Paper Title : Adaptive Coal Classification Using Centroid Contour Distance Object Recognition Method Using Deep Learing

ISSN : 2394-2231
Year of Publication : 2022

10.5281/zenodo.6406898

Authors: K.E.Eswari M.C.A.,M.E., K.Dhivyapriya

         



MLA Style: Adaptive Coal Classification Using Centroid Contour Distance Object Recognition Method Using Deep Learing " K.E.Eswari M.C.A.,M.E., K.Dhivyapriya " Volume 9 - Issue 2 International Journal of Computer Techniques (IJCT) ,ISSN:2394-2231 , www.ijctjournal.org

APA Style: Adaptive Coal Classification Using Centroid Contour Distance Object Recognition Method Using Deep Learing " K.E.Eswari M.C.A.,M.E., K.Dhivyapriya " Volume 9 - Issue 2 International Journal of Computer Techniques (IJCT) ,ISSN:2394-2231 , www.ijctjournal.org

Abstract
The primary effort in learning coal detail is observing coal features. This project developed a coal classification system which allows researchers to do a search by classification even when they don’t know coal name by simply observing their characteristics. The system consists of coalfeatures, finds the features according to input features, and returns selected clusters. Nowadays, coal classification utilizes machine vision to grab and analyze color, shape, size and surface texture. However, the newly proposed extraction margin method only carries out roughly and there is a difference between the margin of the extracted shape, polygon, and the shape margin of the original image still. This project groups i.e., clusters the coal using image area size, pixel color values similarity, based on image’s brightness values and coal shapes. In addition, the study aims in finding the gangue in coal. Based on the pixels count of gangue colors, total gangue percent in the coal is calculated and displayed. This assists in evaluating coal quality. If future, researchers were to expand to other features, coal gangue quantity, etc., even those that are hard to quantify, can also be quantified. ANN is used to classify the coal dataset

Reference
[1] Guo Y, WangX, Wang S, Hu K, Wang W. (2021).“Identificationmethodof coal and coal ganguebased on dielectriccharacteristics,”IEEE Access.,vol. 9, pp. 9845- 9854,Jan. 2021 [2] K.E.Eswari, P.Sivanandham “Enhancement of market data partitioning scalability and high diamentionality management using Deep Learning“, Ïnternational Journal of Computer Techniques“, Vol 8 March 2021. [3] ZhaohuiZheng,Ping Wang,Wei Liu, Jinze Li, RongguangYe,DongweiRen. “Distance-IoULoss: Fasterand BetterLearning for Bounding Box Regression,” Presentedat AAAIConference on Artificial Intelligence 2020. [Online].Available:https://ojs.aaai.org//index.php/AAAI/art icle/view/6999. [3] Gao, Mingyu, et al. “Adaptive anchor box mechanism to improve the accuracy in the object detection system,” Multimedia Tools and Applications., vol. 78, no. 19, pp. 27383-27402, Oct. 2019. [4] Jain, Anil K. . “Data clustering:50 years beyondKmeans.” PatternRecognitionLetters., vol. 31, no. 8, pp. 651- 666,June. 2010. [5] S. Ren, K. He, R. Girshickand J. Sun, “Faster RCNN:Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence.,vol. 39,no. 6, pp. 1137- 1149,June. 2017. [6] Hou, Wei. Identification of Coal and Gangue by Feedforward Neural Network Based on Data Analysis [J]. International Journal of Coal Preparation and Utilization., vol. 39, no. 1, pp. 33-43, Jan. 2019. [7] Dou, Dongyang; Zhou, Deyang; Yang, Jianguo, et al. Coal and gangue recognition under four operating conditions by using image analysis and Relief-SVM [J]. International Journal of Coal Preparation and Utilization., vol. 40, no. 7, pp.473-482, Jul. 2020. [8] Li, Man; Duan, Yong; He, Xianli, et al. Image positioning and identification method and system for coal and gangue sorting robot [J]. International Journal of Coal Preparation and Utilization., May. 2020. DOI.10.1080/19392699.2020.1760855. [9] Jian Song. “Research on Identification Algorithm of Coal and Gangue Based on Image Feature,” M.S. thesis, Dept. Computer science and technology., Hebei University of Engineering., Hebei, China, 2016. [10] Xianmin Ma, Xiaoru ng. “Coal Gangues Automation Selection System Based on ARM Core and CAN Bus, ”Chinese Journal of Scientific Instrument.,vol. 26, no. 8, pp. 305-307, 318, August.2005. [11] Hailing Zhang, Jialin Wang, Jiansheng Wu, Rong Shi. “Application of Rough Sets Theory to Image Enhancement Processing,” Journal of Tongji University (Natural Science)., vol. 36, no. 2, pp. 254-257, Feb. 2008. [12] Wanzhi Wang, Zengcai Wang. “Characteristic Analysis and Recognition of Coal and Rock Based on Visual Technology,” Coal Technology., vol. 33, no. 10, pp. 272-274,Oct. 2014. [13] Yunxia Wu, Yimin Tian. “Methodof coal-rock image feature extraction and recognition based on dictionary learning,” Journal of China Coal Society., vol. 41, no. 12, pp. 3190-3196, Dec. 2016. [14 ] J. Redmon, S. Divvala,R. Girshickand A. Farhadi, “You only look once: Unified real-time object detection,” in Proc. CVPR, Las Vegas, NV, United States, 2016, pp. 779-788. [15] Ping Huo, Hanlin Zeng, KeyanHuo. “Research on density identification system of coal and refuse based on image processing technology, ”Goal Preparation Technology., no. 2, pp. 69-73, Apr.2015. [16] Guo Y, Wang, X, Wang S, Hu K, Wang W. (2021).“Identification method of coal and coal gangue based on dielectric characteristics,” IEEE Access., vol. 9, pp. 9845-9854,Jan. 2021. [17] Xijie Dou, Shibo Wang, Yang Xie, Tong Xuan. “Coal and gangue identification based on IMF energy moment and SVM, ” Journal of Vibration and Shock, vol. 39, no. 24, pp. 39-45, Dec. 2020. [18] Wei Hou. “Identification of Coal and Gangue by Feed-forward Neural Network Based on Data Analysis,” International Journal of Coal Preparation and Utilization, vol. 39, no. 1, pp.33-43, Jan. 2019

Keywords
— Coal Classification, Centroid Contour, Deep Learning, Object Recognition.