利用影像自動判讀多組指針式壓力表

Automatically reads multiple sets of gauge pointer

賴正文(Cheng-Wen Lai)

指導教授 ： 林啟芳

元智大學/資訊學院/資訊工程學系/碩士(2013年)

https://doi.org/10.6838/YZU.2013.00325

摘要

隨著電腦、網路與影像設備的進步，透過網路攝影機擷取高解析的影像，並運用後端電腦自動進行影像辨識，應用於工業上能有效提升工作效率並減少錯誤，對於取代人眼觀測與記錄，更是影像辨識未來重要的發展方向。
本論文針對影像辨識與自動化結合，提出一套自動化辨識多組壓力表與讀取數據的系統，可有效應用於需要大量指針型儀表觀測之場所。透過架設影像設備進行分析，運用壓力表圓形外框特徵自動定位然後讀取壓力數值，及可有效率的透過影像自動收集數據，提供即時警戒與長時間數據分析。

關鍵字

區域分割 ； 圓形偵測 ； 指針表

並列摘要

With computers, network and video equipment advances, high resolution webcam image capture, and the use of back-end computer automated image recognition, in industrial applications can effectively enhance the work efficiency and reduce errors that can replace the human observation and record, image recognition is an important future direction of development.
This thesis combines image recognition and automation, automatic identification and proposed a set of gauges read multiple data systems. This system can be effectively applied to the pointer type instrument requires a lot of observation of the place. Erection of imaging equipment for analysis, using a circular frame features automatic positioning gauge and then read the pressure values. Efficient use the image may be automatically collected data, providing real time data analysis and alert.

並列關鍵字

Region-segmentation method ； Circle detection ； Dials gauges

參考文獻

[1] R. T. Chin and C. A. Harlow, “Automated visual inspection: A survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 4, no. 6, pp. 557-573, 1982.

[2] M. L. Baird, “GAGESIGHT: A computer vision system for automatic inspection of instrument gauges,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 5, no. 6, pp. 618-621, 1983.

[3] Z. A. Jaffery and A. K. Dubey, “Real time visual inspection system (RTVIS) for calibration of mechanical gauges,” Proceedings of the IEEE Recent Advances in Intelligent Computational Systems, pp. 841-846, Trivandrum, Sept. 2011.

[4] Z. A. Jaffery and A. K. Dubey, “Architecture of non-invasive real time visual monitoring system for dial type measuring instrument,” IEEE Sensors Journal, vol. 13, no. 4, pp. 1236-1244, 2013.

[9] R. O. Duda and P. E. Hart, “Use of the Hough transformation to detect lines and curves in pictures,” Communications of the ACM, vol. 15, no. 1, pp. 11-15, Jan. 1972.