Explore chapters and articles related to this topic
An Introduction to Digital Image Analysis of Superconductors
Published in David A. Cardwell, David C. Larbalestier, Aleksander I. Braginski, Handbook of Superconductivity, 2022
Charlie Sanabria, Peter J. Lee
The qualitative information in an image (taken by a microscope, a telescope, or any image-capturing device) can now be easily transformed into quantitative digital data using widely available software—replacing earlier techniques such as planimetry and cut-and-weigha. There are many software packages available today. Many of these software are native to the microscope manufacturers with proprietary aspects (as well as financial costs), so for the purposes of this chapter we will use examples from one of the most widely used IA software: ImageJ, which is both multi-platform and open-source.
Decoding Common Machine Learning Methods
Published in Himansu Das, Jitendra Kumar Rout, Suresh Chandra Moharana, Nilanjan Dey, Applied Intelligent Decision Making in Machine Learning, 2020
Srinivasagan N. Subhashree, S. Sunoj, Oveis Hassanijalilian, C. Igathinathane
The overall processing stages for the decoded ML model development in this chapter are outlined (Figure 2.1) and subsequently described. The data required for this process were generated from the digital images acquired from the two different agricultural applications of identification and classification (soybean aphids and weed species). The actual input data for the ML models need to be in a structured format (with the same data type across features). We used ImageJ (Version 1.52r) for processing and extracting data (Rasband, 2019; Schindelin et al., 2012). ImageJ is an open source, java-based, and free image processing software that allows for the development of task-specific and user-coded applications in the form of plugins (Igathinathane et al., 2009). ImageJ also supports plugin development in several other languages (e.g., JavaScript, Python, Ruby, Clojure, Scala). The raw color images were preprocessed using ImageJ’s thresholding methods to obtain binary images (suitable for further processing) for feature extraction. ImageJ offers a several measurements (features) option from the binary image, such as the object area, major and minor axes length, width and height of bounding box, and Feret dimensions, to name a few. These basic measurements can be used to derive additional shape features to address the requirement of different applications (Igathinathane et al., 2008; Sunoj et al., 2017, 2018; Du and Sun, 2004).
Experimental investigation of dry joint surface and closure characteristics of interlocking blocks under compression
Published in Claudio Modena, F. da Porto, M.R. Valluzzi, Brick and Block Masonry, 2016
T. Zahra, Z. Yin, M. Dhanasekar
Although MBTSS could successfully determine the contact area and contact pressure distribution (including peak) of the dry stack masonry accurately, it is recognised that the technique is expensive. With a view to finding an alternate cheap method was trialled. Carbon paper was inserted in between the concrete half blocks having dimensions of 200 mm x 200 mm x 190 mm and full blocks of dimensions 390 mm x 200 mm x 190 mm. Test setup and a carbon paper imprint are shown in Figure 3. The specimens were loaded using INSTRON of load capacity 300 kN. The carbon paper image imprints were traced for loading increments of 20 kN from 0 kN to 100 kN. Each imprint was then analysed by ImageJ software to compute the surface contact area. ImageJ is a free Java based application developed for processing image analysis. It was first introduced by National Institutes of Health in the US (ImageJ, 2012). With scale being set in the digital image, the other information can be obtained by ImageJ's functions. The software was calibrated first by calculating the Australian mainland area taken from the Google maps; area with an error less than 2% was obtained. After calibration, two A4 sized paper were placed with two carbon papers in the middle of blocks to obtain the contact area of both the top and the bottom block. The imprint papers were digitised with the highest possible resolution. In ImageJ the scale of the image was defined and the contact area was output. The colour threshold was also adjusted in the
Economic parameter design for ultra-fast laser micro-drilling process
Published in International Journal of Production Research, 2019
Jianjun Wang, Yizhong Ma, Fugee Tsung, Gang Chang, Yiliu Tu
Two responses of interest, diameter () and roundness (), are selected as key quality characteristics to reflect geometrical property and machining precision of micro-holes in this paper. Roundness is related to the area and major axis of micro-holes. The formula for roundness in our study is defined as where and in Equation (13) can be obtained by analysing and measuring the pictures of micro-holes with the help of the image photo software IMAGEJ. IMAGEJ and its Java source code are freely available in the following website: http://imagej.nih.gov/ij/.
Using 3D anthropometric data for the modelling of customised head immobilisation masks
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2019
MAR Loja, E Sousa, L Vieira, DMS Costa, DS Craveiro, R Parafita, DC Costa
The usual method of three-dimensional reconstruction in OsiriX is rendering by volume from a three-dimensional dataset that comprises a piled group of flat two-dimensional images. These images are acquired in sequence, with a standardised distance between each and with a regular number of two-dimensional pixels. To create volume rendering, a camera is placed virtually relative to the space created and all voxels contain information on colour and transparency. Surface rendering can be accomplished using a number of different algorithms and consists of a process by which three-dimensional data are converted into vector models. These models are made up of vertices, lines and planes. The conversion is dependent on the algorithm chosen, on the structure to be converted and on the cut-off point chosen (Amato 2017). Also, ImageJ can be used for 3D reconstruction and rendering in the creation of 3D surfaces for medical images although ImageJ was developed with 2D processing and analysis in mind, thanks to plugins, it became a powerful software for 3D processing and analysis (Andrey and Boudier [date unknown]). SurfaceJ is a plugin to create surface plots. Surface plots are colour-coded 3D renderings of the intensity information in the image, where the height (on the z-axis) and the colour in the rendering correlate with the intensity of a pixel in the image (Abramoff and Viergever 2002).
Quantification of desiccation cracks using image analysis technique
Published in International Journal of Geotechnical Engineering, 2018
S. P. Singh, S. Rout, A. Tiwari
To capture the surface cracks and specimen shrinkage, a high resolution (72dpi) digital camera (Canon EOS 60D- pic size 18 MP) is installed on a platform at a fixed height of 50 cm from the specimen. Lakshmikantha et al. (2009), Oren et al. (2006) and Puppala et al. (2004) have adopted a similar technique for capturing images and analysis of desiccation cracks in soil. Black paper is placed on the base of the mould below the sample to avert the white light reflection. In this experimental work, plumb-bob is used to transfer the centre of the camera to the platform that holds specimens. This is adopted to ensure that the camera is vertical to the specimen surface. For this specific position of the camera and the specimen, the captured image is calibrated against a known value. The internal diameter of the mould is used as reference to calibrate the image. The overall set-up is shown in Fig. 2. The above specified camera is directly connected to personal computer (PC) through data cable in order to expedite the capturing of still photographs and subsequently software like ImageJ and Matlab programming tool is used for quantification of cracks. ImageJ is an open source image processing program designed for analysing of scientific multidimensional images. There is many more command operator on menu bar of ImageJ software which is called ImageJ function.