Image Segmentation of Cattle Muzzle Using Region Merging Statistical Technic
Keywords:cattle muzzle, statistical region merging, segmentation, identification, digital image processing.
Making an identification system that able to assist in obtaining, recording and organizing information is the first step in developing any kind of recording system. Nowadays, many recording systems were developed with artificial markers although it has been proved that it has many limitations. Biometrics use of animals provides a solution to these restrictions. On a cattle, biometric features contained in the cattle muzzle that can be used as a pattern recognition sample. Pattern recognition methods can be used for the development of cattle identification system utilizing biometric found on the cattle muzzle using digital image processing techniques. In this study, we proposed cattle muzzle identification method using segmentation Statistical Region Merging (SRM). This method aims to identify specific patterns found on the cattle muzzle by separating the object pattern (foreground) from unnecessary information (background) This method is able to identified individual cattle based on the pattern of it muzzle. Based on our evaluation, this method can provide good performance results. This method good performance can be seen from the precision and recall : 87% and the value of ROC : 0.976. Hopefully this research can be used to help identify cattle accurately on the recording process.
A. Novianto, A. M. Arymurthy. (2012a). Beef Cattle Identification Based On Muzzle Pattern Using a Matching Refinement Technique in SIFT Method. ICACSIS.
A. Novianto & A. M. Arymurthy. (2012b) Automatic Cattle Identification based on Muzzle Photo Using Speed-Up Robust Features Approach. 3rd European Conference of Computer Science ECCS.
Boltz, S. (2009). Image Segmentation Using statistical Region Merging. IEEE Trans. Pattern Anal. Mach. Intell, 26: 1452-1458.
B. Zhang, et. al. (2010). Retinal Vessel Extraction by Matched Filter with First-Order Derivative of Gaussian. Computers in Biology and Medicine, 40: 438-445.
D. P. Berry., et. al. (2005) Accuracy of Predicting Milk Yield From Alternative Milk Recording Schemes. Animal Science, 80(01): 53-60.
F. Lang., et. al. (2014). Polarimetric SAR Image Segmentation Using Statistical Region Merging. Geoscience and Remote Sensing Letter, 11(2): 509-513.
Gonzalez, R. C., et. al. (2008) Digital Image Processing. 3rd ed. USA: Prentice Hall. 2008.
Gualtieri, C. T., Ondrusek, M. G. and Finley, C. (1985). Attention deficit disorders in adults. Clinical Neuropharmacology, 8: 343-356.
H. Leclerc., et.al. (2004). Milk Recording: a Comparison Of The T, Z and Standard Method (Z = Milk Yield Recorded on 2 Milkings and The Contents on One Alternate Milking). Performance Recording of Animals: State of the Art: 198-205.
J. Gatc., et. al. (2012). Plasmodium Parasite Detection on Red Blood Cell Images for the Diagnosis of Malaria Using Double Thresholding. International Conference on Advance computer Science and Information System: 731- 736.
Nock, R., Nielsen. F. (2014) Statistical Region Merging. IEEE Trans. Pattern Anal. Mach. Intell, 26: 1452-1458.
Rahayu, A., et al. (2013). Genetic Evaluation of Dairy Cattle Using Actual Milk Yield Records and Centering Date Method (CDM). Jurnal Ilmiah Peternakan, 1(1): 236-243.
Zhai, L. & Hu, Q. (2011). The Research of Double-biometric Identification Technology Based on Finger Geometry and Palm Print. 2nd International Conference Artificial Intelligence, Management Science and Electronic Commerce (AIMSEC). IEEE xplore: 3530-3533.
Authors who publish with this journal agree to the following terms:
a. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License - Share Alike that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
b. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
c. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
All articles published Open Access will be immediately and permanently free for everyone to read and download. We are continuously working with our author communities to select the best choice of license options, currently being defined for this journal as follows: