Brain Tumour Isolation in MRI Images Based on Statistical Properties and Morphological Process Techniques

Low cost blood vein detection system based on near-infrared LEDs and image-processing techniques

“…The image acquired from the prototype vein detection system is a 24-bit colour image, which is converted to greyscale (8 bit). Colour images have the ability to store more information than greyscale images; thus, the colour image is larger than the greyscale image, leading to a longer processing time [25]. Figure 5 and 6 show colour and greyscale images acquired by the system.…”

“…The image is further enhanced by reducing or removing blur from the image. The Wiener filter is a low-pass filter that depends on the colour density of the image and uses the mean and standard deviation to determine which pixels will be replaced with the centre of the window within the field of adjacent pixels [25].…”

“…Apply a series of morphological processes to eliminate unwanted pixels. The morphological processes provided by the MATLAB environment will include choosing the largest compound to eliminate unwanted pixels that do not represent the vein area by using the connected vehicle algorithm and eliminating the wide vein by using the strel function [25].…”