[논문]자동 암종 분류를 위한 딥러닝 영상처리 기법의 적용성 검토 연구

추엔 팜; 신휴성

doi:10.7474/tus.2020.30.5.462

[국내논문] 자동 암종 분류를 위한 딥러닝 영상처리 기법의 적용성 검토 연구
A Feasibility Study on Application of a Deep Convolutional Neural Network for Automatic Rock Type Classification 원문보기

터널과 지하공간: 한국암반공학회지 = Tunnel and underground space, v.30 no.5, 2020년, pp.462 - 472

추엔 팜 (한국과학기술연합대학원대학교 지반신공간공학과) , 신휴성 (한국건설기술연구원)

초록
AI-Helper

암종 분류은 현장의 지질학적 또는 지반공학적 특성 파악을 위해 요구되는 매우 기본적인 행위이나 암석의 성인, 지역, 지질학적 이력 특성에 따라 동일 암종이라 하여도 매우 다양한 형태와 색 조성을 보이므로 깊은 지질학적 학식과 경험 없이는 쉬운 일은 아니다. 또한, 다른 여러 분야의 분류 작업에서 딥러닝 영상 처리 기법들이 성공적으로 적용되고 있으며, 지질학적 분류나 평가 분야에서도 딥러닝 기법의 적용에 대한 관심이 증대되고 있다. 따라서, 본 연구에서는 동일 암종임에도 다양한 형태와 색을 갖게 되는 실제 상황을 감안하여, 정확한 자동 암종 분류를 위한 딥러닝 기법의 적용 가능성에 대해 검토하였다. 이러한 기법은 향후에 현장 암종분류 작업을 수행하는 현장 기술자들을 지원할 수 있는 효과적인 툴로 활용 가능할 것이다. 본 연구에서 사용된 딥러닝 알고리즘은 매우 깊은 네트워크 구조로 객체 인식과 분류를 할 수 있는 것으로 잘 알려진 'ResNet' 계열의 딥러닝 알고리즘을 사용하였다. 적용된 딥러닝에서는 10개의 암종에 대한 다양한 암석 이미지들을 학습시켰으며, 학습 시키지 않은 암석 이미지들에 대하여 84% 수준 이상의 암종 분류 정확도를 보였다. 본 결과로 부터 다양한 성인과 지질학적 이력을 갖는 다양한 형태와 색의 암석들도 지질 전문가 수준으로 분류해 낼 수 있는 것으로 파악되었다. 나아가 다양한 지역과 현장에서 수집된 암석의 이미지와 지질학자들의 분류 결과가 학습데이터로 지속적으로 누적이 되어 재학습에 반영된다면 암종분류 성능은 자동으로 향상될 것이다.

Abstract ▼ AI-Helper

Rock classification is fundamental discipline of exploring geological and geotechnical features in a site, which, however, may not be easy works because of high diversity of rock shape and color according to its origin, geological history and so on. With the great success of convolutional neural networks (CNN) in many different image-based classification tasks, there has been increasing interest in taking advantage of CNN to classify geological material. In this study, a feasibility of the deep CNN is investigated for automatically and accurately identifying rock types, focusing on the condition of various shapes and colors even in the same rock type. It can be further developed to a mobile application for assisting geologist in classifying rocks in fieldwork. The structure of CNN model used in this study is based on a deep residual neural network (ResNet), which is an ultra-deep CNN using in object detection and classification. The proposed CNN was trained on 10 typical rock types with an overall accuracy of 84% on the test set. The result demonstrates that the proposed approach is not only able to classify rock type using images, but also represents an improvement as taking highly diverse rock image dataset as input.

Keyword

표/그림 (10)

그림 Fig. 1. Examples of the data used in this study
그림 Fig. 2. Example of data augumentation on granite rock image
그림 Fig. 3. Skip connection: (a) Identity block, (b) Convolutional block
그림 Fig. 4. ResNet-50 architecture
그림 Fig. 5. Learning curve: (a) loss and (b) overall accuracy
그림 Fig. 6. Example of test results
표 Table 1. Test result using the best weights of the model
그림 Fig. 7. Example of feature maps in the 1^st convolution layer
그림 Fig. 8. Example of feature maps in the 30^th layer
그림 Fig. 9. Confusion matrix: (a) on validation set and (b) on test set

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

제안 방법

In this study, on the basis of recent breakthrough in Deep CNN we generate a deep learning based classification processes that assist geologist in identifying rock type more efficiently and accurately by using rock images taking during geological survey and also provide a helpful tool for student and junior geologists in practicing rock type classification. Usually, rock samples are collected during field survey, which is then analyzed at laboratory for lithological classification.
In other words, the images were collected without any standardizations, which may result in the lower overall accuracy but the higher generalization ability of the network comparing to other works. To train and evaluate the model, we randomly split the dataset into portions of 70%, 20% and 10% for training, validation and test set, respectively. The validation set is crucial for tuning model’s hyperparameters as giving an idea of how the model behaves on unseen samples during the training process.
One of the most straightforward ways to check the accuracy of the model is to measure how many correct guesses it obtained on the test set. Test result shows that the model can get an overall accuracy of 84% across 116 trials.

대상 데이터

The dataset is composed of more than 1000 images in 10 different classes of rock. Each class contains roughly 100 RGB images with different size, which are then resized to 256 × 256 × 3 pixels for model input (Fig.
The model was trained for 200 epochs with batch size of 16 and 32. Our experiments show that batch size of 16 produces the better result on generalization performance, which is consistent with previous work (LeCun et al.

이론/모형

The model used in this study is inspired by ResNet-50. The major breakthrough with ResNet is that it allows us to train an extremely deep neural networks (150 or more layers) successfully (Ng, 2019).

성능/효과

001 and will then decrease by factor of 10 after epochs of 80, 120 and 150. Although the model is trained with 200 epochs, the best weights of model monitored by lowest validation loss and highest validation accuracy can be saved regardless of which epoch the best model was obtained. This ensures that if the best model was achieved in whichever epoch 150, 175, or even 100, that particular weights of model will be saved and further tested with the test set.
5. The model achieves its best performance at 140^th epoch with the overall accuracy of approximately 85% on validation set. We can see that both the training and validation loss starts to converge after more or less 150 epochs.
One of the most straightforward ways to check the accuracy of the model is to measure how many correct guesses it obtained on the test set. Test result shows that the model can get an overall accuracy of 84% across 116 trials. Besides, other evaluation metrics for classifier model including precision, recall and F1-score are also used to assess the performance of model.
For the diorite, gabbro and gneiss rock, classification test result is slightly lower than the others. Regarding gabbro rock, the precision and recall obtained by the model are 77% and 71%, respectively, which means that 77% of rocks that were classified as gabbro are actually gabbro and the remains 23% were mistaken for gabbro rock; also 71% of all gabbro rock in test set were correctly classified, i.e., 10 images out of 14 test images. Several prediction examples and predicted probability are shown in Fig.
In this study, we have shown that CNN can be successfully applied to classify rock types using images with the overall accuracy of 84% across 116 trials of test set. Additionally, this CNN model perform well on images with different background and also with some interferences such as coin, scale bar or text overlap on the rock.

참고문헌 (18)

Anderson, Don L., 1996, Petrology: The Study of Igneous, Sedimentary and Metamorphic Rocks, American Scientist, 84, 398+.
Andrew, Ng., 2019, Machine Learning course.
Baykan, N.A. and Yilmaz N., 2010, Mineral identification using color spaces and artificial neural networks, Computers and Geosciences, 36, 91-97.

상세보기
Chatterjee, S., 2013, Vision-based rock-type classification of limestone using multi-class support vector machine, Appl. Intell, 39, 14-27.

상세보기
Chatterjee, S., Bhattacherjee, A., Samanta, B. and Pal, S.K., 2008, Rock-type classification of an iron ore deposit using digital image analysis technique, Int. J. Min. Miner. Eng, 1, 22.
Forman, G. and Scholz, M., 2010, Apples-to-apples in cross-validation studies: Pitfalls in classifier performance measurement, ACM Sigkdd Explor. Newsl, 12, 49-57.

상세보기
Guo, C. and Liu, Y., 2014, Recognition of rock images based on multiple color spaces, Sci. Technol. Eng, 14, 247-251 and 255.
He, K., Zhang, X., Ren, S., and Sun, J., 2015, Deep residual learning for image recognition, arXiv preprint arXiv: 1512.03385.
Jiang, Y., 2017, Detecting Geological Structures in Seismic Volumes Using Deep Convolutional Neural Networks, Master Thesis.
LeCun, Y., Bottou, L., Orr, G.B. and Muller, K.R., 1998, Efficient BackProp. In: Orr G.B., Muller KR. (eds) Neural Networks: Tricks of the Trade, Lecture Notes in Computer Science, 1524.
Patel, A.K., Chatterjee, S., Gorai, A.K., 2017, Development of online machine vision system using support vector regression (SVR) algorithm for grade prediction of iron ores, 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA). IEEE, 149-152.
Patel, A.K., Gorai, A.K., Chatterjee, S., 2016, Development of Machine Vision-based System for Iron Ore Grade Prediction using Gaussian Process Regression (GPR), Pattern Recognit. Inf. Process, 45-48.
Pires de Lima, R., Bonar, A., Coronado, D.D., Marfurt, K., and Nicholson, C, 2019, Deep convolutional neural networks as a geological image classification tool, The Sedimentary Record, 17(2), 4-9.
Ran, X., Xue, L., Zhang, Y., Liu, Z., Sang, X. and He, X., 2019, Rock Classification from Field Image Patches Analyzed Using a Deep Convolutional Neural Network, Mathematics, 7, 755.

상세보기
Shu, L., McIsaac, K., Osinski, G.R. and Francis, R., 2017, Unsupervised feature learning for autonomous rock image classification, Computers and Geosciences, 106, 10-17.

상세보기
Wang, C., Li, Y., Fan, G., Chen, F., and Wang, W., 2018, Quick recognition of rock images for mobile applications, J. Eng. Sci. Technol. Rev, 11, 111-117.

상세보기
Zhang, Y., Li, M. and Han, S., 2018, Automatic identification and classification in lithology based on deep learning in rock images, Acta Petrol. Sin, 34, 333-342.
Zhang, Y., Li, M., Han, S., Ren, Q., and Shi, J., 2019, Intelligent Identification for Rock-Mineral Microscopic Images Using Ensemble Machine Learning Algorithms, Sensors (Basel, Switzerland), 19(18), 3914.

상세보기

저자의 다른 논문 :

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증