Filters








5,050 Hits in 3.6 sec

High-speed structured light scanning system and 3D gestural point cloud recognition

Yin Zhou, Kai Liu, Jinglun Gao, Kenneth E. Barner, Fouad Kiamilev
2013 2013 47th Annual Conference on Information Sciences and Systems (CISS)  
The proposed point cloud recognition approach achieves recognition rates up to 98.0% over the gesture database and 88.2% over the face database in our pilot study.  ...  Finally, utilizing the system, we contribute to the research community two large-scale high-resolution 3D point cloud databases, i.e., SLI 3D Hand Gesture Database and SLI 3D Face Database.  ...  Table 1 : 1 Comparison of recognition rates and time elapse over the SLI 3D Hand Gesture Database. Time elapse (second) represents only the time for classifying one query point cloud.  ... 
doi:10.1109/ciss.2013.6552323 dblp:conf/ciss/ZhouLGBK13 fatcat:b4z6trtd6jbepdtqx2b2riv2sm

Feature Extraction for Facial Expression Recognition based on Ensemble Learning Algorithm

Shang-fu Gong, Juan Chen, Peng-tao Jia
2015 International Journal of Hybrid Information Technology  
In order to extract facial expression feature effectively, this paper puts forward a new way of facial expression feature extraction ensemble learning algorithm based on ensemble thinking.  ...  Experimental results on JAFFE expression database show that this ensemble learning model gets higher recognition rate and better generalization ability than single learning device.  ...  On the other hand, try to reduce the redundant information, speed up the information processing.  ... 
doi:10.14257/ijhit.2015.8.6.06 fatcat:zkphqhha6rflhiiimumhbgp63q

An Improved Brain-Inspired Emotional Learning Algorithm for Fast Classification

Ying Mei, Guanzheng Tan, Zhentao Liu
2017 Algorithms  
However, the traditional ANN shows slow training speed, and it is hard to meet the real-time requirement for large-scale applications.  ...  In this study, we aim to propose a more accurate BEL algorithm for fast classification.  ...  Author Contributions: Ying Mei is responsible for the research work related to brain-inspired emotional learning algorithm, performed all of the simulations and did all of the write-up.  ... 
doi:10.3390/a10020070 fatcat:sh6dqkfzqvdwvgrihacj4uc2tu

Facial Expression Recognition Using Uniform Local Binary Pattern with Improved Firefly Feature Selection

Abdulla Elmadhoun, Md Jan Nordin
2018 ARO. The Scientific Journal of Koya University  
Experimental results using the Japanese female facial expression database show that the proposed approach yielded good classification accuracy compared to state-of-the-art methods.  ...  The great deluge is a local search algorithm that helps to enhance the exploitation ability of the firefly algorithm, thus preventing being trapped in local optima.  ...  up the computations.  ... 
doi:10.14500/aro.10378 fatcat:5ebbv6hr7rbmrgfhnddzoodere

Filipino based Facial Emotion Features Datasets using Haar-Cascade Classifier and Fisherfaces Linear Discriminant Analysis Algorithm

Anna Liza A. Ramos, Paolo A. Buenafe, Evander Keannu C. Cabrales, Jasreel D. Teñido, Shaina O. Portas
2019 Zenodo  
In fact, various studies conducted utilized the available datasets – applying different methodologies and implementing the best suited algorithms to improve the classification performance and increase  ...  In result, the study marked a classification accuracy of 90.66% based on the API outcomes with 150 instances and 83.61 % classification rate for 609 features – it clearly outperformed the results acquired  ...  Bermudez for providing their valued inputs in making this study more relevant.  ... 
doi:10.5281/zenodo.5209549 fatcat:c7s4ahnngfbithw35ji55wmcma

Statistical Evaluation of Face Recognition Techniques under Variable Environmental Constraints

Louis Asiedu, Atinuke O. Adebanji, Francis Oduro, Felix O. Mettle
2015 International Journal of Statistics and Probability  
The Repeated Measures Design, Paired Comparison test, Box's M test and Profile Analysis were used for performance evaluation of the algorithms on the merit of efficiency and consistency in recognizing  ...  So how hard could it be for a computer? It has been established that face recognition is a dedicated process in the brain (Marqueś, 2010).  ...  The time used by algorithm 2 in the whitening process accounts for the differences in the algorithms' runtime (speed).  ... 
doi:10.5539/ijsp.v4n4p93 fatcat:uxfnn6rcq5c7bc5ielssrkylhy

Multimodal Affect Recognition Using Boltzmann Zippers

Kun LU, Xin ZHANG
2013 IEICE transactions on information and systems  
Second-order methods are applied to Boltzmann zippers to speed up learning and pruning process.  ...  This letter presents a novel approach for automatic multimodal affect recognition.  ...  To speed up learning in Boltzmann zippers, the damped Gauss-Newton method [12] is used for training.  ... 
doi:10.1587/transinf.e96.d.2496 fatcat:g4gezv52zveuxpi6fblua274f4

Sparse Representation Classifier Embedding Subspace Mapping and Support Vector for Facial Expression Recognition

Shaoqin Lu, Lei Xue, Xiaoqing Gu, Xin Ning
2021 Wireless Communications and Mobile Computing  
It is one type of commonly used image classification algorithms for FER in recent years.  ...  The solution of SRC-SM-SV uses an alternate iteration method, which makes the optimization process of the algorithm simple and efficient.  ...  By selecting representative training samples, the data can be compressed to reduce the computation scale, thereby speeding up the efficiency of sparse decomposition. Li et al.  ... 
doi:10.1155/2021/9340147 fatcat:vnhvhxieobhw3fmyoqe3plpsui

A smart login system using face detection and recognition by ORB algorithm

Mohammad Jahangir Alam, Tanjia Chowdhury, Md. Shahzahan Ali
2020 Indonesian Journal of Electrical Engineering and Computer Science  
This research has used the Viola and Jones algorithm for face detection and ORB for image matching in face recognition and Java, MySql, OpenCV, and iReport are used for implementation.</p>  ...  Primarily, the device captures the face images and stores the captured images into the specific path of the computer relating the information into a database.  ...  Diverse descriptors average computation time Detector Run time(ms) Speed up() SURF 176 1.9 FAST 2 169 BRISK 10 33.8 ORB 7 48.3 Table 3 . 3 Speed-up over the sequential matching Descriptor  ... 
doi:10.11591/ijeecs.v20.i2.pp1078-1087 fatcat:epk4yu56pvdw5dkqtssrvxtlxy

Facial Expression Identification System Using fisher linear discriminant analysis and K- Nearest Neighbor Methods

2019 Zanco Journal of Pure and Applied Sciences  
Facial Expressions (JAFFE) database.  ...  The system is applied to recognize various basic facial expressions such as happy, neutral, angry, disgust, sad, fear and surprise, in the Karolinska Directed Emotional Faces (KDEF) and Japanese Female  ...  This database is free and available on the Internet for academic and research purposes.  ... 
doi:10.21271/zjpas.31.2.2 fatcat:bauj5ykrdjcvdj4anku47tlnpe

Pulsed Melodic Processing – The Use of Melodies in Affective Computations for Increased Processing Transparency [chapter]

Alexis Kirke, Eduardo Miranda
2013 Music and Human-Computer Interaction  
Pulsed Melodic Processing (PMP) is a computation protocol that utilizes musically-based pulse sets ("melodies") for processing -capable of representing the arousal and valence of affective states.  ...  The key mode was measured using a modified key finding algorithm (Krumhansl and Kessler 1982) which gave a value of 3 for maximally major and -3 for maximally minor.  ...  In these, four representative state-labels are used to represent the four quadrants of the PMP-value table: "Sad" for [-3,0], "Stressed" for [-3,1], "Relaxed" for [3,0], and "Happy" for [3, 1] .  ... 
doi:10.1007/978-1-4471-2990-5_10 fatcat:brdomreuu5bhbo6j3vkx6qsdqa

Recognizing facial action units using independent component analysis and support vector machine

Chao-Fa Chuang, Frank Y. Shih
2006 Pattern Recognition  
In this paper, we focus on recognizing facial action units (AUs), which represent the subtle change of facial expressions.  ...  Furthermore, the proposed system is fast since it takes only 1.8 ms for classifying a test image. ᭧  ...  The advantages are to reduce the dimensionality of the detected faces from the previous stage and to speed up the computation in the next stage.  ... 
doi:10.1016/j.patcog.2006.03.017 fatcat:3wncfk4qdffz5g5saiezccs6ry

Discovering closed frequent itemsets on multicore: Parallelizing computations and optimizing memory accesses

B Negrevergne, A Termier, J Méhaut, T Uno
2010 2010 International Conference on High Performance Computing & Simulation  
In this paper we present PLCMQS, a parallel algorithm based on the LCM algorithm, recognized as the most efficient algorithm for sequential discovery of closed frequent itemsets.  ...  Thanks to a detailed experimental study, we show that PLCMQS is the only algorithm which is generic enough to compute efficiently closed frequent itemsets both on sparse and dense databases, thus improving  ...  Their algorithm scales up very well with the number of cores, with a quasi-linear speed-up on a lot of real-world databases.  ... 
doi:10.1109/hpcs.2010.5547082 dblp:conf/ieeehpcs/NegrevergneTMU10 fatcat:yh2lmtcrhzetbhk5p5e6xmh544

The Possibilities of Classification of Emotional States Based on User Behavioral Characteristics

Martin Magdin, D. Držík, J. Reichel, S Koprda
2020 International Journal of Interactive Multimedia and Artificial Intelligence  
The sample of the reference database consisted of 50 students.  ...  To gather data for the classifier we used an application, the Emotnizer, which we had developed for this purpose.  ...  We designed a classification algorithm for emotional states classification.  ... 
doi:10.9781/ijimai.2020.11.010 fatcat:47znxe6pjzdivnjcwfpzkuwzbu

A Bayesian approach to recognise facial expressions using vector flows

Xiaofan Sun, Leon Rothkrantz, Dragos Datcu, Pascal Wiggers
2009 Proceedings of the International Conference on Computer Systems and Technologies and Workshop for PhD Students in Computing - CompSysTech '09  
The classifier has been trained and tested on video recordings from the Cohn Kanade database. It contains recordings from the six basic emotions as defined by Ekman.  ...  In that database about 70 persons show facial expressions from the 6 basic emotions starting from the neutral position up to the apex, showing the maximal intensity.  ...  This movement can be visualized by a vector field that represents the speed and direction of movements. We used the Lucas Kanade algorithm [6] to compute the vector flow from the video recordings.  ... 
doi:10.1145/1731740.1731772 dblp:conf/compsystech/SunRDW09 fatcat:jlh7ogswb5bhtlg3droeaema5i
« Previous Showing results 1 — 15 out of 5,050 results