狗鼻紋影像比對

Dog Nose Print Image Matching

10.6295/TAMJ.201902_19(1).0005

羅廷君(Ting-Chun Lo)；陳艾薇(Ai-Wei Chen)；張尹瑄(Yin-Hsuan Chang)

影像切割 ； 影像基準點定位 ； 狗鼻紋辨識系統 ； 犬隻管理 ； image segmentation ； pivot point location ； Dog Nose Pattern Recognition system ； dog management

台灣管理學刊

19卷1期（2019 / 02 / 01）

77 - 93

繁體中文

隨著飼養寵物的比例提升，民眾隨意棄養及寵物走失比例也愈高，此問題便是造成流浪狗氾濫的主要因素。為了解決流浪狗的問題，除了相關法規，我們也需要有效的管理犬隻。因此本研究利用狗鼻紋紋路，如人類指紋一樣具有唯一性，結合影像處理的技術，以此建立一套狗鼻紋影像比對系統，來解決管理狗隻問題。狗鼻紋比對系統主要分成兩個部分：狗鼻紋影像切割和狗鼻紋影像比對。本研究是延續〈狗鼻紋影像基準點定位〉（林育廷，2017）切割出完整鼻紋區塊，再定位出最佳的影像基準點，並藉由同一隻狗不同角度和方向的影像找出彼此對應的區塊，進而達到辨識犬隻目的。

With the increase in the proportion of keeping pets, most of pets have still been abandoned and missing. This problem is the main factor causing the surplus of stray dogs. To solve the problem about stray dogs, we not only need the legislation, but also should effectively manage the quantity of dogs. In our research, we use dog nose prints, which is unique as human fingerprints. Besides, using techniques of image processing to develop our Dog Nose Print Image Matching system, which can solve the problem of managing dogs. The dog nose print image matching system is mainly divided into two parts: dog nose print image segmentation and dog nose print image matching. We continue ＂Pivot Point Location of Dog Nose Printimage＂ (Lin, 2017) to cut out the entire dog nose pattern. Then, locating the best pivot point of the image, and matching the patterns even though the nose of those images are different angles and directions. By this method, we achieve our purpose of identifying dogs.

1. Chan, Y.-K.,Chang, C.-C.(2001).Image matching using run-length feature.Pattern Recognition Letters,22(5),447-455.
2. Chan, Y.-K.,Huang, D. C.,Liu, K. C.,Chen, R. T.,Jiang, X.(2014).An automatic indirect immunofluorescence cell segmentation system.Mathematical Problems in Engineering,2014,1-13.
3. Coldea, N.(1994).Nose prints as a method of identification in dogs.Veterinary Quarterly,16(suppl. 1),60.
4. Crespo, J.,Schafer, R.(2012).The flat zone approach and color images.Mathematical morphology and its applications to image processing,Dordrecht, The Netherlands:
5. Dickert, L. T. (2011, August 19). Dogs noseprints can be used to prove identity, just like fingerprints. All Pet News. Retrieved from http://www.allpetnews.com/dogs-noseprintscan-be-used-to-prove-identity-just-like-fingerprints
6. Guan, X.,Jian, S.,Hongda, P.,Zhiguo, Z.,Haibin, G.(2009).An image enhancement method based on gamma correction.2009 International symposium on computational intelligence and design,Piscataway, NJ:
7. Haralick, R. M.,Sternberg, S. R.,Zhuang, X.(1987).Image analysis using mathematical morphology.IEEE Transactions on Pattern Analysis and Machine Intelligence,9,532-550.
8. Levialdi, S.(1972).On shrinking binary picture patterns.Communications of the ACM,15(1),7-10.
9. Nguyen, U. T. V.,Bhuiyan, A.,Park, L. A. F.,Ramamohanarao, K.(2013).An effective retinal blood vessel segmentation method using multi-scale line detection.Pattern Recognition,46(3),703-715.
10. Rosenfeld, A.(1970).Connectivity in digital pictures.Journal of the ACM,17,146-160.
11. Shanmugavadivu, P.,Balasubramanian, K.(2014).Particle swarm optimized multiobjective histogram equalization for image enhancement.Optics & Laser Technology,57,243-251.
12. Sim, K. S.,Tso, C. P.,Tan, Y. Y.(2007).Recursive sub-image histogram equalization applied to gray scale images.Pattern Recognition Letters,28,1209-1221.
13. Zhang, D.,Park, W.-J.,Lee, S.-J.,Choi, K.-A.,Ko, S.-J.(2012).Histogram partition based gamma correction for image contrast enhancement.2012 IEEE 16th International Symposium on Consumer Electronics,Harrisburg, PA:
14. 行政院農委會（2017）。106 年度全國家犬貓數量調查結果統計表。動物資訊保護網。取自 https://animal.coa.gov.tw/html/index_06_1_Y106.html
15. 林育廷(2017)。台中，國立中興大學資訊管理學系。