Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Automatic Extraction of Canine Cataract Area with Fuzzy Clustering

퍼지 클러스터링을 이용한 반려견의 백내장 영역 자동 추출

  • Kim, Kwang Baek (Division of Computer Software Engineering, Silla University)
  • Received : 2018.07.21
  • Accepted : 2018.08.21
  • Published : 2018.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Canine cataract is developed with aging and can cause the blindness or surgical treatment if not treated timely. In this paper, we propose a method for extracting cataract suspicious areas automatically with FCM(Fuzzy C_Means) algorithm to overcome the weakness of previously attempted ART2 based method. The proposed method applies the fuzzy stretching technique and the Max-Min based average binarization technique to the dog eye images photographed by simple devices such as mobile phones. After applying the FCM algorithm in quantization, we apply the brightness average binarization method in the quantized region. The two binarization images - Max-Min basis and brightness average binarization - are ANDed, and small noises are removed to extract the final cataract suspicious areas. In the experiment with 45 dog eye images with canine cataract, the proposed method shows better performance in correct extraction rate than the ART2 based method.

반려견의 백내장은 노화와 함께 자연스럽게 발병하며 적시에 치료하지 못하면 수술을 해야 하거나 실명이 될 수도 있다. 따라서 본 논문에서는 기존의 ART2 기반 반려견 백내장 추출 방법의 단점을 개선하기 위해서 FCM(Fuzzy C_Means) 알고리즘을 이용하여 백내장 의심 영역을 자동 추출하는 방법을 제안한다. 제안된 방법은 핸드폰 등 간편하게 촬영된 반려견의 안구 영상에 퍼지 스트레칭 기법과 Max-Min 기반 평균 이진화 기법을 적용하여 후보 영역을 이진화한다. 그리고 FCM 알고리즘을 적용하여 양자화한 후에 양자화 된 영역에서 밝기 평균 이진화 기법을 적용한다. 이 두 방법으로 이진화된 영상 (Max-Min 기반과 밝기 평균 이진화)을 AND로 연산한 후 잡음을 제거하여 백내장 의심 영역으로 추출한다. 기존의 ART2 방식의 백내장 추출 방법과 제안된 백내장 추출 방법을 45개의 백내장 영상을 대상으로 실험한 결과, 제안된 방법이 기존의 백내장 추출 방법보다 백내장 추출률이 개선된 것을 확인하였다.

Keywords

HOJBC0_2018_v22n11_1428_f0001.png 이미지

Fig. 1 Fuzzy Membership Function for Stretching

HOJBC0_2018_v22n11_1428_f0002.png 이미지

Fig. 2 The Effect of Fuzzy Stretching

HOJBC0_2018_v22n11_1428_f0003.png 이미지

Fig. 3 FCM Algorithm

HOJBC0_2018_v22n11_1428_f0004.png 이미지

Fig. 4 The Effect of ART2 Quantization

HOJBC0_2018_v22n11_1428_f0005.png 이미지

Fig. 5 The Effect of FCM Quantization

HOJBC0_2018_v22n11_1428_f0006.png 이미지

Fig. 6 Cataract Area Extraction with AND optation of two Binarizations

HOJBC0_2018_v22n11_1428_f0007.png 이미지

Fig. 7 Cataract Analysis by Visualization

HOJBC0_2018_v22n11_1428_f0008.png 이미지

Fig. 8 Software Snapshot for Canine Cataract Extraction

HOJBC0_2018_v22n11_1428_f0009.png 이미지

Fig. 10 Visual Comparison of the Previous[4] and the Proposed Method

HOJBC0_2018_v22n11_1428_f0010.png 이미지

Fig. 9 Cataract Extractions and Normal Eye Cases

Table. 1 Performance Evaluation of Previous ART2 based Method and the Proposd Method in Successful Extraction Rate

HOJBC0_2018_v22n11_1428_t0001.png 이미지

References

  1. K. B. Kim, D. H. Song, and Y. W. Woo, "Machine Intelligence can guide Pet Dog Health Pre-Diagnosis for Casual Owner: A Neural Network Approach," International Journal of Bio-Science and Bio-Technology, vol.6, no.2, pp. 83-90, Aug. 2014. https://doi.org/10.14257/ijbsbt.2014.6.2.08
  2. P. D. S. Raghuvanshi and S. K. Maiti, "Canine cataracts and its management: An overview," Journal of Animal Research, vol.3, no.1, pp.17-26, July 2013.
  3. M. G. Davidson and S. R. Nelms, Diseases of the canine lens and cataract formation. In: Veterinary Ophthalmology, 4th edn. (ed. Gelatt KN) Ames, Blackwell Publishing, pp. 859-887, 2007.
  4. K. B. Kom, "Extraction of Canine Cataract Object for Developing Handy Pre-diagnostic Tool with Fuzzy Stretching and ART2 Learning," International Journal of Fuzzy Logic and Intelligent Systems, vol.16, no.1 pp. 21-26, Mar. 2016. https://doi.org/10.5391/IJFIS.2016.16.1.21
  5. K. B. Kim, "Extracting Ganglion Cysts from Ultrasound Image with Fuzzy Membership Function," Journal of the Korea Institute of Information and Communication Engineering, vol.19, no.6, pp. 1296-1300, Jun. 2015. https://doi.org/10.6109/jkiice.2015.19.6.1296
  6. D. J. Kim, P. L. Manjusha, "Building Detection in High Resolution Remotely Sensed Images based on Automatic Histogram-Based Fuzzy C-Means Algorithm," Asia-pacific Journal of Convergent Research Interchange, HSST, vol.3, no.1, pp. 57-62, Mar. 2017. https://doi.org/10.21742/apjcri.2017.12.11
  7. S. -H. Kim, G. Heo, "Improvement on Density-Independent Clustering Method," Journal of the Korea Institute of Information and Communication Engineering, vol.21 no.5, pp. 967-973, May 2017. https://doi.org/10.6109/JKIICE.2017.21.5.967
  8. K. B. Kim, D. H. Song, "Vision based Crack Identification and Analysis on the Surface of Concrete Slab Structures," Information, vol.18, no.6(A), pp. 2381-2386, Jun. 2015.