Detection of circuit components on hand-drawn circuit images by using faster R-CNN method

In this study, one of deep learning methods, which has been very popular in recent years, is employed for the detection and classification circuit components hand-drawn images. Each component located different positions on scanned images circuits, are frequently used electrical electronics engineering, considered as a separate object. order to detect image, Faster Region Based Convolutional Neural Network (R-CNN) method instead conventional methods. With R-CNN method, developed years classify objects, preprocessing image data minimized, feature extraction phase done automatically. it aimed four circuits with high accuracy by using Python programming language Google Colab platform. The be detected specified resistor, inductor, capacitor, voltage source. For training model used, set was created collecting 800 consisting hand drawings people. components, pretrained Inception V2 after fine tuning arrangements depending process requirements. trained 50000 epochs, success tested drawn styles paper. able quickly rate performance. addition, loss graphics were examined. proposed shows its efficiency detecting each 4 classifying them