1. College of Engineering, Nanjing Agricultural University, Nanjing 210031, China 2. Changzhou Textile Garment Institute of Technology, Changzhou 213164, China
摘要: 提出一种基于高光谱成像技术的鸡胴体表面低可见污染物的双波段检测算法。首先,在所采集的高光谱数据中,选择ROI(region of interesting)内光谱的同一性最好、同时与边缘区域平均光谱差值最大的675 nm波段图像进行二值化处理,利用区域生长法提取最大连通区域作为掩膜。再将掩膜与污染物可分辨度最大的400 nm谱段图像进行“与”操作,提取出最大面积的鸡胴体待检ROI,最后利用标记法识别出ROI内有污染物存在的鸡胴体。试验结果表明,采用这种双波段算法,不仅可以获得能够根据鸡胴体形状及位置自适应调节的最大ROI(比已有研究方法提取的ROI面积大176%以上),而且对鸡胴体表面低可见度血液、胆汁和粪便的正确检出率平均可达81.6%。
关键词:双波段算法;污染物;可分辨度;高光谱图像;鸡胴体
Abstract:A novel dual-band algorithm for detecting contaminants with low visibility on chicken carcass surface based on hyperspectral image was proposed. Firstly, The 675 nm band image, in which the identity of the intensity within ROI (Region of Interest)is the best and the spectrum difference between ROI and the edge of the ROI is the biggest, was chosen from the hyperspectral data for binarization and the mask was extracted by using region growing on the biggest connected area. Then the “and” operation between the mask and the 400 nm band image with the largest discriminability of contaminants was carried out. The max ROI which can self adapt according to the position and shape of the chicken carcass was obtained. Finally,the labeling method was used to recognize if there are contaminations within the segmented ROI. The results showed that through the proposed method, the max ROIs which could self adapt to the position and shape of the chicken carcass were extracted and the average size of the ROI was bigger than 176% compared to that by existing methods. The average correct identification rate of contaminations such as blood, bile and feces was 81.6%.
[1] Musgrove M T, Berrang M E, Byrd J A, et al. Poultry Science, 2001, 80(6): 825. [2] Berrang M E, Buhr R J, Cason J A. Poultry Science, 2000, 79(2): 286. [3] Berrang M E, Smith D P, Windham W R, et al. Journal of Food Protection, 2004, 67(2): 235. [4] Everard C D, Kim M S, Lee H. Proc. SPIE, Sensing for Agriculture and Food Quality and Safety VI, 2014, 9108: 91080A. [5] Park B, Chen Y R. Transactions of the ASAE, 1994, 37(6): 1983. [6] Park B, Chen Y R, Huffman R W. Journal of Food Engineering, 1996, 30(1): 197. [7] Park B, Chen Y R, Nguyen M. Journal of Agricultural Engineering Research, 1998, 69(4): 351. [8] Yoon S C, Park B, Lawrence K C, et al. Computers and Electronics in Agriculture, 2011, 79(2): 159. [9] Park B, Lawrence K C, Windham W R, et al. Transactions of the ASAE, 2002, 45(6): 2017. [10] Park B, Yoon S C, Windham W R, et al. Sensing and Instrumentation for Journal of Food Quality and Safety, 2011, 5(1): 25. [11] ZHAO Jin-hui,TU Dong-cheng,OUYANG Jing-yi, et al(赵进辉, 涂冬成, 欧阳静怡, 等). Acta Agriculturae Universitatis Jiangxiensis(江西农业大学学报), 2011, 33(3): 0573. [12] ZHAO Jin-hui, YU Fang, WU Rui-mei, et al(赵进辉, 吁 芳, 吴瑞梅, 等). Laser &Optoelectronics Progress(激光与光电子学进展), 2011, 48(7): 163. [13] Yang C C, Chao K, Kim M S. Sensing and Instrumentation for Food Quality and Safety, 2009, 3(1): 70. [14] Chao K, Yang C C, Chen Y R, et al. Poultry Science,2007, 86(11): 2450. [15] Yang C C, Chan D E, Chao K, et al. Proc. SPIE, Optics for Natural Resources, Agriculture and Foods, 2006, 6381: 63810Y.