Image Pre-Processing of USG Images by Adjusting Varying Luminance Trend and Applying Morphological Operations on Segmented Image using Thresholding

Dr. Sampada Margaj

Abstract: This study discusses analysis of USG images by pre-processing the images for varying luminance by performing morphological operations. Ultrasound images are used to provide information in most of the medical diagnosis. Here we have tried to fix the problem with kidney stone USG images. The image generated by the two-dimensional ultrasound has not been able to provide complete information. Therefore, in order get the form of kidney stone on ultrasound image can be clearly identified with the necessary process of image analysis that can detect the boundaries of objects edges, so that it can differentiate between one object with another object on the ultrasound image. We have used linear model to remove the trend of varying illuminance and applied morphological operations on the same to get more accurate segmented image. It can be used in the ultrasound image segmentation process to obtain the best shape of the object in the image. Based on the available results we can be concluded that the simple linear regression and morphological processing are an appropriate method to fix the varying illuminance and making clearer USG image.

Keywords: USG, Simple linear regression, Thresholding, Morphological operations, Kidney stone detection

Edition: Volume 12 Issue 2, February 2023,

Pages: 1080 - 1084