MCNN+: Gemstone Image Classification Algorithm with Deep Multi-feature Fusion CNNs
by Haoyuan Huang 1 
, Rongcheng Cui* 2 
1 College of Jewelry, Shanghai Jian Qiao University, Shanghai, 201306, China
2 School of Computer Science and Technology, Shanghai University of Electric Power, Shanghai, 201306, China
* Author to whom correspondence should be addressed.
Journal of Engineering Research and Sciences, Volume 3, Issue 8, Page # 15-20, 2024; DOI: 10.55708/js0308002
Keywords: CNN, Multi-features, Image Classification, Gemstone, Data Fusion
Received: 14 May 2024, Revised: 18 July 2024, Accepted: 19 July 2024, Published Online: 01 August 2024
APA Style
Huang, H., & Cui, R. (2024). MCNN+: Gemstone image classification algorithm with deep multi-feature fusion CNNs. Journal of Engineering Research and Sciences, 3(8), 15-20. https://doi.org/10.55708/js0308002
Chicago/Turabian Style
Huang, Haoyuan, and Rongcheng Cui. “MCNN+: Gemstone Image Classification Algorithm with Deep Multi-feature Fusion CNNs.” Journal of Engineering Research and Sciences 3, no. 8 (2024): 15-20. https://doi.org/10.55708/js0308002.
IEEE Style
H. Huang and R. Cui, “MCNN+: Gemstone Image Classification Algorithm with Deep Multi-feature Fusion CNNs,” Journal of Engineering Research and Sciences, vol. 3, no. 8, pp. 15-20, 2024, doi: 10.55708/js0308002.
Accurate gemstone classification is critical to the gemstone and jewelry industry, and the good performance of convolutional neural networks in image processing has received wide attention in recent years. In order to better extract image content information and improve image classification accuracy, a CNNs gemstone image classification algorithm based on deep multi-feature fusion is proposed. The algorithm effectively deeply integrates a variety of features of the image, namely the main color features extracted by the k-means++ clustering algorithm and the spatial position features extracted by the denoising convolutional neural network. Experimental results show that the proposed method provides competitive results in gemstone image classification, and the classification accuracy is nearly 9% higher than that of CNN. By deeply integrating multiple features of the image, the algorithm can provide more comprehensive and significant useful information for subsequent image processing.
- D. Bersani, P. P. Lottici, “Applications of raman spectroscopy to gemol- ogy”, Analytical and bioanalytical chemistry, vol. 397, pp. 2631–2646, 2010, doi:10.1007/s00216-010-3700-1.
- J. E. Shigley, “A review of current challenges for the identification of gemstones”, Geologija, , no. 64, 2008, doi:10.2478/v10056-008-0048-8.
- L. Alzubaidi, J. Zhang, A. J. Humaidi, A. Al-Dujaili, Y. Duan, O. Al- Shamma, J. Santamaría, M. A. Fadhel, M. Al-Amidie, L. Farhan, “Review of deep learning: concepts, cnn architectures, challenges, applications, future directions”, Journal of big Data, vol. 8, pp. 1–74, 2021, doi:10.1186/s40537-021-00444-8.
- T. Kattenborn, J. Leitloff, F. Schiefer, S. Hinz, “Review on convolu- tional neural networks (cnn) in vegetation remote sensing”, ISPRS journal of photogrammetry and remote sensing, vol. 173, pp. 24–49, 2021, doi:10.1016/j.isprsjprs.2020.12.010.
- H. Gupta, K. H. Jin, H. Q. Nguyen, M. T. McCann, M. Unser, “Cnn- based projected gradient descent for consistent ct image reconstruc- tion”, IEEE transactions on medical imaging, vol. 37, no. 6, pp. 1440–1453, 2018, doi:10.1109/TMI.2018.2832656.
- H. Lee, H. Kwon, “Going deeper with contextual cnn for hyperspectral image classification”, IEEE Transactions on Image Processing, vol. 26, no. 10, pp. 4843–4855, 2017, doi:10.1109/TIP.2017.2725580.
- I. Maula, V. Amrizal, A. H. Setianingrum, N. Hakiem, “Develop- ment of a gemstone type identification system based on hsv space colour using an artificial neural network back propagation algorithm”, “International Conference on Science and Technology (ICOSAT 2017)- Promoting Sustainable Agriculture, Food Security, Energy, and En- vironment Through Science and Technology for Development”, pp. 104–109, Atlantis Press, 2017, doi:10.2991/icosat-17.2018.24.
- A. Ostreika, M. Pivoras, A. Misevičius, T. Skersys, L. Paulauskas, “Clas- sification of objects by shape applied to amber gemstone classification”, Applied Sciences, vol. 11, no. 3, p. 1024, 2021, doi:10.3390/app11031024.
- A. Ostreika, M. Pivoras, A. Misevičius, T. Skersys, L. Paulauskas, “Classification of amber gemstone objects by shape”, 2020, doi:10.20944/preprints202008.0336.v1.
- R. S. Castro Rios, “Researching of the deep neural network for amber gemstone classification”, Master’s thesis, Universitat Politècnica de Catalunya, 2018.
- S. Sinkevičius, A. Lipnickas, K. Rimkus, “Multiclass amber gemstones classification with various segmentation and committee strategies”, “2013 IEEE 7th International Conference on Intelligent Data Acqui- sition and Advanced Computing Systems (IDAACS)”, vol. 1, pp. 304–308, IEEE, 2013, doi:10.1109/IDAACS.2013.6662694.
- X. Liu, J. Mao, “Research on key technology of diamond particle detection based on machine vision”, “MATEC Web of Conferences”, vol. 232, p. 02059, EDP Sciences, 2018, doi:10.1051/matecconf/201823202059.
- B. H. Y. Chow, C. C. Reyes-Aldasoro, “Automatic gemstone classifi- cation using computer vision”, Minerals, vol. 12, no. 1, p. 60, 2021, doi:10.3390/min12010060.
- K. Hurrell, M. L. Johnson, Gemstones: a complete color reference for precious and semiprecious stones of the world, Chartwell Books, 2016.
- C. M. Breeding, A. H. Shen, S. Eaton-Magaña, G. R. Rossman, J. E. Shigley, A. Gilbertson, “Developments in gemstone analysis tech- niques and instrumentation during the 2000s.”, Gems & Gemology, vol. 46, no. 3, 2010.
- R. Liddicoat, “Developing the powers of observation in gem testing”, Gems Gemol, vol. 10, pp. 291–319, 1962.
- E. Fritsch, C. M. Stockton, “Infrared spectroscopy in gem identifica- tion”, Gems & gemology, vol. 23, no. 1, pp. 18–26, 1987.
- A. L. Jenkins, R. A. Larsen, “Gemstone identification using raman spectroscopy”, disclosure, vol. 7, p. 9, 2004.
- L. Kiefert, S. Karampelas, “Use of the raman spectrometer in gemmological laboratories”, Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, vol. 80, no. 1, pp. 119–124, 2011, doi:10.1016/j.saa.2011.03.004.
- T. He, “The applications of ultraviolet visible absorption spectrum detection technology in gemstone identification”, “Proceedings of the 5th International Conference on Materials Engineering for Advanced Technologies (ICMEAT 2016), Quebec, QC, Canada”, pp. 5–6, 2016.
- S. Thompson, F. Fueten, D. Bockus, “Mineral identification using artificial neural networks and the rotating polarizer stage”, Computers & Geosciences, vol. 27, no. 9, pp. 1081–1089, 2001, doi:10.1016/S0098- 3004(00)00153-9.
- N. A. Baykan, N. Yılmaz, “Mineral identification using color spaces and artificial neural networks”, Computers & Geosciences, vol. 36, no. 1, pp. 91–97, 2010, doi:10.1016/j.cageo.2009.04.009.
- H. Izadi, J. Sadri, M. Bayati, “An intelligent system for mineral identi- fication in thin sections based on a cascade approach”, Computers & Geosciences, vol. 99, pp. 37–49, 2017, doi:10.1016/j.cageo.2016.10.010.
- H. Pereira Borges, M. S. de Aguiar, “Mineral classification using machine learning and images of microscopic rock thin section”, “Advances in Soft Computing: 18th Mexican International Confer- ence on Artificial Intelligence, MICAI 2019, Xalapa, Mexico, October 27–November 2, 2019, Proceedings 18”, pp. 63–76, Springer, 2019, doi:10.1007/978-3-030-33749-0_6.
- J. Maitre, K. Bouchard, L. P. Bédard, “Mineral grains recognition using computer vision and machine learning”, Computers & Geosciences, vol. 130, pp. 84–93, 2019, doi:10.1016/j.cageo.2019.05.009.
- Y. Zhang, M. Li, S. Han, Q. Ren, J. Shi, “Intelligent identifi- cation for rock-mineral microscopic images using ensemble ma- chine learning algorithms”, Sensors, vol. 19, no. 18, p. 3914, 2019, doi:10.3390/s19183914.
- K. Muthukaruppan, S. Thirugnanam, R. Nagarajan, M. Rizon, S. Yaa- cob, M. Muthukumaran, T. Ramachandran, “A comparison of south east asian face emotion classification based on optimized ellipse data using clustering technique”, Journal of Image and Graphics, vol. 3, no. 1, 2015, doi:https://doi.org/10.18178/joig.3.1.1-5.
- Y. Karayaneva, D. Hintea, “Object recognition in python and mnist dataset modification and recognition with five machine learning classifiers”, Journal of Image and Graphics, vol. 6, no. 1, pp. 10–20, 2018.
- L. Wang, B. Liu, S. Xu, J. Pan, Q. Zhou, “Ai auxiliary labeling and clas- sification of breast ultrasound images”, Journal of Image and Graphics, vol. 9, no. 2, pp. 45–49, 2021.
- N. M. Trieu, N. T. Thinh, “A study of combining knn and ann for classifying dragon fruits automatically”, Journal of Image and Graphics, vol. 10, no. 1, pp. 28–35, 2022.
- J. Gu, Z. Wang, J. Kuen, L. Ma, A. Shahroudy, B. Shuai, T. Liu,
X. Wang, G. Wang, J. Cai, et al., “Recent advances in convolutional neural networks”, Pattern recognition, vol. 77, pp. 354–377, 2018, doi:10.1016/j.patcog.2017.10.013. - Y. Chen, C. Li, P. Ghamisi, X. Jia, Y. Gu, “Deep fusion of re- mote sensing data for accurate classification”, IEEE Geoscience and Remote Sensing Letters, vol. 14, no. 8, pp. 1253–1257, 2017, doi:10.1109/LGRS.2017.2704625.
- R. Kiran, P. Kumar, B. Bhasker, “Dnnrec: A novel deep learning based hybrid recommender system”, Expert Systems with Applications, vol. 144, p. 113054, 2020, doi:10.1016/j.eswa.2019.113054.
- X. Peng, X. Zhang, Y. Li, B. Liu, “Research on image feature extraction and retrieval algorithms based on convolutional neural network”, Journal of Visual Communication and Image Representation, vol. 69, p. 102705, 2020, doi:10.1016/j.jvcir.2019.102705.
- D. Arthur, S. Vassilvitskii, “k-means++: The advantages of careful seeding”, Tech. rep., Stanford, 2006.
- Y. Bengio, A. Courville, P. Vincent, “Representation learning: A review and new perspectives”, IEEE transactions on pattern anal- ysis and machine intelligence, vol. 35, no. 8, pp. 1798–1828, 2013, doi:10.1109/TPAMI.2013.50.
- D. Steinkraus, I. Buck, P. Y. Simard, “Using gpus for machine learn- ing algorithms”, “Eighth International Conference on Document Analysis and Recognition (ICDAR’05)”, pp. 1115–1120, IEEE, 2005, doi:10.1109/ICDAR.2005.251.
- “Gemstone images”, https://www.kaggle.com/lsind18/ gemstone-images.
