在结合矩形框加权均值算法的基础上,提出一种对光照不均图像进行二值化处理的自适应加权均值算法。对流量计图像中每个像素点分别计算阈值,利用和值表及自适应计算调整参数t,可有效地避免光照不均的影响,减少程序计算量,增强阈值自适应能力,提高流量检测速度及图像二值化处理效果。结果显示,在C++环境下,分别运用自适应加权均值算法和传统的基于小波包及Niblack 算法,对所采集的同一幅流量计光照不均图像进行二值化处理,自适应加权均值算法用时1.6 ms,基于小波包及Niblack 算法用时9.3 ms,且自适应加权均值算法处理效果明显优于传统算法。
In order to obtain the field flowmeter data that can not be transmitted as electrical signals automatically, the binarization is necessary. The current method can not eliminate the influence of the uneven illumination in processing the flowmeter data. Therefore, an improved weighted average algorithm combined with a rectangular box is put forward. The method of the summed-area table is used to calculate the sum of the gray values in each rectangular area of the flowmeter image, which reduces the running time effectively. Meanwhile, the method of the class space combined with the cohesion is applied to automatically adjust the parameters. With the C++ programming and the method, the image processing time is 1.6 ms. For the same image, the image processing time by the Wavelet Packet and the Niblack Method is 9.3 ms. Therefore, the image processing speed is significantly improved by the method. The experiments show that the binarization of the unevenly illuminated image is improved with the method and a better image is obtained from the flowmeter data. Hence, the accuracy of the flowmeter is improved.
[1] 李忠柱, 吕颖超, 黄志尧, 等. 基于C4D技术的小通道流体流量测量装置及方法[J]. 工程热物理学报, 2013, 34(9): 1679-1682. Li Zhongzhu, Lü Yingchao, Huang Zhiyao, et al. A device and method for flowrate measurement of fluid in small channel based on C4D technique[J]. Journal of Engineering Thermophysics, 2013,34(9):1679-1682.
[2] 李勇, 雷晶. 汽轮机凝汽器冷却水流量的在线测量方法研究[J]. 仪器仪表学报, 2010, 31(6): 1347-1351. Li Yong, Lei Jing. Research on the online monitoring method for flow rate of cooling water in condenser of steam turbine[J]. Chinese Journal of Scientific Instrument, 2010, 31(6): 1347-1351.
[3] 陆培源, 王建中, 罗涛. 基于改进Otsu的室外道路实时检测与跟踪算法[J]. 科技导报, 2011, 32(8): 58-62. Lu Peiyuan, Wang Jianzhong, Luo Tao. Real-time detection and tracking of road information for outdoor vision-based robot based on improved Otsu[J]. Science & Technology Review, 2011, 32(8): 58-62.
[4] Veenman C J, Reinders M J T, Backer E. A maximum variance cluster algorithm[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2002, 24(9): 1273-1280.
[5] Tan K T, Chai D, Kato H, et al. Designing a color barcode for mobile applications[J]. IEEE Pervasive Computing, 2010 (2): 50-55.
[6] 唐泉, 樊晓平, 黎燕. 基于分块聚类的车牌图像二值化方法[J]. 计算机仿真, 2010, 27(3): 286-289, 352. Tang Quan, Fan Xiaoping, Li Yan. Binary method of license plate image basedonblocking- clustering[J]. Computer Simulation, 2010, 27 (3): 286-289, 352.
[7] Technical Report EPCWellner P D. Adaptive thresholding for the digital desk[R]. EPC1993-110. Connecticut: Xerox, 1993.
[8] Bradley D, Roth G. Adaptive thresholding using the integral image[J]. Journal of Graphics, Gpu, and Game tools, 2007, 12(2): 13-21.
[9] 杨吉宏, 胡顺波, 张民, 等. 灰度图像加权有向平滑滤波算法[J]. 计算机工程与设计, 2010, 31(1): 153-156. Yang Jihong, Hu Shunbo, Zhang Min, et al. Weighted and directional smoothing algorithm for gradation images[J]. Computer Engineering and Design, 2010, 31(1): 153-156.
[10] 皋军, 黄丽莉, 孙长银. 一种基于局部加权均值的领域适应学习框架[J]. 自动化学报, 2013, 82(7): 1037-1052. Gao Jun, Huang Lili, Sun Changyin. A local weighted mean based domain adaptation learning framework[J]. Acta Automatica Sinica, 2013, 82(7): 1037-1052.
[11] 张洁玉, 赵鸿萍, 陈曙. 自适应阈值及加权局部二值模式的人脸识别[J]. 电子与信息学报, 2014, 36(6): 1327-1333. Zhang Jieyu, Zhao Hongping, Chen Shu. Face recognition based on weighted local binary pattern with adaptive threshold[J]. Journal of Electronics & Information Technology, 2014, 36(6): 1327-1333.
[12] 木拉提·哈米提, 周晶晶, 严传波, 等. 新疆地方性肝包虫CT图像的灰度直方图特征提取与分析[J]. 科技导报, 2012, 33(6): 66-70. Hamit Murat, Zhou Jingjing, Yan Chuanbo, et al. Feature extraction and analysis on CT image of xinjianglocalliver hydatid by using grayscale histograms[J]. Science & Technology Review, 2012, 33(6): 66- 70.
[13] 吕行军, 韩宪忠, 王克俭, 等. 基于最大方差阈值法的火车票图像二值化处理[J]. 计算机应用与软件, 2012, 29(7): 249-253. Lü Xingjun, Han Xianzhong, Wang Kejian, et al. Binarisaton processing of train ticket images based on maximum variance threshold algorithm[J]. Computer Applications and Software, 2012, 29(7): 249-253.
[14] 申森, 李艾华, 姚良, 等. 基于小波包和Niblack法的枪号图像二值化算法[J]. 光子学报, 2013, 42(3): 354-358. Shen Sen, Li Aihua, Yao Liang, et al. Gun code binary image algorithm based on wavelet packet and Niblack method[J]. Acta Photonica Sinica, 2013, 42(3): 354-358.
[15] 高美琴, 毋立芳, 李建德, 等. 利用纹理相关性对OCT影像进行血管分割[J]. 信号处理, 2013, 29(4): 527-531. Gao Meiqin, Wu Lifang, Li Jiannder, et al. Essel border segmentation of oct image susing textural correlation[J]. Journal of Signal Processing, 2013, 29(4): 527-531.
