy.

Pore network complexity and thresholding of 3D soil images

Informative geometric parameters are needed to describe the complex spatial arrangement of pore systems in porous media. Three-dimensional images (45.1 μm resolution) of soil samples exhibiting different spatial arrangements and porosities were analyzed to calculate their generalized dimensions ( D q ) in the multifractal framework. Four different threshold criteria were used to transform the CT grey-scale imagery in the binary imagery of pore space and solid phase to study the influence of this choice in D q values. Thresholds were based on the histograms of the CT units representing voxels. The selection of the threshold affected the value of the apparent porosity inferred from the CT images. The pore space structure could be described by the multifractal model only for the larger cubes sizes (side lengths ranging from 32 to 256 voxel sides) regardless of the thereshold criteria. Values of D q were obtained by restricting multifractal analysis (MFA) to these cube sizes. The difference w between the D q values for q = −1 to q = 5 was also dependent on the threshold criterion selection, and was used to compare the effect of the threshold criteria selection on the multiscaling behavior. The w values decreased exponentially as the apparent porosity increased. For the same threshold, the largest values of w , indicating the most developed multifractal structure, were found in the surface horizon where interactions with atmosphere and root activity were the most pronounced, and in the relatively deep illuvial horizons where the colloidal material was accumulated that was leached from the upper soil horizons. The strong influence of the image threshold on the parameters of the multifractal models suggests that structure of the grey image along with the frequency distribution of grey level may be a useful indicator for the threshold selection.

Influence of thresholding in mass and entropy dimension of 3-D soil images

Abstract. With the advent of modern non-destructive tomography techniques, there have been many attempts to analyze 3-D pore space features mainly concentrating on soil structure. This analysis opens a challenging opportunity to develop techniques for quantifying and describe pore space properties, one of them being fractal analysis. Undisturbed soil samples were collected from four horizons of Brazilian soil and 3-D images at 45 μm resolution. Four different threshold criteria were used to transform computed tomography (CT) grey-scale imagery into binary imagery (pore/solid) to estimate their mass fractal dimension (Dm) and entropy dimension (D1). Each threshold criteria had a direct influence on the porosity obtained, varying from 8 to 24% in one of the samples, and on the fractal dimensions. Linear scaling was observed over all the cube sizes, however depending on the range of cube sizes used in the analysis, Dm could vary from 3.00 to 2.20, realizing that the threshold influenced mainly the scaling in the smallest cubes (length of size from 1 to 16 voxels). Dm and D1 showed a logarithmic relation with the apparent porosity in the image, however, the increase of both values respect to porosity defined a characteristic feature for each horizon that can be related to soil texture and depth.

46.4: Ghosting Reduction Using Digital Halftoning for Electrophoretic Displays

AbstractGhosting on electrophoretic displays is an image artifact where previously displayed image content is visible in the current image. This paper introduces use of the previous image in a digital halftoning method to dither ghosting errors from grayscale imagery. Experiments show this method eliminates ghosting artifacts providing quality images without hardware modification.