Bone Fissure Detection in Digital X-ray images by using Image Processing

COMPUTER ENGINEERING

The image processing technique is extremely helpful for several applications like biomedical, security, satellite imaging, personal image and medicine etc. The implementation of image processing such as image enhancement, feature segmentation and feature excitation are used for fracture detection. The uses canny edge detection methodology for segmentation. The canny method produces perfect information from the bone image. Bone fracture is a common problem in every developed countries and the number of fractures also increasing day by day very rapidly. A bone fracture may occur due to simple accidents or different types of diseases. There are mainly four types of bone demonstration X-ray, CT, MRI and Ultrasound. But X-ray diagnosis is commonly used for bone fracture detection due to their low cost, high speed and wide availability. Although CT and magnetic resonance imaging pictures provide higher quality pictures for body organs than X-ray pictures. Moreover, the level of quality of X-ray images is enough for bone fracture detection. The RGB image is converted into binary image. This algorithm uses Haar Cascade trained model which is trained via millions and even billions of images. It also uses canny image recognition to find shape and angle of bone. So, we will also able to find number of fragments. After the segmentation the area of the fracture is calculated. The method has been tested on a set of images. The main goal of the paper is to detect the bone fracture from X-ray images using Open CV software. Open CV in Python requires very less processing power than MATLAB so it can easily be implemented on ARM benchmark processor and single board computer.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.