Character recognition technology of power engineering drawings based on feature extraction and template matching
HOU Kai
MEI Shiyan
Abstract：[Objective]Power engineering drawings are essential for production planning,construction,and check and acceptance stages in engineering projects.However,traditional manual recognition methods suffer from low efficiency,high error rates,and high costs,which makes them unsuitable for modern complex engineering projects.In recent years,significant progress has been made on computer vision technology in the field of automatic recognition.Nevertheless,existing algorithms still face challenges such as low recognition efficiency and poor accuracy in identifying slanted and deformed characters in power engineering drawings.[Methods]To address these shortcomings,a character recognition algorithm based on the visual geometry group(VGG)network and Hu invariant moment was proposed,which aimed to improve the recognition efficiency and accuracy for power engineering drawings by combining scale-adaptive deep convolutional features with Hu invariant moment features.Firstly,deep convolutional features were extracted using the VGG network,and the output layer was adaptively selected to achieve scale-adaptive feature extraction for templates and images.This approach avoided the multiple times of feature extraction in traditional sliding window techniques,only extracting features once for each template and image and thereby significantly improving processing efficiency.Secondly,to address the challenges of slanted and deformed characters,Hu invariant moment features were integrated as supplementary features.Their translation and rotation invariance were leveraged to enhance robustness against complex character shapes.[Results]The performance superiority of the proposed algorithm was validated in terms of efficiency and accuracy by comparing it with existing algorithms.The results demonstrate that the proposed algorithm offers significant advantages.Its execution time is approximately one-fourth that of the traditional convolutional neural networks(CNNs)-based character recognition algorithm,namely that the proposed algorithm has greatly improved processing speed.By integrating Hu invariant moment features,the algorithm exhibits strong robustness in recognizing slanted and deformed characters.Adopting an adaptive output layer selection strategy further enhances the accuracy and robustness of feature extraction,surpassing the fixed-layer feature extraction methods.[Conclusion]The proposed algorithm shows greater adaptability in complex scenarios,holding promising application potential.The highlights of this study are as follows:the proposed scale-adaptive deep convolutional feature extraction method achieves single-step feature extraction in character recognition of power engineering drawings and thereby significantly improves efficiency;the integration of Hu invariant moment features enhances the ability to recognize complex character shapes,particularly robustness against slanted and deformed characters.This study not only provides an efficient character recognition algorithm but also offers new perspectives for the automated processing of power engineering drawings with computer vision.Future research may focus on further optimizing the robustness of character features to improve system performance.
Keywords：power engineering drawingcharacter recognitionfeature extractiontemplate matchingVGG networkdeep convolutional featurenormalized cross-correlation coefficientHu invariant moment
Publication Date：2025-03-31
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：7( 176-182 )