Real Time Recognition of 2D Bar Codes in Complex Image Conditions

Liang, Ying-Hong; Wang, Zhiyan; Cao, Xiao-Ye; Xu, Xiaowei

doi:10.1109/icmlc.2007.4370421

Cited by 14 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Binarization is a necessary step in recognition bar code, and it is used in most recognition algorithm [5][6][7][8]. Selection of a proper binarization method is critical to the performance of barcode recognition system.…”

Section: Binarizationmentioning

confidence: 99%

See 1 more Smart Citation

Bar Code Recognition in Complex Scenes by Camera Phones

Liu

Yang

2008

2008 Fourth International Conference on Natural Computation

View full text Add to dashboard Cite

Mobile phones with a camera function are capable of capturing image and processing tasks. Quick Response Code has been widely used in industrial information tagging applications where high data capacity, robust error corrections are required. It has become a kind of mobile 2D barcode which is used widely in China and Japan. In deal with the influence by the different light conditions and noise, a novel recognition algorithm is given in this paper. First, we combine filter, rough location and binarization to erase noises and reduce computation. Then, we propose an accurate location and orientation, skew correction with the help of alignment patterns algorithm to build a bar code grid. Finally, we use error correction and decoding process to generate the result. Our simulation results show that the proposed schemes is accurate, fast and can significantly reduce the influence of non-uniform illumination by achieving up to 98 percent in recognition rate.

show abstract

Section: Binarizationmentioning

confidence: 99%

“…An algorithm capable of recognizing the PDF 417 barcode is proposed in real time with a mobile phone in [6]. This method includes three steps.…”

Section: Introductionmentioning

confidence: 99%

Bar Code Recognition in Complex Scenes by Camera Phones

Liu

Yang

2008

2008 Fourth International Conference on Natural Computation

View full text Add to dashboard Cite

show abstract

“…Fig.1 shows most of the complex cases. As described in [1], the main difficulties of these situations are listed as follows:…”

Section: Introductionmentioning

confidence: 99%

“…A classifier method using Adaboost algorithm, which is well developed and widely used in human face detection, to allocate the four vertexes of PDF417 barcode is present in [2] by Yan and Wang. While the training process is long and the result is hard to predict, they developed a new locating approach [1] by detecting line segments that have consecutive pixels with the same gray value (black or white) in binarized image, considering the fact that the gray change frequency of the code area is quite high. This method provides a common approach for locating the code region for any rectangular bar codes and can overcome the effect caused by background noises, but when it comes to the samples with small code region, the performance is not as well as hoped.…”

Section: Introductionmentioning

confidence: 99%

An Improved Recognition Method of PDF417 Barcode

Liu

Yin

et al. 2010

2010 Chinese Conference on Pattern Recognition (CCPR)

View full text Add to dashboard Cite

An improved recognition method of PDF417 barcode is proposed in this paper. It is efficient and accurate in complex image conditions, including high noises, distortions, low contrast and uneven environment illumination. The method consists of the following four steps: ROI detection-based on edge detection and morphological operation, barcode rectification-based on bilinear interpolation, rows and columns segmentation-based on projection and waveform analysis, and the final decoding process. Experimental results showed that the proposed method can successfully detect and recognize PDF417barcode in various image conditions.

show abstract

“…The method works well with images with bad illumination conditions and with strong perspective deformation. Y Liang, et al [4] proposed a method which includes three steps: The first step detects the code region using the Otsu algorithm [5] and the Least Square Method (LSM). The second method searches for the cut-off rules with a scanning approach.…”

Section: Introductionmentioning

confidence: 99%