使用梯度向量直方圖之QR Code偵測

The detection of QR codes with histograms of oriented gradients

宋崇銘(Chung-Ming Sung)

指導教授 ： 林義隆

共同指導教授 ： 鄭志宏(Jyh-Hong Jeng)

義守大學/電機資訊學院/資訊工程學系/碩士(2015年)

https://doi.org/10.6343/ISU.2015.00141

摘要

目前QR Code(Quick Response Code)是一種常見的二維條碼，由於智慧型手機越來越普及化，QR Code的應用也越來越廣泛，常在雜誌或者是海報上發現它們的存在，為的是方便資訊的儲存和型廣告行銷。一般使用者容易透過手機的應用程式來解碼。目前應用程式必須要近距離並對準QR Code才能讀取訊息。此篇論文結合QR Code和梯度方向直方圖(Histograms of Oriented Gradients，HOGs)，希望能在一張影像裡面找出QR Code的所在位置。輸入影像經過HOG特徵擷取，將像素點分類成9個方向的強度，透過特徵的資訊來辦識影像中是否存在QR Code。由於QR Code的影像主要由黑白影像的小方塊所組成，經過HOG的特徵擷取之後的資訊容易辨識，最後使用AdaBoost分類器來判斷，以此來提升辨識率。

關鍵字

二維條碼 ； 梯度向量直方圖 ； 分類器

並列摘要

With the popularity of Smartphone, the applications of QR Code become more diverse. To store information and advertising sale, we can often find QR Codes in a periodical or on the poster. General users can utilize mobile phone's application to decode QR Code easily. Such mobile application requires to get close to and point at the QR Code to read data. This study uses HOGs (Histograms of Oriented Gradients) to perform QR code detection. It aims to improve the recognition rate of QR Code in an image. When extracting HOG feature from input image, each pixel will be divided into nine directions with intensities, We then use feature information to identify the presence of QR Code in an image. Since a QR Code consists of black and white small boxes, through the HOG feature, information can easily recognized. To achieve this function, we use AdaBoost method to efficiently classify the existence of QR codes.

並列關鍵字

QR Code ； HOG ； AdaBoost

參考文獻

[5] Kobayashi, T., A. Hidaka, and T. Kurita, “Selection of histograms of oriented gradients features for pedestrian detection,” in Proc.14th Int. Conf. Neural Information Processing, Kitakyushu, Japan, Nov.13-16, pp.598-607, 2007.

[6] D. M. Gavrila and V. Philomin, “Real-time object detection for smart vehicles,” IEEE International Conference on Computer Vision, vol. 1, pp. 87–93, 1999.

[7] D. M. Gavrila, “A Bayesian, exemplar-based approach to hierarchical shape matching,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 8, pp. 1408–1421, 2007.

[10] B. Wu and R. Nevatia, “Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors,” IEEE International Conference on Computer Vision, pp. 90–97, 2005

[12] Y. T. Chen and C. S. Chen, “A cascade of feed-forward classifiers for fast pedestrian detection,” IEEE Asian Conference on Computer Vision, pp. 905–914, 2007.