Abstract
Depending on the prevailing researches, the classification of face shapes could be deployed for numerous applications. This paper intends to develop a new method for face shape classification using intelligent approaches. The presented method includes three stages namely, (i) Face Detection (ii) Pre-processing (iii) Feature extraction (iv) Classification. The face detection process is used for identifying the most significant objects in the face, probably eyes, nose, etc. which is done using the Viola-Jones algorithm. Moreover, the pre-processing stage includes the Histogram Equalization (HE) model for enhancing the contrast of the image. The classification of face shapes is performed by a hybrid classifier that links Convolutional Neural Network (CNN) and Neural Network (NN). For performing the CNN-based classification, the images are directly given as input. On the other hand, NN-based classification requires features as input. Hence, the pre-processed image is again subjected to the feature extraction process, where the features are extracted using the Active Appearance Model (AAM) and the Active Shape Model (ASM). For reducing the length of extracted features, the optimal feature selection process is adopted, which is done by improved Grey Wolf Optimization (GWO) algorithm. As the main contribution, the features, number of hidden neurons in the convolutional layer of CNN, and training of NN (weight update) is optimally chosen by improved GWO so-called as Fitness Sorted Grey Wolf Update (FS-GU) model. Finally, the average of two outcomes from both CNN, and NN provides the classified five categories of face shapes like heart, oblong, oval, round, and square. The performance of the proposed classification model is finally validated by comparing over the conventional models by analyzing the relevant performance metrics.
Similar content being viewed by others
Abbreviations
- 3D :
-
3-Dimensional
- HE:
-
Histogram Equalization
- CNN:
-
Convolutional Neural Network
- AAM:
-
Active Appearance Model
- ASM:
-
Active Shape Model
- NN:
-
Neural Network
- GWO:
-
Grey Wolf Optimization
- FS-GU:
-
Fitness Sorted Grey Wolf Update
- SVM:
-
Support Vector Machines
- PCA:
-
Principle Component Analysis
- MKL:
-
Multiple Kernel Learning
- VC:
-
Vector Concatenation
- MRI:
-
Magnetic Resonance Imaging
- ECG:
-
Electroencephalography
- DBN:
-
Dynamic Bayesian Network
- PLS:
-
Partial Least Squares
- bvFTD:
-
Behavioural Variant Of Fronto-Temporal Dementia
- AP:
-
Affinity Propagation
- LR:
-
Linear Regression
- MLP:
-
Multilayer Perceptron
- NPV:
-
Net Present Value
- MCC:
-
Matthews Correlation Coefficient
- FPR:
-
False Positive Rate
- FNR:
-
False Negative Rate
- FDR:
-
False Discovery Rate
- GA:
-
Genetic Algorithm
- CDF:
-
Cumulative Distribution Function
- PSO:
-
Particle Swarm Optimization
- FF:
-
FireFly
- WOA:
-
Whale Optimization Algorithm
References
Benini S, Khan K, Leonardi R, Mauro M, Migliorati P (May 2019) Face analysis through semantic face segmentation. Signal Process Image Commun 74:21–31
Bicego M, Lovato P (April 2016) A bioinformatics approach to 2D shape classification. Comput Vis Image Underst 145:59–69
Bouchaffra D (Aug. 2012) Mapping dynamic Bayesian networks to α shapes: application to human faces identification across ages. IEEE Trans Neural Netw Learning Syst 23(8):1229–1241
de Mesquita Sá Junior JJ, Backes AR, Bruno OM (2018) Randomized neural network based descriptors for shape classification. Neurocomputing 312:201–209
de Paulo Carlos G, Pedrini H, Schwartz WR (October 2015) Classification schemes based on Partial Least Squares for face identification. J Vis Commun Image Represent 32:170–179
De Winter F-L, Timmers D, de Gelder B, Van Orshoven M, Van den Stock J (2016) Face shape and face identity processing in behavioral variant fronto-temporal dementia: a specific deficit for familiarity and name recognition of famous faces. NeuroImage: Clinical 11:368–377
Edwards GJ, Cootes TF, Taylor CJ (1998) Face recognition using active appearance models. Wolfson Image Analysis Unit
Fister I, Fister I, Yang X-S, Brest J (December 2013) A comprehensive review of firefly algorithms. Swarm and Evolutionary Computation 13:34–46
Heisel S, Ernst J, Emshoff A, Schembecker G, Wohlgemuth K (1 March 2019) Shape-independent particle classification for discrimination of single crystals and agglomerates. Powder Technol 345:425–437
Huang B, Wu J, Zhang D, Li N (2010) Tongue shape classification by geometric features. Inf Sci 180(2):312–324
Jarrett K, Kavukcuogl K, Ranzato M, LeCun Y (2009) What is the best multi-stage architecture for object recognition? In Computer Vision, International Conference on, pages 2146–2153
Kapil Juneja (2017) MPMFFT based DCA-DBT integrated probabilistic model for face expression classification. Journal of King Saud University - Computer and Information Sciences, in press, corrected proof. Available online 25 October.
Kashiwaya K, Noumachi T, Hiroyoshi N, Ito M, Tsunekawa M (August 2012) Effect of particle shape on hydrocyclone classification. Powder Technol 226:147–156
LeCun Y, Kavukvuoglu K, Farabet C (2010) Convolutional networks and applications in vision. In Circuits and Systems, International Symposium on:253–256
Lee S, Charon N, Charlier B, Popuri K (January 2017) Mirza Faisal Beg, “atlas-based shape analysis and classification of retinal optical coherence tomography images using the functional shape (fshape) framework”. Med Image Anal 35:570–581
Lv C, Wu Z, Wang X, Zhou M, Toh K-A (April 2019) Nasal similarity measure of 3D faces based on curve shape space. Pattern Recogn 88:458–469
McCall J (2005) Genetic algorithms for modelling and optimisation. J Comput Appl Math 184(1):205–222
Jian-Xun Mi, Zhiheng Luo, Li-Fang Zhou, Fujin Zhong, (2018) Bilateral structure based matrix regression classification for face recognition. Neurocomputing, In press, corrected proof. Available online 5 November 2018.
Mirjalili S, Lewis A (May 2016) The whale optimization algorithm. Adv Eng Softw 95:51–67
Mirjalili S, Mirjalili SM, Lewis A (2014) Grey wolf optimizer. Adv Eng Softw 69:46–61
Nemrodov D, Behrmann M, Niemeier M, Drobotenko N, Nestor A (January 2019) Multimodal evidence on shape and surface information in individual face processing. NeuroImage 1:813–825
Ninu Preetha NS, Brammya G, Ramya R, Praveena S, Binu D, Rajakumar BR (2018) Grey wolf optimisation-based feature selection and classification for facial emotion recognition. IET Biometrics 7(5):490–499. https://doi.org/10.1049/iet-bmt.2017.0160
Pasupa K, Sunhem W, Loo CK (15 April 2019) MA hybrid approach to building face shape classifier for hairstyle recommender system. Expert Syst Appl 120:14–32
Petpairote C, Madarasmi S, Chamnongthai K (2018) Personalised-face neutralisation using best-matched face shape with a neutral-face database. IET Comput Vis 12(3):252–260
Ravi RV, Subramaniam K (2020) Image compression using optimized wavelet filter derived from grey wolf algorithm. J Ambient Intell Humaniz Comput:1–12
Roshini TV, Ravi RV, Reema Mathew A, Kadan AB, Subbian PS (2020) Automatic diagnosis of diabetic retinopathy with the aid of adaptive average filtering with optimized deep convolutional neural network. Int J Imaging Syst Technol 30:1173–1193
Sánchez-Escobedo D, Castelán M, Smith WAP (January 2016) Statistical 3D face shape estimation from occluding contours. Comput Vis Image Underst 142:111–124
Sohn I (2019) A robust complex network generation method based on neural networks. Physica A: Statistical Mechanics and its Applications 523:593–601
Song M, Sun Z, Liu K, Lang X (May 2015) Iterative 3D shape classification by online metric learning. Computer Aided Geometric Design 35–36:192–205
Song M, Sun Z, Li H (January 2017) Accumulative categorization: online 3D shape classification for progressive collections. Graph Model 89:14–27
H. Takahashi, M. Komatsu, H. Kim, J. K. Tan, S. Ishikawa and A. Yamamoto (2010) Segmentation method for cardiac region in CT images based on active shape model. ICCAS 2010, Gyeonggi-do, pp. 2074-2077.
Tarel JP, Hautiere N (2009) Fast visibility restoration from a single color or gray level image. IEEE International Conference on Computer Vision
Vinolin V (April 2019) Breast cancer detection by optimal classification using GWO algorithm. 2(2)
Wagh MB, Gomathi N (2018) Water wave optimization-based routing protocol for vehicular adhoc networks. International Journal of Modeling, Simulation, and Scientific Computing 9(05):1850047
Wang H, Zhang H, Ray N (July 2012) Clump splitting via bottleneck detection and shape classification. Pattern Recogn 45(7):2780–2787
Wilamowska K, Wu J, Heike C, Shapiro L (2012) Shape-based classification of 3D facial data to support 22q11.2DS craniofacial research. J Digit Imaging 25:400–408
Xia B, Amor BB, Drira H, Daoudi M, Ballihi L (March 2015) Combining face averageness and symmetry for 3D-based gender classification. Pattern Recogn 48(3):746–758
Zhang J, Xia P (17 February 2017) An improved PSO algorithm for parameter identification of nonlinear dynamic hysteretic models. J Sound Vib 389:153–167
Zhao L, Bentin S (2011) The role of features and configural processing in face-race classification. Vis Res 51(23–24):2462–2470
Zhu R, Zhu L, Dong-nan L (December 2015) Study of color heritage image enhancement algorithms based on histogram equalization. Optik 126(24):5665–5667
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Sukumaran, A., Brindha, T. Optimal feature selection with hybrid classification for automatic face shape classification using fitness sorted Grey wolf update. Multimed Tools Appl 80, 25689–25710 (2021). https://doi.org/10.1007/s11042-021-10710-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-10710-9