基于最小平均距离免疫算法的模糊红外图像分割

doi:10.3964/j.issn.1000-0593(2018)11-3645-08

Abstract
References
Related Citation (12)

Download: PDF (1712 KB)
Export: BibTeX | EndNote (RIS)

Abstract Criminals tend to use various methods to cope with the traditional forensic image technologies, so infrared image is becoming an effective means for obtaining crime scene traces. However, segmentation targets from infrared image shoot in crime scene is a challenging task as these images are target weakened infrared images. Previous studies about immune algorithms do not describe immune variation and immune recognition distance in the network and algorithm. In opposition to segment these target weakened traces infrared images, we propose a new immune framework with immune variation and minimum mean immune recognition distance, and construct a new immune segmentation algorithm with minimum mean distance immune field. According to the distinguishing feature of infrared images, this method use multi-step classification algorithm, immune variation and adaptive immune minimum mean distance recognition to achieve optimal classification based on the overall statistical properties of target areas and background areas. Experimental results show that the proposed immune algorithm with minimum mean distance can segment target weakened infrared images efficiently. Compared with classical edge template and conventional region template methods, the proposed algorithm has better segmentation results, especially the boundaries of five fingers.

Key words：Blurred infrared image; Image segmentation; Immune field

Received: 2017-11-13 Accepted: 2018-03-21

ZTFLH:

TP391

Cite this article:

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2018)11-3645-08 OR https://www.gpxygpfx.com/EN/Y2018/V38/I11/3645

[1] Guo W M, Alham N K, Liu Y, et al. Neural Processing Letters, 2016, 44(1): 161.
[2] Gao J Q, Xu L Z. Neural Processing Letters. 2016, 43(3): 805.
[3] Gharipour A, Liew A W C. Pattern Recognition, 2016, 58: 1.
[4] Girshick R, Donahue J, Darrell T, et al. IEEE Transactions on Pattern Analysis And Machine Intelligence, 2016, 38(1): 142.
[5] Christodoulidis A, Hurtut T, Ben Tahar H, et al. Computerized Medical Imaging and Graphics, 2016, 52: 28.
[6] Shi Y H, Gao Y Z, Liao S, et al. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(11): 2286.
[7] Zanetti M, Ruggiero V, Miranda M. Communications in Nonlinear Science and Numerical Simulation, 2016, 36: 528.
[8] Kim S, Yoo C D, Nowozin S, et al. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(9): 1761.
[9] Akselrod-Ballin A, Dafni H, Addadi Y, et al. Scientific Reports, 2016, 6.
[10] Kumar M P, Turki H, Preston D, et al. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(7): 1373.
[11] Zhu Z C, Nandi A K. IEEE Transactions on Wireless Communications, 2014, 13(8): 4483.
[12] Bett S K, Palamuleni L G, Ruhiiga T M. Asia Life Sciences, 2013, 245.
[13] Kapetanovic D, Rusek F, Abrudan T E, et al. IEEE Transactions on Signal Processing, 2012, 60(8): 4470.
[14] Ghimire S, Wang H Y. Computational Statistics & Data Analysis, 2012, 56(7): 2273.
[15] Nasibov E, Kandemir-Cavas C. Computational Biology and Chemistry, 2009, 33(6): 461.
[16] Srivastava M S. Journal of Multivariate Analysis, 2006, 97(9): 2057.
[17] Silva W B, Freitas C C, Sant’Anna S J S, et al. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2013, 6(3): 1263.
[18] Chen Y C, Su C T. Applied Mathematics and Computation, 2016, 283: 141.
[19] Kahraman H T. Data & Knowledge Engineering, 2016, 103: 44.
[20] Yu Xiao, Fu Dongmei. Infrared Physics and Technology，2014, 64(C): 9.
[21] Yu Xiao. Infrared Physics & Technology, 2014，(67): 116.
[22] Yu Xiao, Yuan Ximei, Dong Enzeng, et al. Infrared Physics and Technology, 2016, 77(C): 9.