Eye Statement Recognition for Driver Fatigue Detection Based on Gabor Wavelet and HMM

2011 ◽  
Vol 128-129 ◽  
pp. 123-129
Author(s):  
Hai Yan Yang ◽  
Xin Hua Jiang ◽  
Lei Wang ◽  
Yong Hui Zhang
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Good Accuracy ◽  
Hidden Markov ◽  
Detection Algorithm ◽  
Gabor Wavelet ◽  
Recognition Method ◽  
Driver Fatigue ◽  
Gabor Features ◽  
Fatigue Detection

Eye statement is one of the most important factors reflecting driver fatigue. A novel eye statement recognition method for driver fatigue detection based on Gabor transformation and Hidden Markov Model is proposed in this paper, in which, the eye detection algorithm is borrowed from Zafer Savas' TrackEye software, and Gabor features, i.e. the eye state features, of the eye are extracted by using Gabor wavelet. After that, by using these features, the classifier is trained by HMM (Hidden Markov Model) to distinguish the eye states including fatigue and alert, then the consecutive five frames are considered to judge whether there exists driver fatigue or not. Simulation results show that the new method has good accuracy and effectiveness.

scholarly journals A novel seizure detection algorithm informed by hidden Markov model event states

2016 ◽  
Vol 13 (3) ◽  
pp. 036011 ◽  
Author(s):  
Steven Baldassano ◽  
Drausin Wulsin ◽  
Hoameng Ung ◽  
Tyler Blevins ◽  
Mesha-Gay Brown ◽  
...  
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Seizure Detection ◽  
Detection Algorithm

scholarly journals A Fusion Recognition Method Based on Multifeature Hidden Markov Model for Dynamic Hand Gesture

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Guoliang Chen ◽  
Kaikai Ge
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Calculation Model ◽  
Opening Angle ◽  
Hand Gesture ◽  
Leap Motion ◽  
Recognition Method ◽  
Hand Gestures ◽  
Multiple Features

In this paper, a fusion method based on multiple features and hidden Markov model (HMM) is proposed for recognizing dynamic hand gestures corresponding to an operator’s instructions in robot teleoperation. In the first place, a valid dynamic hand gesture from continuously obtained data according to the velocity of the moving hand needs to be separated. Secondly, a feature set is introduced for dynamic hand gesture expression, which includes four sorts of features: palm posture, bending angle, the opening angle of the fingers, and gesture trajectory. Finally, HMM classifiers based on these features are built, and a weighted calculation model fusing the probabilities of four sorts of features is presented. The proposed method is evaluated by recognizing dynamic hand gestures acquired by leap motion (LM), and it reaches recognition rates of about 90.63% for LM-Gesture3D dataset created by the paper and 93.3% for Letter-gesture dataset, respectively.

Combinatorial Detection Algorithm for Copy Number Variations Using High-throughput Sequencing Reads

2019 ◽  
Vol 33 (14) ◽  
pp. 1950022
Author(s):  
Hai Yang ◽  
Daming Zhu
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
High Throughput ◽  
Copy Number ◽  
High Throughput Sequencing ◽  
Hidden Markov ◽  
Read Depth ◽  
Detection Algorithm ◽  
Gc Bias ◽  
Unmapped Reads

Copy number variation (CNV) is a prevalent kind of genetic structural variation which leads to an abnormal number of copies of large genomic regions, such as gain or loss of DNA segments larger than 1[Formula: see text]kb. CNV exists not only in human genome but also in plant genome. Current researches have testified that CNV is associated with many complex diseases. In this paper, guanine-cytosine (GC) bias, mappability and their effect on read depth signals in sequencing data are discussed first. Subsequently, a new correction method for GC bias and an improved combinatorial detection algorithm for CNV using high-throughput sequencing reads based on hidden Markov model (CNV-HMM) are proposed. The corrected read depth signals have lower correlation with GC content, mappability of reads and the width of analysis window. Then we create a hidden Markov model which maps the reads onto the reference genome and records the unmapped reads. The unmapped reads are counted and normalized. The CNV-HMM detects the abnormal signal of read count and gains the candidate CNVs using the expectation maximization (EM) algorithm. Finally, we filter the candidate CNVs using split reads to promote the performance of our algorithm. The experiment result indicates that the CNV-HMM algorithm has higher accuracy and sensitivity for CNVs detection than most current detection algorithms.

Recognition of Offline Handwritten Chinese Characters of Amount in Words Based on Integrated Features and HMM

2012 ◽  
Vol 263-266 ◽  
pp. 2639-2642
Author(s):  
Cai Feng Liu ◽  
Xue Dong Tian ◽  
Fang Yang
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Recognition Rate ◽  
Experimental Results ◽  
Chinese Characters ◽  
Recognition Method ◽  
Voting Rule

A recognition method of offline handwritten Chinese characters of amount in words is presented. The method uses elastic mesh strategy to divide character images written by special men into meshes, and extracts directional element and key point features in every mesh to produce a vector. Based on independent Hidden Markov Model classifiers, this paper uses voting rule to integrate the Hidden Markov Model classifiers. The experimental results show that this method has a relative high recognition rate.

scholarly journals High Performance Human Face Recognition using Gabor Based Pseudo Hidden Markov Model

2013 ◽  
Vol 4 (1) ◽  
pp. 81-102 ◽  
Author(s):  
Arindam Kar ◽  
Debotosh Bhattacharjee ◽  
Mita Nasipuri ◽  
Dipak Kumar Basu ◽  
Mahantapas Kundu
Keyword(s):  
Face Recognition ◽  
Markov Model ◽  
Hidden Markov Model ◽  
High Performance ◽  
Hidden Markov ◽  
Gabor Wavelet ◽  
Data Set ◽  
Scanning Method ◽  
Face Images ◽  
Gabor Wavelet Transformation

This paper introduces a novel methodology that combines the multi-resolution feature of the Gabor wavelet transformation (GWT) with the local interactions of the facial structures expressed through the Pseudo Hidden Markov Model (PHMM). Unlike the traditional zigzag scanning method for feature extraction a continuous scanning method from top-left corner to right then top-down and right to left and so on until right-bottom of the image i.e., a spiral scanning technique has been proposed for better feature selection. Unlike traditional HMMs, the proposed PHMM does not perform the state conditional independence of the visible observation sequence assumption. This is achieved via the concept of local structures introduced by the PHMM used to extract facial bands and automatically select the most informative features of a face image. Thus, the long-range dependency problem inherent to traditional HMMs has been drastically reduced. Again with the use of most informative pixels rather than the whole image makes the proposed method reasonably faster for face recognition. This method has been successfully tested on frontal face images from the ORL, FRAV2D, and FERET face databases where the images vary in pose, illumination, expression, and scale. The FERET data set contains 2200 frontal face images of 200 subjects, while the FRAV2D data set consists of 1100 images of 100 subjects and the full ORL database is considered. The results reported in this application are far better than the recent and most referred systems.

State recognition method for machining process of a large spot welder based on improved genetic algorithm and hidden Markov model

2016 ◽  
Vol 231 (11) ◽  
pp. 2135-2146 ◽  
Author(s):  
Bing Wang ◽  
Ping Yan ◽  
Qiang Zhou ◽  
Libing Feng
Keyword(s):  
Genetic Algorithm ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Machining Process ◽  
Adaptive Genetic Algorithm ◽  
Improved Genetic Algorithm ◽  
Recognition Method ◽  
State Recognition ◽  
Model Recognition

Large spot welder is an important equipment in rail transit equipment manufacturing industry, but having the problem of low utilization rate and low effectlvely machining rate. State monitoring can master its operating states real time and comprehensively, and providing data support for state recognition. Hidden Markov model is a state classification method, but it is sensitive to the initial model parameters and easy to trap into a local optima. Genetic algorithm is a global searching method; however, it is quite poor at hill climbing and also has the problem of premature convergence. In this paper, proposing the improved genetic algorithm, and combining improved genetic algorithm and hidden Markov model, a new method of state recognition method named improved genetic algorithm–hidden Markov model is proposed. In the proposed method, improved genetic algorithm is used for optimizing the initial parameters, and hidden Markov model as a classifier to recognize the operating states for machining process. This method is also compared with the other two recognition methods named adaptive genetic algorithm–hidden Markov model and hidden Markov model, in which adaptive genetic algorithm is similarly used for optimizing the initial parameters, however hidden Markov model (in both methods) as a classifier. Experimental results show that the proposed method is very effective, and the improved genetic algorithm–hidden Markov model recognition method is superior to the adaptive genetic algorithm–hidden Markov model and hidden Markov model recognition method.

Sign in / Sign up

Export Citation Format

Share Document