A Comprehensive Study on the Recognition of Gurmukhi Script

2020 ◽  
Vol 17 (6) ◽  
pp. 2674-2677
Author(s):  
Sandhya Sharma ◽  
Sheifali Gupta ◽  
Neeraj Kumar
Keyword(s):  
Nearest Neighbor ◽  
Text Recognition ◽  
Support Vector ◽  
Svm Classifier ◽  
Mlp Neural Network ◽  
The People ◽  
Linear Svm ◽  
Gurmukhi Script ◽  
Exchange Data ◽  
Comprehensive Study

Nowadays, we process all the important information of our lives electronically. Due to the involvement of computers in every sphere there may be a need to develop some efficient and fast techniques so that records can be easily transferred between people and computer systems. Offline text recognition provides an interface between humans and computers. Many researchers are working to recognize the text of Indian scripts like Bangla, Devanagari, Gurmukhi etc. but it is still a challenge to exchange data between people and computers due to the different writing style of the people and very little work has been done for Gurmukhi. In this article different accuracy results are reviewed which are achieved by different researchers using different classification techniques. Various classifiers for the recognition of characters like Support Vector Machine (SVM) based classifier (Upper zone classifier and Lower zone classifier), Hidden Markov Model (HMM) by using a set of features of the normalized x–y traces of the stroke, DCT2 feature set using Linear SVM classifier, Polynomial SVM with iDCT2 features, Multi layered perceptron (MLP) neural network and Knearest neighbor (KNN) etc. classifiers have been used.

Gaits Classification of Normal vs. Patients by Wireless Gait Sensor and Support Vector Machine (SVM) Classifier

2017 ◽  
Vol 5 (1) ◽  
pp. 17-29 ◽  
Author(s):  
Taro Nakano ◽  
B.T. Nukala ◽  
J. Tsay ◽  
Steven Zupancic ◽  
Amanda Rodriguez ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Real Time ◽  
Human Subjects ◽  
Wearable Sensors ◽  
Normal Subjects ◽  
Support Vector ◽  
Svm Classifier ◽  
Time Dynamic ◽  
Linear Svm ◽  
Dynamic Gait

Due to the serious concerns of fall risks for patients with balance disorders, it is desirable to be able to objectively identify these patients in real-time dynamic gait testing using inexpensive wearable sensors. In this work, the authors took a total of 49 gait tests from 7 human subjects (3 normal subjects and 4 patients), where each person performed 7 Dynamic Gait Index (DGI) tests by wearing a wireless gait sensor on the T4 thoracic vertebra. The raw gait data is wirelessly transmitted to a near-by PC for real-time gait data collection. To objectively identify the patients from the gait data, the authors used 4 different types of Support Vector Machine (SVM) classifiers based on the 6 features extracted from the raw gait data: Linear SVM, Quadratic SVM, Cubic SVM, and Gaussian SVM. The Linear SVM, Quadratic SVM and Cubic SVM all achieved impressive 98% classification accuracy, with 95.2% sensitivity and 100% specificity in this work. However, the Gaussian SVM classifier only achieved 87.8% accuracy, 71.7% sensitivity, and 100% specificity. The results obtained with this small number of human subjects indicates that in the near future, the authors should be able to objectively identify balance-disorder patients from normal subjects during real-time dynamic gaits testing using intelligent SVM classifiers.

scholarly journals Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel

2003 ◽  
Vol 15 (7) ◽  
pp. 1667-1689 ◽  
Author(s):  
S. Sathiya Keerthi ◽  
Chih-Jen Lin
Keyword(s):  
Support Vector Machines ◽  
Model Selection ◽  
Heuristic Method ◽  
Gaussian Kernel ◽  
Support Vector ◽  
Svm Classifier ◽  
Vector Machines ◽  
Rbf Kernel ◽  
Linear Svm ◽  
Generalization Errors

Support vector machines (SVMs) with the gaussian (RBF) kernel have been popular for practical use. Model selection in this class of SVMs involves two hyper parameters: the penalty parameter C and the kernel width σ. This letter analyzes the behavior of the SVM classifier when these hyper parameters take very small or very large values. Our results help in understanding the hyperparameter space that leads to an efficient heuristic method of searching for hyperparameter values with small generalization errors. The analysis also indicates that if complete model selection using the gaussian kernel has been conducted, there is no need to consider linear SVM.

scholarly journals SSVEP-based brain-computer interface for computer control application using SVM classifier

2018 ◽  
Vol 7 (4) ◽  
pp. 2722
Author(s):  
Raymond Sutjiadi ◽  
Timothy John Pattiasina ◽  
Resmana Lim
Keyword(s):  
Brain Computer Interface ◽  
Computer Control ◽  
Occipital Lobe ◽  
Ease Of Use ◽  
Computer Interface ◽  
Support Vector ◽  
Svm Classifier ◽  
Linear Svm ◽  
Control Application ◽  
The Brain

In this research, a Brain Computer Interface (BCI) based on Steady State Visually Evoked Potential (SSVEP) for computer control applications using Support Vector Machine (SVM) is presented. For many years, people have speculated that electroencephalographic activities or other electrophysiological measures of brain function might provide a new non-muscular channel that can be used for sending messages or commands to the external world. BCI is a fast-growing emergent technology in which researchers aim to build a direct channel between the human brain and the computer. BCI systems provide a new communication channel for disabled people. Among many different types of the BCI systems, the SSVEP based has attracted more attention due to its ease of use and signal processing. SSVEPs are usually detected from the occipital lobe of the brain when the subject is looking at a twinkling light source. In this paper, SVM is used to classify SSVEP based on electroencephalogram data with proper features. Based on the experiment utilizing a 14-channel Electroencephalography (EEG) device, 80 percent of accuracy can be reached by our SSVEP-based BCI system using Linear SVM Kernel as classification engine. 

BASIC HANDWRITTEN CHARACTER RECOGNITION FROM MULTI-LINGUAL IMAGE DATASET USING MULTI-RESOLUTION AND MULTI-DIRECTIONAL TRANSFORM

2012 ◽  
Vol 10 (05) ◽  
pp. 1250046 ◽  
Author(s):  
SHITALA PRASAD ◽  
GYANENDRA K. VERMA ◽  
BHUPESH KUMAR SINGH ◽  
PIYUSH KUMAR
Keyword(s):  
Character Recognition ◽  
Nearest Neighbor ◽  
Morphological Alteration ◽  
Support Vector ◽  
Svm Classifier ◽  
K Nearest Neighbor ◽  
Novel Approach ◽  
Pros And Cons ◽  
Resolution Algorithm ◽  
Level Fusion

This paper, proposes a novel approach for feature extraction based on the segmentation and morphological alteration of handwritten multi-lingual characters. We explored multi-resolution and multi-directional transforms such as wavelet, curvelet and ridgelet transform to extract classifying features of handwritten multi-lingual images. Evaluating the pros and cons of each multi-resolution algorithm has been discussed and resolved that Curvelet-based features extraction is most promising for multi-lingual character recognition. We have also applied some morphological operation such as thinning and thickening then feature level fusion is performed in order to create robust feature vector for classification. The classification is performed with K-nearest neighbor (K-NN) and support vector machine (SVM) classifier with their relative performance. We experiment with our in-house dataset, compiled in our lab by more than 50 personnel.

scholarly journals Video Data Extraction and Processing for Investigation of Vehicles’ Impact on the Asphalt Deformation Through the Prism of Computational Algorithms

2020 ◽  
Vol 37 (6) ◽  
pp. 899-906
Author(s):  
Sabahudin Vrtagić ◽  
Edis Softić ◽  
Mirza Ponjavić ◽  
Željko Stević ◽  
Marko Subotić ◽  
...  
Keyword(s):  
Traffic Accidents ◽  
Data Extraction ◽  
Video Data ◽  
Digital Data ◽  
Vehicle Classification ◽  
Support Vector ◽  
Svm Classifier ◽  
Small Data ◽  
Video File ◽  
Linear Svm

There are numerous algorithms and solutions for car or object detection as humanity is aiming towards the smart city solutions. Most solutions are based on counting, speed detection, traffic accidents and vehicle classification. The mentioned solutions are mostly based on high-quality videos, wide angles camera view, vehicles in motion, and are optimized for good visibility conditions intervals. A novelty of the proposed algorithm and solution is more accurate digital data extraction from video file sources generated by security cameras in Bosnia and Herzegovina from M18 roadway, but not limited only to that particular source. From the video file sources, data regarding number of vehicles, speed, traveling direction, and time intervals for the region of interest will be collected. Since finding contours approach is effective only on objects that are mobile, and because the application of this approach on traffic junctions did not yield desired results, a more specific approach of classification using a combination of Histogram of Oriented Gradients (HOG) and Support Vector Machines (Linear SVM) has shown to be more appropriate as the original source data can be used for training where the main benefit is the preservation of local second-order interactions, providing tolerance to local geometric misalignment and ability to work with small data samples. The features of the objects within a frame are extracted first by standardizing the feature variables and then computing the first order gradients of the frame. In the next stage, an encoding that remains robust to small changes while being sensitive to local frame content is produced. Finally, the HOG descriptors are generated and normalized again. In this way the channel histogram and spatial vector becomes the feature vector for the Linear SVM classifier. With the following parameters and setup system accuracy was around 85 to 95%. In the next phase, after cleaning protocols on collected data parameters, data will be used to research asphalt deformation effects.

Text Localisation for Roman Words from Shop Signage

2017 ◽  
Vol 14 (2) ◽  
pp. 49
Author(s):  
Nurbaity Sabri ◽  
Noor Hazira Yusof ◽  
Zaidah` Ibrahim ◽  
Zolidah Kasiran ◽  
Nur Nabilah Abu Mangshor
Keyword(s):  
Comparative Study ◽  
Kernel Function ◽  
Texture Features ◽  
Text Recognition ◽  
Primary Data ◽  
Support Vector ◽  
Svm Classifier ◽  
Histogram Of Oriented Gradient ◽  
Speeded Up Robust Features ◽  
Better Than

Text localisation determines the location of the text in an image. This process is performed prior to text recognition. Localising text on shop signage is a challenging task since the images of the shop signage consist of complex background, and the text occurs in various font types, sizes, and colours. Two popular texture features that have been applied to localise text in scene images are a histogram of oriented gradient (HOG) and speeded up robust features (SURF). A comparative study is conducted in this paper to determine which is better with support vector machine (SVM) classifier. The performance of SVM is influenced by its kernel function and another comparative study is conducted to identify the best kernel function. The experiments have been conducted using primary data collected by the authors. Results indicate that HOG with quadratic kernel function localises text for shop signage better than SURF.

The Novel Indices of Short-Time Heart Rate Variability for Prediction of Cardiovascular and Cerebrovascular Events

2020 ◽  
Vol 10 (3) ◽  
pp. 769-774
Author(s):  
Shiliang Shao ◽  
Ting Wang ◽  
Chunhe Song ◽  
Yun Su ◽  
Xingchi Chen ◽  
...  
Keyword(s):  
Heart Rate ◽  
Heart Rate Variability ◽  
Nearest Neighbor ◽  
Singular Value ◽  
Support Vector ◽  
Svm Classifier ◽  
K Nearest Neighbor ◽  
Cerebrovascular Events ◽  
The Hilbert Transform ◽  
Short Time

In this paper, eight novel instantaneous indices of short-time heart rate variability (HRV) signals are proposed for prediction of cardiovascular and cerebrovascular events. The indices are based on Bubble Entropy (BE) and Singular Value Decompose (SVD). The process of indices calculation is as follows, firstly, the instantaneous amplitude (IA), instantaneous frequency (IF) and instantaneous phase (IP) of HRV signals are estimated by the Hilbert transform. Secondly, according to the HRV, IA, IP and IF, the BE and singular value (SV) is calculated, then eight novel indices are obtained, they are BEHRV, BEIA, BEIF, BEIP, SVHRV, SVIA, SVIF and SVIP. Last but not least, in order to evaluate the performance of the eight novel indices for prediction of cardiovascular and cerebrovascular events, the difference analysis of eight indices is carried out by t-test. According to the p value, seven of the eight indices BEHRV, BEIA, BEIF, BEIP, SVIA, SVIF and SVIP are thought to be the indices to discriminate the E group and N group. The K-nearest neighbor (KNN), support vector machine (SVM) and decision tree (DT) are applied on the seven novel indices. The results are that, seven novel indices are significantly different between the events and non-events groups, and the SVM classifier has the highest classification Acc and Spe for prediction of cardiovascular and cerebrovascular events, they are 88.31% and 90.19%, respectively.

Study on XML Retrieval Results Classification

2012 ◽  
Vol 263-266 ◽  
pp. 1773-1777
Author(s):  
Hong Yu ◽  
Xiao Lei Huang ◽  
Zhi Ling Wei ◽  
Chen Xia Yang
Keyword(s):  
Nearest Neighbor ◽  
Classification Performance ◽  
Feedback Mechanism ◽  
Support Vector ◽  
Svm Classifier ◽  
K Nearest Neighbor ◽  
Xml Retrieval ◽  
Text Documents ◽  
Plain Text ◽  
Xml Documents

Mining (classify or clustering) retrieval results to serve relevance feedback mechanism of search engine is an important solution to improve effectiveness of retrieval. Unlike plain text documents, since the XML documents are semi-structured data, for XML retrieval results classification, consider exploiting structure features of XML documents, such as tag paths and edges etc. We propose to use Support Vector Machine (SVM) classifier to classify XML retrieval results exploiting both their content and structure features. We implemented the classification method on XML retrieval results based on the IEEE SC corpus. Compared with k-nearest neighbor classification (KNN) on the same dataset in our application, SVM perform better. The experiment results have also shown that the use of structure features, especially tag paths and edges, can improve the classification performance significantly.

People Counting Based on the Analysis of the Mass

2014 ◽  
Vol 945-949 ◽  
pp. 1875-1879
Author(s):  
Tao Li ◽  
Dong Mei Li ◽  
Ren Jie Huang ◽  
Xue Zhu Zhao
Keyword(s):  
Support Vector Machine ◽  
Video Surveillance ◽  
Support Vector ◽  
Svm Classifier ◽  
The Novel ◽  
People Counting ◽  
The People ◽  
Objects Tracking ◽  
Counting Model ◽  
Novel Algorithm

In order to improve the accuracy of people counting in video surveillance, the method for people counting based on the analysis of the mass is proposed. The novel algorithm of objects tracking is designed to aim at people counting, and the people counting model is obtained by training a support vector machine (SVM) classifier with the input of the feature of mass. The experimental results show that the accuracy of counting is over 93%.

People Counting Based on the Moving Feature of the Mass

2014 ◽  
Vol 989-994 ◽  
pp. 2540-2542
Author(s):  
Peng Zhe Qiao ◽  
Tao Li ◽  
Tao Xiang ◽  
Xi Zhi Zhang
Keyword(s):  
Support Vector Machine ◽  
Energy Density ◽  
Optical Flow ◽  
Video Surveillance ◽  
Support Vector ◽  
Svm Classifier ◽  
People Counting ◽  
The People ◽  
Flow Algorithm ◽  
Counting Model

In order to improve the accuracy of people counting in video surveillance, the method for people counting based on the moving feature of the mass is proposed. We obtain the orientation and energy density of mass through the optical flow algorithm, and get the information about the size of mass to design the feature of mass. The people counting model is obtained by training a support vector machine (SVM) classifier with the moving feature and shape feature of mass. The experimental results confirm that our approach improves the accuracy of people counting.

Sign in / Sign up

Export Citation Format

Share Document