隨著貿易越來越頻繁，每一個商品在製造、買賣的過程中都需要透過條碼來確保過程正確無誤，但條碼容易受光照不均、雜訊等因素影響，再加上條碼的種類十分多元，也讓條碼的定位更加困難。由於傳統方法只能找單一種類條碼且易受到雜訊的影響而使結果有誤，因此為了有效解決這些問題，本研究採用以深度學習為基礎的方法來研究多種類條碼的定位。本研究分為三個階段。第一階段訓練深度學習網路來找出條碼。考慮到FasterRCNN網路相較於RCNN等較舊的神經網路，其在物體辨識的領域中取得了更快更準的辨識結果，因此本研究採用FasterRCNN的架構進行神經網路的訓練。訓練所需資料採用CipherLab之條碼掃描器拍攝，總共包含10008張圖片，並以8:1:1比例分為訓練資料、驗證資料及測試資料。第二階段為提出2個有效的傳統影像處理演算法來辨識條碼。本研究先利用神經網路剪枝的方式試圖找出條碼的特徵，然而效果不佳，因此改採用Gradcam將神經網路的權重可視化方法，以獲得每層神經網路權重分別對圖片的哪些區域影響最大。藉此來幫助傳統影像處理演算法的優化。結果評估所採用的影像以CipherLab公司所提供之測試圖像作為依據，評估方法以辨識結果之precision及recall為主，其中又特別著重在recall值，本研究最終神經網路結果recall為0.89、precision為0.65，最終2種傳統影像方法模擬較佳者可達到recall數值為0.88、precision數值為0.52，顯示本研究對條碼辨識能夠有不錯的效果。第三階段會將傳統影像演算法較佳的結果實現在PDA模擬器上，其辨識速度約為1200ms。雖然在執行速度上有所不足，但本方法能夠成功的定位多種不同的條碼，並且擁有不錯的定位結果。

Abstract
As trade grows more and more frequently, every product needs to use a barcode to ensure that the process of manufacturing and shipping is correct. However, the recognition of barcodes can easily be affected by factors such as uneven lighting and noise. In addition, the numerous categories of barcodes also make the barcode localization difficult. Traditional methods are limited for the detection capability with different types of barcodes and for the detection accuracy under noisy conditions. In order to solve these problems, we apply deep learning to localize various types of barcodes.

This research consists of three parts. Firstly, a deep learning neural network was trained to find out barcodes. FasterRCNN was adopted in this research because of its faster and more accurate detection results compared to the older neural network such as RCNN. The training data used were captured by the barcode scanner made by CipherLab. A total of 10008 images were divided into the training data, the verification data and the test data by a ratio of 8:1:1 with the verification and the test date in a ratio.

Secondly, this research proposed two algorithms based on the results of FasterRCNN. Neural network pruning was used to find the feature of barcodes. However, the result was unsatisfactory. Hence, a weight visualization method, Gradcam, was used to get the saliency maps at some layers of the neural network. By using the result of Gradcam, two traditional image processing approaches was proposed for barcode detection. Method 1 used the image entropy to enhance the region of barcodes. Method 2 detected barcodes by morphology. Testing barcode images provided by CipherLab were used to validate the performance of the two methods. We used recall and precision for our evaluation method, and focused on the performance of recall.

The recall value of FasterRCNN was 0.89 and precision value was 0.65. Method 1 obtained the recall value of 0.86 and the precision value of 0.53, while Method 2 was with the recall value of 0.88 and the precision value of 0.52. The result showed that our method can detection barcode well.

Finally, we choose method 2 and implemented it on the PDA simulator. On PDA simulator we can detect all the barcodes of an image within 1.2 seconds. Although we do not have very good barcode detection speed, our method can successfully detect various kind of barcodes and achieve good detection results.

參考文獻
Sonam Wasule, Shilpa Metkar. (2016). “An effective approach to recover
corrupted or mobile captured 2D barcode images with improved accuracy,” 2016 Conference on Advances in Signal Processing (CASP)Cummins College of Engineering for Women, Pune, Jun 9-11.

Feng Liu, Anan Liu, Meng Wang, Zhaoxuan Yang. (2010). “Robust and Fast Localization Algorithm for Data Matrix Barcode,” 2010 International Conference on Optoelectronics and Image Processing, 356-359.

Anil K. Jain, Sushil K. Bhattacharjee and Yao Chen On (1992). “Texture In Document Images,” Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1992, 677-680.

YING-HONG LIANG, ZHI-YAN WANG (2006). “A SKEW DETECTION METHOD FOR 2D BAR CODE IMAGES BASED ON THE LEAST SQUARE METHOD,” 2006 International Conference on Machine Learning and Cybernetics, 3974-3977.

Alexander Tropf, Douglas Chai (2006). “LOCATING 1-D BAR CODES IN DCT-DOMAIN,” 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, 741-744.

Leng Biao (2007). “A DataMatrix-based Mutant Code Design and Recognition Method Research,” Fourth International Conference on Image and Graphics (ICIG 2007), 570-574.

Ruwan Janapriya, Lasantha Kularatne, Kosala Pannipitiya, Anuruddha Gamakumara (2003). “A LOW COST OPTICAL BARCODE READER USING A WEBCAM”, Engineering Research Unit (ERU) Symposium, Sri Lanka.

Hock Chai, Douglas Florian (2005). “Locating and Decoding EAN-13 Barcodes from Images Captured by Digital Cameras,” International Conference on Information Communications & Signal Processing, Bangkok, Thailand, 6-9 Dec. 2005.
Chunhui Zhang, Jian Wang, Shi Han, Mo Yi, Zhengyou Zhang (2006). “AUTOMATIC REAL-TIME BARCODE LOCALIZATION IN COMPLEX SCENES,”International Conference on Image Processing, Atlanta, GA, USA,497-500.

Yue Liu, Bo Yang, Ju Yang (2008). “Bar Code Recognition in Complex Scenes by Camera Phones,”International Conference on Natural Computation, Jinan, China, 462-466.

Nan Guo, Xiaonian Wang, Zhuping Wang, Jin Zhu (2015). “GBVS based 1D and 2D barcodes Localization in complex scene,” 2015 International Conference on Computational Intelligence and Communication Networks, 352-356.

Alessandro Zamberletti, Ignazio Gallo, Simone Albertini (2013). “Robust Angle Invariant 1D Barcode Detection,” 2013 Second IAPR Asian Conference on Pattern Recognition, 160-164.

K. Han, M. Sun, X. Zhou, G. Zhang and H. Dang, Z. Liu (2017). “A New Method in Wheel Hub Surface Defect Detection: Object Detection Algorithm Based on Deep Learning,” International Conference on Advanced Mechatronic Systems, 335-338.

Y.-H. Byeon, K.-C. Kwak (2017). “A Performance Comparison of Pedestrian Detection Using Faster RCNN and ACF,” IIAI International Congress on Advanced Applied Informatics (IIAI-AAI), 858-863.

G. Chandan, A. Jain, H. Jain, Mohana (2018). “Real Time Object Detection and Tracking Using Deep Learning and OpenCV,” International Conference on Inventive Research in Computing Applications (ICIRCA), 1305-1308.

Hyeonwoo Noh, Seunghoon Hong, Bohyung Han (2015). “Learning Deconvolution Network for Semantic Segmentation,” 2015 IEEE International Conference on Computer Vision (ICCV),1520-1528.

Chengyang Li, Dan Song, Ruofeng Tong, Min Tang (2019). “
Illumination-aware faster R-CNN for robust multispectral pedestrian detection,” Pattern Recognition 85, 161–171

Tomas Björklund, Attilio Fiandrotti, Mauro Annarumma, Gianluca Francini, Enrico Magli (2019). “Robust license plate recognition using neural networks trained on synthetic images,” Pattern Recognition 93, 134–146

Otsu N. (1979). “A thresholding selection method from gray-level histograms”, IEEE Transactions on Systems, Man, and Cybernetics, Vol. 9, 62-66.

Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, (2012). “ImageNet Classification with Deep Convolutional Neural Networks,” Advances in Neural Information Processing Systems, Vol.25, 1-9.
Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, Hans Peter Graf, (2017). “Pruning Filters for Efficient ConvNets,” Computer Vision and Pattern Recognition, 1-13.

Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra, (2019). “Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization,” International Journal of Computer Vision, 1-24.

Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun, (2015). “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” Computer Vision and Pattern Recognition, 1-14.

Andy的條碼世界 (2012)。2021 年 1 月 7 日 取自http://www.appsbarcode.com/barcode-type.php
http://www.appsbarcode.com/Code%2039.php