Simulink Component Recognition Using Image Processing

In early stages of engineering design, pen-and-paper sketches are often used to quickly convey concepts and ideas. Free-form drawing is often preferable to using computer interfaces due to its ease of use, fluidity and lack of constraints. The objective of this project is to create a trainable sketched Simulink component recognizer and classifying the individual Simulink components from the input block diagram. The recognized components will be placed on the new Simulink model window after which operations can be performed over them. Noise from the input image is removed by Median filter, the segmentation process is done by K-means clustering algorithm and recognition of individual Simulink components from the input block diagram is done by Euclidean distance. The project aims to devise an efficient way to segment a control system block diagram into individual components for recognition.