作者:
孫廣旗(新興河北工程技術(shù)有限公司,河北 邯鄲 056107)
崔 勇(中國科學(xué)院沈陽自動(dòng)化研究所,遼寧 沈陽 100169)
申振鑫(新興河北工程技術(shù)有限公司,河北 邯鄲 056107)
王 宇(中國科學(xué)院沈陽自動(dòng)化研究所,遼寧 沈陽 100169)
摘要:本文針對(duì)鑄管行業(yè)常見的鑄管鑄字號(hào)的特點(diǎn),設(shè)計(jì)了基于深度學(xué)習(xí)的鑄管內(nèi)壁陽文鑄字的檢測和識(shí)別方案。文中對(duì)比了主流的神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu),分析其優(yōu)缺點(diǎn)并確定了方案的細(xì)節(jié)。在鑄管廠部署實(shí)施后,通過科學(xué)的方法對(duì)應(yīng)用效果進(jìn)行了統(tǒng)計(jì),驗(yàn)證了該鑄字檢測和識(shí)別方案的優(yōu)異效果。
關(guān)鍵詞:CNN;深度學(xué)習(xí);鑄字檢測;鑄字識(shí)別
Abstract: In this paper, according to the characteristics of common ironpipecharacters, we design the detection and identification scheme ofraised characters in the inner wall of iron pipes based on deep learning.In this paper, we compare the most famous neural network structures,analyze their advantages and disadvantages and determine the details ofthe scheme according the result. After being deployed and implementedin the ductile iron pipes factory, the application effect is statisticallyanalyzed scientifically, and the excellent effect of the casting detectionand identification scheme are verified.
Key words: Deep learning; CNN; Iron-Pipe character detection; Iron-Pipe character Recognition
在線預(yù)覽:基于深度學(xué)習(xí)的鑄管鑄字的檢測與識(shí)別方案設(shè)計(jì).pdf
摘自《自動(dòng)化博覽》2021年10月刊