Real-time image processing system for endoscopic applications
Jingxuan Kang, Rajamani Doraiswami · 2004
A simple and cost-effective real-time image processing system has been developed to enable rapid prototyping of full-fledged image processing systems. Images are periodically acquired from a video source using specialized control software. Image data is passed via interprocess communication to image processing modules executed in the MATLAB environment. Processed results are returned to the control software and displayed in real-time. Image processing modules have been developed for the recognition and visual enhancement of gastrointestinal polyps contained in endoscope video. These modules are implemented within the prototyping system to process endoscope video in real-time. The objective of the system is not to perform diagnosis in lieu of a physician, but to assist in the visualization and identification of abnormal structures such as polyps during endoscopic procedures. A prototype of the system has been constructed and tested using recorded endoscope video.