Bi-layer deep feature fusion based mineral classification using hand-specimen images

被引:0
|
作者
Behera, Santi Kumari [1 ]
Rao, Mannava Srinivasa [2 ]
Amat, Rajat [3 ]
Sethy, Prabira Kumar [4 ,5 ]
机构
[1] VSSUT Burla, Dept Comp Sci & Engn, Sambalpur, India
[2] PVP Siddhartha Inst Technol, Dept Elect & Commun Engn, Vijayawada, Andhra Pradesh, India
[3] Sambalpur Univ, Dept Elect & Commun Engn, SUIIT, Sambalpur, Odisha, India
[4] Sambalpur Univ, Dept Elect, Sambalpur, Odisha, India
[5] Guru Ghasidas Vishwavidyalaya, Dept Elect & Commun Engn, Bilapur, CG, India
关键词
Mineral identification; deep learning; bi-layer feature fusion; deep feature; IDENTIFICATION;
D O I
10.3233/JIFS-221987
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Mineral classification is a crucial task for geologists. Minerals are identified by their characteristics. In the field, geologists can identify minerals by examining lustre, color, streak, hardness, crystal habit, cleavage, fracture, and specific features. Geologists sometimes use a magnifying hand lens to identify minerals in the field. Surface color can assist in identifying minerals. However, it varies widely, even within a single mineral family. Some minerals predominantly show a single color. So, identifying minerals is possible considering surface color and texture. But, again, a limited database of minerals is available with large-scale images. So, the challenges arise to identify the minerals using their images with limited images. With the advancement of machine learning, the deep learning approach with bi-layer feature fusion enhances the dimension of the feature vector with the possibility of high accuracy. Here, an experimental analysis is reported with three possibilities of bi-layer feature fusion of three CNN models like Alexnet, VGG16 & VGG19, and a framework is suggested. Alexnet delivers the highest performance with the bi-layer fusion of fc6 and fc7. The achieved accuracy is 84.23%, sensitivity 84.23%, specificity 97.37%, precision 84.7%, FPR 2.63%, F1 Score 84.17%, MCC 81.75%, and Kappa 53.59%.
引用
收藏
页码:6969 / 6976
页数:8
相关论文
共 50 条
  • [1] Bi-Layer Behavioral-Based Feature Selection Approach for Network Intrusion Classification
    Eid, Heba F.
    Salama, Mostafa A.
    Hassanien, Aboul Ella
    Kim, Tai-hoon
    SECURITY TECHNOLOGY, 2011, 259 : 195 - +
  • [2] Learning Deep Feature Fusion for Group Images Classification
    Zhao, Wenting
    Wang, Yunhong
    Chen, Xunxun
    Tang, Yuanyan
    Liu, Qingjie
    COMPUTER VISION, PT II, 2017, 772 : 566 - 576
  • [3] Automatic Bi-Layer Video Segmentation Based on Sensor Fusion
    Wu, Qiong
    Boulanger, Pierre
    Bischof, Walter F.
    19TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1-6, 2008, : 1654 - 1657
  • [4] Automatic Recognition of Ripening Tomatoes by Combining Multi-Feature Fusion with a Bi-Layer Classification Strategy for Harvesting Robots
    Wu, Jingui
    Zhang, Baohua
    Zhou, Jun
    Xiong, Yingjun
    Gu, Baoxing
    Yang, Xiaolong
    SENSORS, 2019, 19 (03)
  • [5] Deep manifold feature fusion for classification of breast histopathology images
    Wang, Pin
    Li, Pufei
    Li, Yongming
    Xu, Jin
    Yan, Fang
    Jiang, Mingfeng
    DIGITAL SIGNAL PROCESSING, 2022, 123
  • [6] Identification of Complaint Microblogs based on Multimodal and Bi-layer Fusion Framework
    Chen, Feng
    Zhang, Yunjiao
    Xu, Yanhua
    2022 5TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND NATURAL LANGUAGE PROCESSING, MLNLP 2022, 2022, : 266 - 270
  • [7] Human Gender Classification Based on Hand Images Using Deep Learning
    Mukherjee, Rajesh
    Bera, Asish
    Bhattacharjee, Debotosh
    Nasipuri, Mita
    Communications in Computer and Information Science, 2022, 1695 CCIS : 314 - 324
  • [8] A bi-layer model for identification of piwiRNA using deep neural learning
    Adnan, Adnan
    Wang, Hongya
    Ali, Farman
    Khalid, Majdi
    Alghushairy, Omar
    Alsini, Raed
    JOURNAL OF BIOMOLECULAR STRUCTURE & DYNAMICS, 2023,
  • [9] A bi-layer model for identification of piwiRNA using deep neural learning
    Adnan, Adnan
    Hongya, Wang
    Ali, Farman
    Khalid, Majdi
    Alghushairy, Omar
    Alsini, Raed
    JOURNAL OF BIOMOLECULAR STRUCTURE & DYNAMICS, 2024, 42 (11): : 5725 - 5733
  • [10] Deep Feature Extraction and Feature Fusion for Bi-Temporal Satellite Image Classification
    Asokan, Anju
    Anitha, J.
    Patrut, Bogdan
    Danciulescu, Dana
    Hemanth, D. Jude
    CMC-COMPUTERS MATERIALS & CONTINUA, 2021, 66 (01): : 373 - 388