skip to main content
10.1145/3321707.3321748acmconferencesArticle/Chapter ViewAbstractPublication PagesgeccoConference Proceedingsconference-collections
research-article

Using a genetic algorithm with histogram-based feature selection in hyperspectral image classification

Published: 13 July 2019 Publication History

Abstract

Optical sensing has the potential to be an important tool in the automated monitoring of food quality. Specifically, hyperspectral imaging has enjoyed success in a variety of tasks ranging from plant species classification to ripeness evaluation in produce. Although effective, hyperspectral imaging is prohibitively expensive to deploy at scale in a retail setting. With this in mind, we develop a method to assist in designing a low-cost multispectral imager for produce monitoring by using a genetic algorithm (GA) that simultaneously selects a subset of informative wavelengths and identifies effective filter bandwidths for such an imager. Instead of selecting the single fittest member of the final population as our solution, we fit a univariate Gaussian mixture model to the histogram of the overall GA population, selecting the wavelengths associated with the peaks of the distributions as our solution. By evaluating the entire population, rather than a single solution, we are also able to specify filter bandwidths by calculating the standard deviations of the Gaussian distributions and computing the full-width at half-maximum values. In our experiments, we find that this novel histogram-based method for feature selection is effective when compared to both the standard GA and partial least squares discriminant analysis.

References

[1]
Judith A Abbott. 1999. Quality measurement of fruits and vegetables. Postharvest biology and technology 15, 3 (1999), 207--225.
[2]
Elfatih M Abdel-Rahman, Fethi B Ahmed, and Riyad Ismail. 2013. Random forest regression and spectral band selection for estimating sugarcane leaf nitrogen concentration using EO-1 Hyperion hyperspectral data. International Journal of Remote Sensing 34, 2 (2013), 712--728.
[3]
Sebastian Bach, Alexander Binder, Grégoire Montavon, Frederick Klauschen, Klaus-Robert Müller, and Wojciech Samek. 2015. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS one 10, 7 (2015).
[4]
Douglas F Barbin, Da-Wen Sun, and Chao Su. 2013. NIR hyperspectral imaging as non-destructive evaluation tool for the recognition of fresh and frozen-thawed porcine longissimus dorsi muscles. Innovative Food Science & Emerging Technologies 18 (2013), 226--236.
[5]
Matthew Barker and William Rayens. 2003. Partial least squares for discrimination. Journal of Chemometrics: A Journal of the Chemometrics Society 17, 3 (2003), 166--173.
[6]
Marion F. Baumgardner, Larry L. Biehl, and David A. Landgrebe. 2015. 220 Band AVIRIS Hyperspectral Image Data Set: June 12, 1992 Indian Pine Test Site 3. https://purr.purdue.edu/publications/1947/1. (Sep 2015).
[7]
Johannes Brauers, Nils Schulte, and Til Aach. 2008. Multispectral filter-wheel cameras: Geometric distortion model and compensation algorithms. IEEE transactions on image processing 17, 12 (2008), 2368--2380.
[8]
Leo Breiman. 2001. Random forests. Machine learning 45, 1 (2001), 5--32.
[9]
Jean C Buzby, Hodan Farah-Wells, and Jeffrey Hyman. 2014. The estimated amount, value, and calories of postharvest food losses at the retail and consumer levels in the United States. USDA-ERS Economic Information Bulletin 121 (2014).
[10]
Jonathan Cheung-Wai Chan and Desiré Paelinckx. 2008. Evaluation of Random Forest and Adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery. Remote Sensing of Environment 112, 6 (2008), 2999--3011.
[11]
Jun-Hu Cheng, Da-Wen Sun, and Hongbin Pu. 2016. Combining the genetic algorithm and successive projection algorithm for the selection of feature wavelengths to evaluate exudative characteristics in frozen-thawed fish muscle. Food chemistry 197 (2016), 855--863.
[12]
William HE Day and Herbert Edelsbrunner. 1984. Efficient algorithms for agglomerative hierarchical clustering methods. Journal of classification 1, 1 (1984), 7--24.
[13]
Jie Feng, Licheng Jiao, Fang Liu, Tao Sun, and Xiangrong Zhang. 2016. Unsupervised feature selection based on maximum information and minimum redundancy for hyperspectral images. Pattern Recognition 51 (2016), 295--309.
[14]
Yao-Ze Feng, Gamal ElMasry, Da-Wen Sun, Amalia GM Scannell, Des Walsh, and Noha Morcy. 2013. Near-infrared hyperspectral imaging and partial least squares regression for rapid and reagentless determination of Enterobacteriaceae on chicken fillets. Food Chemistry 138, 2--3 (2013), 1829--1836.
[15]
TM Gajanana, D Sreenivasa Murthy, and M Sudha. 2011. Post harvest losses in fruits and vegetables in South India-A review of concepts and quantification of losses. Indian Food Packer 65 (2011), 178--187.
[16]
AA Gowen, CPo O'Donnell, PJ Cullen, G Downey, and JM Frias. 2007. Hyperspectral imaging-an emerging process analytical tool for food quality and safety control. Trends in food science & technology 18, 12 (2007), 590--598.
[17]
John Henry Holland. 1992. Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. MIT press.
[18]
Adel A Kader. 2004. Increasing food availability by reducing postharvest losses of fresh produce. In International Postharvest Symposium 682. 2169--2176.
[19]
Mohammed Kamruzzaman, Gamal ElMasry, Da-Wen Sun, and Paul Allen. 2012. Non-destructive prediction and visualization of chemical composition in lamb meat using NIR hyperspectral imaging and multivariate regression. Innovative Food Science & Emerging Technologies 16 (2012), 218--226.
[20]
Shijin Li, Hao Wu, Dingsheng Wan, and Jiali Zhu. 2011. An effective feature selection method for hyperspectral image classification based on genetic algorithm and support vector machine. Knowledge-Based Systems 24, 1 (2011), 40--48.
[21]
Renfu Lu. 2004. Multispectral imaging for predicting firmness and soluble solids content of apple fruit. Postharvest Biology and Technology 31, 2 (2004), 147--157.
[22]
Michael W Mahoney and Petros Drineas. 2009. CUR matrix decompositions for improved data analysis. Proceedings of the National Academy of Sciences (2009), 697--702.
[23]
Kezhi Z Mao. 2004. Orthogonal forward selection and backward elimination algorithms for feature subset selection. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 34, 1 (2004), 629--634.
[24]
Scott A Mathews. 2008. Design and fabrication of a low-cost, multispectral imaging system. Applied optics 47, 28 (2008), F71--F76.
[25]
Seyyid Ahmed Medjahed and Mohammed Ouali. 2018. Band selection based on optimization approach for hyperspectral image classification. The Egyptian Journal of Remote Sensing and Space Science (2018).
[26]
Mostafa Moradkhani, Ali Amiri, Mohsen Javaherian, and Hossein Safari. 2015. A hybrid algorithm for feature subset selection in high-dimensional datasets using FICA and IWSSr algorithm. Applied Soft Computing 35 (2015), 123--135.
[27]
Bart M Nicolai, Elmi Lötze, Ann Peirs, Nico Scheerlinck, and Karen I Theron. 2006. Non-destructive measurement of bitter pit in apple fruit using NIR hyperspectral imaging. Postharvest biology and technology 40, 1 (2006), 1--6.
[28]
Gerrit Polder, Gerie WAM van der Heijden, and IT Young. 2002. Spectral image analysis for measuring ripeness of tomatoes. Transactions of the ASAE 45, 4 (2002), 1155.
[29]
J. R. Quinlan. 1986. Induction of decision trees. Machine Learning 1, 1 (1 March 1986), 81--106.
[30]
P Rajkumar, N Wang, G EImasry, GSV Raghavan, and Y Gariepy. 2012. Studies on banana fruit quality and maturity stages using hyperspectral imaging. Journal of Food Engineering 108, 1 (2012), 194--200.
[31]
Amir Salimi, Mansour Ziaii, Ali Amiri, Mahdieh Hosseinjani Zadeh, Sadegh Karimpouli, and Mostafa Moradkhani. 2018. Using a Feature Subset Selection method and Support Vector Machine to address curse of dimensionality and redundancy in Hyperion hyperspectral data classification. The Egyptian Journal of Remote Sensing and Space Science 21, 1 (2018), 27--36.
[32]
Innapa Saranwong, Jinda Sornsrivichai, and Sumio Kawano. 2001. Improvement of PLS calibration for Brix value and dry matter of mango using information from MLR calibration. Journal of Near Infrared Spectroscopy 9, 4 (2001), 287--295.
[33]
S Serranti, G Bonifazi, V Luciani, and L D'Aniello. 2017. Classification of Peronospora infected grapevine leaves with the use of hyperspectral imaging analysis. In Sensing for Agriculture and Food Quality and Safety IX, Vol. 10217. International Society for Optics and Photonics.
[34]
George Themelis, Jung Sun Yoo, and Vasilis Ntziachristos. 2008. Multispectral imaging using multiple-bandpass filters. Optics letters 33, 9 (2008), 1023--1025.
[35]
Di Wu and Da-Wen Sun. 2013. Advanced applications of hyperspectral imaging technology for food quality and safety analysis and assessment: A Review Part I: Fundamentals. Innovative Food Science & Emerging Technologies 19 (2013), 1--14.
[36]
Jihoon Yang and Vasant Honavar. 1998. Feature subset selection using a genetic algorithm. In Feature extraction, construction and selection. Springer, 117--136.
[37]
Mohammed J Zaki, Wagner Meira Jr, and Wagner Meira. 2014. Data mining and analysis: fundamental concepts and algorithms. Cambridge University Press.
[38]
Li Zhuo, Jing Zheng, Xia Li, Fang Wang, Bin Ai, and Junping Qian. 2008. A genetic algorithm based wrapper feature selection method for classification of hyperspectral images using support vector machine. In Geoinformatics 2008 and Joint Conference on GIS and Built Environment: Classification of Remote Sensing Images, Vol. 7147. International Society for Optics and Photonics.

Cited By

View all
  • (2025)How to Evaluate and Remove the Weakened Bands in Hyperspectral Image ClassificationIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2025.352691763(1-15)Online publication date: 2025
  • (2024)CANNIBAL Unveils the Hidden Gems: Hyperspectral Band Selection via Clustering of Weighted Variable Interaction GraphsProceedings of the Genetic and Evolutionary Computation Conference10.1145/3638529.3654203(412-421)Online publication date: 14-Jul-2024
  • (2023)Object Classification Using ECOC Multi-class SVM and HOG CharacteristicsIntelligent Systems Design and Applications10.1007/978-3-031-27440-4_3(23-33)Online publication date: 31-May-2023
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
GECCO '19: Proceedings of the Genetic and Evolutionary Computation Conference
July 2019
1545 pages
ISBN:9781450361118
DOI:10.1145/3321707
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 13 July 2019

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. feature selection
  2. genetic algorithm
  3. histogram
  4. hyperspectral imaging
  5. produce monitoring

Qualifiers

  • Research-article

Conference

GECCO '19
Sponsor:
GECCO '19: Genetic and Evolutionary Computation Conference
July 13 - 17, 2019
Prague, Czech Republic

Acceptance Rates

Overall Acceptance Rate 1,669 of 4,410 submissions, 38%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)13
  • Downloads (Last 6 weeks)2
Reflects downloads up to 10 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2025)How to Evaluate and Remove the Weakened Bands in Hyperspectral Image ClassificationIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2025.352691763(1-15)Online publication date: 2025
  • (2024)CANNIBAL Unveils the Hidden Gems: Hyperspectral Band Selection via Clustering of Weighted Variable Interaction GraphsProceedings of the Genetic and Evolutionary Computation Conference10.1145/3638529.3654203(412-421)Online publication date: 14-Jul-2024
  • (2023)Object Classification Using ECOC Multi-class SVM and HOG CharacteristicsIntelligent Systems Design and Applications10.1007/978-3-031-27440-4_3(23-33)Online publication date: 31-May-2023
  • (2022)Incorporating Lévy Flight to Distribution-Based Discrete Particle Swarm Optimization確率分布に基づく離散粒子群最適化におけるLévy flight の導入Journal of Japan Society for Fuzzy Theory and Intelligent Informatics10.3156/jsoft.34.1_51134:1(511-521)Online publication date: 15-Feb-2022
  • (2021)Hyperspectral Dimensionality Reduction Based on Inter-Band Redundancy Analysis and Greedy Spectral SelectionRemote Sensing10.3390/rs1318364913:18(3649)Online publication date: 13-Sep-2021
  • (2021)Hyperspectral Band Selection for Multispectral Image Classification with Convolutional Networks2021 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN52387.2021.9533700(1-8)Online publication date: 2021
  • (2020)FASTENER Feature Selection for Inference from Earth Observation DataEntropy10.3390/e2211119822:11(1198)Online publication date: 23-Oct-2020
  • (2020)Binary biogeography-based optimization based SVM-RFE for feature selectionApplied Soft Computing10.1016/j.asoc.2020.107026(107026)Online publication date: Dec-2020

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media