China
Africa
Explore chapters and articles related to this topic
Computer-aided Diagnosis (CAD) System for Determining Histological Grading of Astrocytoma Based on Ki67 Counting
Published in Varun Bajaj, G.R. Sinha, Computer-aided Design and Diagnosis Methods for Biomedical Applications, 2021
Fahmi Akmal Dzulkifli, Maryam Ahmad Sharifuddin, Mohd Yusoff Mashor, Hasnan Jaafar
The enhanced images were compared with the original images for assessing the performance and accuracy of the system in improving the quality of original images. All enhanced images were saved in the (*.jpg) format. Figure 11.4 shows an example of a comparison between the original image and output image after applying an image enhancement technique. Figure 11.4 also provides a comparison of RGB histograms between the original image and the output image. An image histogram refers to a bar graph that represents the frequency of the intensity values that occur in an image. Each bar indicates one intensity level. The horizontal axis refers to the intensities of the image, which can be a color or grayscale intensities. The vertical axis explains the frequency of the intensity values.
The Role(s) of Computers
Published in F. Brent Neal, John C. Russ, Measuring Shape, 2017
In order to measure objects to determine size, shape, position, or brightness, or even simply to count them, it is necessary to isolate them from their surroundings. The most common way to accomplish this is by thresholding—selecting a range of brightness or color values that represent the objects and clearing all of the other pixels to some background color, usually white but sometimes black or transparent. The pixels corresponding to the objects may either be set to a contrasting color or left unchanged. When the thresholded image consists of just two possible pixel values, such as black for objects and white for background, it is called a binary image. The thresholding operation may be performed manually or using automatic algorithms based on the image histogram. Some methods also take into account the values of neighboring pixels or use independent knowledge such as the permissible size range of objects.
Automated Lung Cancer Detection From PET/CT Images Using Texture and Fractal Descriptors
Published in Ayman El-Baz, Jasjit S. Suri, Lung Imaging and CADx, 2019
K. Punithavathy, Sumathi Poobal, M. M. Ramya
HE methods enhance image contrast by using the image histogram. CLAHE is the most widely used traditional HE method in contrast enhancement. These techniques tend to improve the contrast of medical images by modifying the gray-level histogram. Even though they sharpen the boundaries, they result in overenhancement and the loss of important local information, which may lead to poor diagnosis. To overcome these drawbacks, fuzzy-image enhancement has been utilized in this study. Fuzzy rule–based enhancement improves enhancement by making the high-intensity regions brighter and low-intensity regions more dark [45, 56].
Analysis of accuracy factor and pre-processing methodology of image compensation for 3D reconstruction using 2D image obtained from unmanned aerial vehicle (UAV)
Published in Journal of Asian Architecture and Building Engineering, 2022
Daeyoon Moon, Kyuhyup Lee, Hyunglyul Ko, Soonwook Kwon, Seojoon Lee, Jinwoo Song
Studies have been conducted to improve 2D image quality to overcome the limitation of photogrammetry in various construction sites. The data processing of 2D images acquired through UAV can be the most efficient method to obtain high-quality 3D data. The pre-processing method of 2D images to acquire more precise 3D data can be done variously by changing illuminance, contrast, and sharpness. Among the above processing methods, the most efficient method is changes in illuminance and contrast of images considering algorithms to acquire photogrammetry data. Generally, this process is called histogram equalization (HE). This method transforms illuminance and contrast by changing image histogram of image information values displayed as a form of histogram. Previous studies have focused on improving quality of image itself, which limited 2D data utilization, and few studies have been conducted on 3D data generation and correlation.
Colour band fusion and region enhancement of spectral image using multivariate histogram
Published in International Journal of Image and Data Fusion, 2021
Dhiman Karmakar, Rajib Sarkar, Madhura Datta
Let us consider the grey-level histogram corresponding to an image, composed of light objects on a dark background. Furthermore, let us suppose that the object and background pixels have grey levels grouped into two dominant modes. One obvious way to extract the objects from the background is to select a threshold that separates these modes. Then, any point for which is called an object point; otherwise, the point is called a background point. If three or more dominant modes characterise the image histogram (for example, two types of light objects on a dark background), it is possible to segment the image by multilevel thresholding. This is generally less reliable than its single-level thresholding. Great care must be taken with illumination because it plays a crucial role in establishing the shape of the histogram in the resulting image.
Colour-image encryption based on 2D discrete wavelet transform and 3D logistic chaotic map
Published in Journal of Modern Optics, 2020
Anand B. Joshi, Dhanesh Kumar, D.C. Mishra, Vandana Guleria
An image histogram shows the graph between pixel intensity and number of pixels for each intensity value. Figure 11(a–c) shows the histogram of images of Figures 5(a)–7(a) and Figure 11(d–f) shows the histogram of images of Figs. 5(b)–7(b), respectively. Figure 11(d–f) shows that the histogram of encrypted image is fairly uniformly and completely different from histogram of original image. Thus, the proposed method is secure against histogram based attacks.