19,204 Hits in 4.1 sec

Recognizing Gender from Human Facial Regions using Genetic Algorithm [article]

Avirup Bhattacharyya, Rajkumar Saini, Partha Pratim Roy, Debi Prosad Dogra, Samarjit Kar
2017 arXiv   pre-print
Finally, the classification scores obtained from individual regions are combined with a genetic algorithm based learning to improve the overall classification accuracy.  ...  Recently, recognition of gender from facial images has gained a lot of importance.  ...  The classification scores of individual regions have been combined with genetic algorithm to provide improved performance.  ... 
arXiv:1712.01661v1 fatcat:tnqynnda5fbp7ev3d5cawqkpqq

Speaker State Recognition: Feature Selection Method based on Self-adjusting Multi-criteria Evolutionary Algorithms

Roman Sergienko, Elena Loseva
2016 Proceedings of the 13th International Conference on Informatics in Control, Automation and Robotics  
algorithm and self-adjusting multi-criteria genetic programming.  ...  The proposed approach was compared with different methods for feature selection on four audio corpora for speaker emotion recognition and for speaker gender identification.  ...  It turns out that by using the proposed evolutionary technique we could significantly improve efficiency of the recognition tasks.  ... 
doi:10.5220/0005946801230129 dblp:conf/icinco/SergienkoL16 fatcat:xcu5sczdjbdodjk5o3wtqpmnkq

An Extended Local Binary Pattern for Gender Classification

Abbas Roayaei Ardakany, Mircea Nicolescu, Monica Nicolescu
2013 2013 IEEE International Symposium on Multimedia  
This paper addresses the problem of gender recognition by proposing a new feature descriptor to be used in classification.  ...  recognition accuracy.  ...  genetic algorithms V.  ... 
doi:10.1109/ism.2013.61 dblp:conf/ism/ArdakanyNN13 fatcat:nukjvwaxznathkraxbl4t6pxfi

Automated Recognition of Paralinguistic Signals in Spoken Dialogue Systems: Ways of Improvement

Maxim Sidorov
2015 Journal of Siberian Federal University Mathematics & Physics  
Speaker-or gender-specific information is used either for including into the feature vector directly, or for creating separate emotion recognition models for each gender or speaker.  ...  Secondly, a feature selection procedure is an important part of any classification problem; therefore, we proposed using a feature selection technique, based on a genetic algorithm or an information gain  ...  Speaker State Recognition with Feature Selection Techniques To perform the feature selection-based approach two techniques have been chosen, Information Gain Ratio (IGR) and a Genetic Algorithm (GA).  ... 
doi:10.17516/1997-1397-2015-8-2-208-216 fatcat:d5w7qpag2fbdrk2tfxzgfag6yq

A Classifier Model based on the Features Quantitative Analysis for Facial Expression Recognition

Amir Jamshidnezhad, Md Jan Nordin
2011 International Journal on Advanced Science, Engineering and Information Technology  
Also in this model, fuzzy logic and genetic algorithm are used to classify facial expressions.  ...  Genetic algorithm is an exclusive attribute of proposed model which is used for tuning membership functions and increasing the accuracy.  ...  Therefore, objective in this research is development of facial expression recognition systems using Genetic Algorithm and Fuzzy rule based System (GAFs) in order to reduce the complexity and also performance  ... 
doi:10.18517/ijaseit.1.4.81 fatcat:pwsauhv5abbbdm6eruhxlc4xxi

Face Recognition System Using Genetic Algorithm

Pratibha Sukhija, Sunny Behal, Pritpal Singh
2016 Procedia Computer Science  
However, the recognition process used by the human brain for identifying faces is very challenging. In this paper, a Genetic Algorithm (GA) based approach is proposed for face recognition.  ...  Face recognition is probably the biometric method that is used to identify people mainly from their faces.  ...  The main purpose of research is to improve the recognition rate using the proposed method.  ... 
doi:10.1016/j.procs.2016.05.183 fatcat:ekriunpcsbb4haeerzca5trnni

Gender Detection using Machine Learning Techniques and Delaunay Triangulation

Sarthak Gupta
2015 International Journal of Computer Applications  
Various classification algorithms such as Functional Trees, AdaBoost, J48, and few others are used to gauge the maximum accuracy.  ...  Gender prediction can prove to be a very useful technique in HCI (Human Computer Interaction) Systems.  ...  Zehang Sun et al, [12] proposed Gender classification from frontal face images using genetic feature subset selection.  ... 
doi:10.5120/ijca2015905507 fatcat:vwibtk734zci5i6a4zgtkj3som

Evolutionary eigenvoice MLLR speaker adaptation

Reza Sahraeian, Mehdi Mohammadi, Ahmad Akbari, Ahmad Ayatollahi
2011 Procedia Computer Science  
Experimental results on TIMIT database illustrate that genetic algorithm, using random individuals in first population, leads to up to 1.03% improvement in phoneme recognition rate.  ...  To find the best solution for the coefficients estimation problem, we suggest using genetic algorithm (GA) for rapid speaker adaptation.  ...  Moreover, we try to improve the performance of genetic algorithm by using the coefficients estimated by maximum likelihood in initial population.  ... 
doi:10.1016/j.procs.2010.12.163 fatcat:zyb5dwlx3jbvlpmjaf2hobjsmq

Introduction to the special issue on evolutionary computer vision and image understanding

Gustavo Olague, Stefano Cagnoni, Evelyne Lutton
2006 Pattern Recognition Letters  
We deeply appreciate the promptness, clarity, and useful suggestions that were provided, by Gabriella Sanniti di Baja, Editor-in-Chief for Special Issues of Pattern Recognition Letters, during various  ...  The next three papers use genetic programming to approach object classification and recognition.  ...  In A situated model for sensory-motor coordination in gaze control, de Croon et al. attack the problem of gaze control coordination using a situated model to approach a gender recognition task.  ... 
doi:10.1016/j.patrec.2005.07.013 fatcat:dm4s7rmifraelm755rxsy4ysjm

Privacy-Preserving Human Action Recognition with a Many-Objective Evolutionary Algorithm

Pau Climent-Pérez, Francisco Florez-Revuelta
2022 Sensors  
In this paper, a many-objective evolutionary algorithm (MaOEA) is used in order to maximise action recognition from individuals while concealing (minimising recognition of) gender and age.  ...  Human action recognition (HAR), and in particular, the recognition of activities of daily living (ADLs), can be used for these types of assessment or journaling.  ...  code' (therefore, often also called genetic algorithms, GAs).  ... 
doi:10.3390/s22030764 pmid:35161511 pmcid:PMC8840543 fatcat:jhxsclhwdzcolfku4iyfejzqwi

Gender classification for real-time audience analysis system

Vladimir Khryashchev, Lev Shmaglit, Andrey Shemyakov, Anton Lebedev
2014 Proceedings of 15th Conference of Open Innovations Association FRUCT  
Both training technique of the proposed algorithm and experimental results acquired on a large image dataset are presented. More than 90% accuracy of viewer's gender recognition is achieved.  ...  As reported previously, the proposed system consists of five consecutive stages: face detection, face tracking, gender recognition, age classification and statistics analysis.  ...  Gender recognition, for example, can be used to collect and estimate demographic indicators [5] [6] [7] [8] .  ... 
doi:10.1109/fruct.2014.6872428 dblp:conf/fruct/KhryashchevSSL14 fatcat:qyvmndfnazc57n6yh4zktlkrjm

Brand Marketing Decision Support System Based on Computer Vision and Parallel Computing

Yishu Liu, Jun Li, Rashid A Saeed
2022 Wireless Communications and Mobile Computing  
Then, use parallel computing to optimize the genetic algorithm to improve the running speed of the algorithm.  ...  Parallel genetic algorithms run 1.8 times faster than serial genetic algorithms at the lowest and 9 times faster at the highest.  ...  Parallel genetic algorithm can improve the running speed of the algorithm and save calculation time.  ... 
doi:10.1155/2022/7416106 fatcat:ax2lz6vwyjfqbd3symx5ug6hqq

A methodological study and analysis of machine learning algorithms

Shubham Mathur, Akash Badone
2019 International Journal of Advanced Technology and Engineering Exploration  
Machine leaning algorithms have been used in vast area of research including stock market to medical informatics.  ...  Support vector machine (SVM), decision tree, random forest, K-nearest neighbors (KNN), naïve Bayes and multilayer perceptron (MLP) are widely used algorithms in different area of data classification.  ...  [25] Gender recognition of names based on machine learning algorithm They have studied for the gender recognition of Chinese names. 5 [26] Analysis of machine learning algorithms for gender classification  ... 
doi:10.19101/ijatee.2019.650020 fatcat:z4q4nruzsjcahlplweqip5bt5e

Classification of Fruit Flies by Gender in Images Using Smartphones and the YOLOv4-Tiny Neural Network

Mikhail A. Genaev, Evgenii G. Komyshev, Olga D. Shishkina, Natalya V. Adonyeva, Evgenia K. Karpova, Nataly E. Gruntenko, Lyudmila P. Zakharenko, Vasily S. Koval, Dmitry A. Afonnikov
2022 Mathematics  
In the genetic analysis of flies, a routine task is to determine the offspring size and gender ratio in their populations.  ...  Among the factors that most strongly influencing the accuracy of fly gender recognition, the fly's position on the paper was the most important.  ...  Acknowledgments: Data analysis was performed using the computational resources of the "Bioinformatics" Joint Computational Center of the ICG SB RAS.  ... 
doi:10.3390/math10030295 fatcat:muupyaik3ncmbn4w2x467anp4m

A Tool to Develop Arabic Handwriting Recognition System Using Genetic Approach

2010 Journal of Computer Science  
That system start from preprocessing and segmentation phases that deepened on thinning the image and found the V and H projection profile until recognition phase by genetic algorithm.  ...  Results: The genetic algorithm stand on feature extraction algorithm that defined six feature for each segment beak. The system can be recognized Arabic handwriting with 87% accuracy.  ...  The use of genetic algorithm to recognize a character has been a new algorithm used in this problem.  ... 
doi:10.3844/jcssp.2010.619.624 fatcat:gjzsmj6yizcrzcob2chh7d7ni4
« Previous Showing results 1 — 15 out of 19,204 results