1,720,991 research outputs found
Face recognition using holistics features of low frequency infomation
No full textAccess is limited to UniMAP community.Face recognition has been getting the most attention from researchers in biometrics. Since the introduction of biometrics, it tried to find a process identified by comparing the current biometric pattern to the database. Here is a function of behavior in addition to the
physiological much of which work in the program as an example of biometric fingerprint,
iris scanning, signature, hand geometry and voice/speech. Man or woman can be separated as proof of identification in addition to the recognition will depend on your circumstances of the request. Some work on facial recognition has been successful method to identify facial features or remotely using a template that includes some of the area. A holistic technique used to identify characteristics or face geometry was introduced. Characterization advance achieved by random sampling of selected properties of the image pixels. From this information, we developed a data set corresponding to the low frequency values. The facial recognition systems for personal identification and validation using Principle Component Analysis (PCA) are among the most common technique for feature extraction technique used in face recognition. The test results in a database interface Olivetti Research Laboratory (ORL) to produce interesting results from the point of view of the recognition success, rate, and the robustness of face recognition algorithms
Gait recognition using principle component analysis implemented on DSP Processor
No full textThis research focus on the development of an automatic human identification system
using gait sequence images. Human identification is widely used in computer vision applications such as surveillance system, criminal investigations and human-computer interaction. Many identification approaches have shortcomings thus they require subject cooperation and sensitive to environmental and physiological changes. They also have high computational cost and are time consuming thus difficult to implement in
hardware. Gait sequence consists of non-stationary data and can be modeled using a
statistical learning technique. The proposed method consists of three different stages.
The pre-processing stage computes the average silhouette images to capture the
important information and get a better representation for gait silhouette data. Then a
principle component analysis (PCA) technique is applied on the average silhouette to
extract the important gait features and reduce a dimension of gait data. A linear
projection method used in this stage is able to reduce redundant features and remove
noise from the gait image. Furthermore, this approach will increase a discriminating
power in the feature space when dealing with low frequency information. Low
dimensional feature distribution in the feature space is assumed to be Gaussian, thus the
Euclidean distance classifier can be used in the classification stage. The proposed
algorithm is a model-free based which uses gait silhouette features for the compact gait
image representation and a linear feature reduction technique to remove redundant
information and noise. The proposed algorithm has been tested using a benchmark
CASIA dataset. The experimental results show that the best recognition rate is 90%
when the image is represented using 500 PCA coefficients. Low number of PCA
coefficients will give a possibility for the Euclidean distance classifier to be
implemented in hardware such as DSP processor. The implementation of the proposed
algorithm using the DSP-based processor achieved better performance in term of
computational time compared to the PC-Based processor with a ratio of 0.5 seconds
Face recognition system using DCT features implemented on DSP processor
No full textFace recognition is a challenge because the faces always change due to facial
expression, direction, light, and scale. Furthermore, it needs good computing techniques for recognition in order to reduce the system’s complexity. Our approach focuses on the local feature extraction in the frequency domain. DCT was proposed as the feature extraction algorithm for face recognition, which captures the important features in the
face image and at the same time reduces the feature space. PCA then performs the
feature reduction of the extracted image and produces a small size of feature vector. The
propose method can reduce data dimension in feature space. The classification is done
by using the Euclidean distance between the projection test and projection train images.
The algorithm is tested using DSP processor and achieve a same performance with PC
based. The extensive experimentations that have been carried out upon standard face
databases such as ORL shows that significant performance is achieved by this method,
which is 98.5% for best selected test image and 95% for the worst selected test image.
Besides that, execution time is also measured, whereby to recognize 40 people, the
system only requires 0.3313 second. The proposed method not only offers
computational savings, but is also fast and has a high degree of recognition accuracy
Palmprint recognition using eigen-palm image implemented on DSP processor
No full textThis study focuses on the development of a human identification system using eigenpalm
images. Human identification based on biometric technology is extensively used
in several applications, such as access control and criminal investigation. The proposed
method consists of three main stages. The preprocessing stage computes the palmprint
images to capture important information and produce a better representation of
palmprint image data. The second stage extracts significant features from palmprint
images and reduces the dimension of the palmprint image data by applying the principal
component analysis (PCA) technique. A linear projection method is used in this stage to
reduce redundant features and remove noise from the palmprint image. Furthermore,
this approach increases discrimination power in the feature space. The Euclidean
distance classifier is used in the classification stage, which is the third stage. The
proposed method is tested using a benchmark PolyU dataset. Experimental results show
that the best achieved recognition rate is 97.5% when the palmprint image is resized
with 0.2 resizing scale and represented using 34 PCA coefficients. The raw data
projection and Euclidean distance classifier can be implemented on a digital signal
processor (DSP) board. Implementing the proposed algorithm using the DSP board
achieves better performance in computation time compared with a personal computerbased
system which make the system 47.2% faster
Information fusion of face and palm-print multimodal biometric at matching score level
No full textMultimodal biometric systems that integrate the biometric traits from several modalities
are able to overcome the limitations of single modal biometrics. Fusing the information at the middle stage by consolidating the information given by different traits can give a better result due to the richness of information at this stage. In this thesis, an information fusion at matching score level is used to integrate face and palm-print
modalities. Three types of matching score rule are used which is sum, product and
minimum rule. A linear statistical projection method based on the principle component
analysis (PCA) is used to capture the important information and reduce feature
dimension in the feature space. A fusion process is performed using matching score
computed using Euclidean distance classifier. The experiment is conducted using a
benchmark ORL face and PolyU palm-print dataset to examine the recognition rates of
the propose technique. The best recognition rate is 98.96% achieved by using sum rule
fusion method. Recognition rate can also be improved by increasing number of training
images and number of PCA coefficients
Palmprint recognition using local features
No full textAccess is limited to UniMAP community.There was a period of time when biometrics had been viewed as the technology
for the feature. It has showcased prominently in variety of science fiction films being on
sophisticated protection measure that is used to protect important documents or files,
and propreties etc. Today, it is not far from reality with the help of overly busy
innovation of technology. Biometrics will be progressively being used for protected
authentication of people or individual’s as well as creating its existence felts within
human lives. By using an individual’s physical or behavioral characterisctics to
recognize these individuals. It is a complicated function of the people’s protection need,
simplicity of use as well the size of the organization by the decision which that
biometric is employed. Due to the stability and unique characteristic, palmprint is
probably the comparatively a brand-new physical biometrics. The rich texture details of
information of palmprint provides on the effective means within personal or individuals
identification. The main visual section of the human brains is in charge of making the
foundation of three-dimensional chart of visual space and extracting features concerning
the type and positioning of the objects based on psycho-physiology research. The
fundamental design can be indicated as linear superposition of basis function.
Specifically, this particular concepts named Principal Component Analysis (PCA)
motivated us to be able to implement a linear projection technique to extract the
palmprint consistency texture features. In this paper has an overview and methods
utilizing for capturing an image, processing an image, pre-processing, verification of
algorithm, algorithm specifically created for real time palmprint recognition in large
database and measures regarding safeguarding palmprint systems along with users
privacy
Face recognition using Eigen-Face implemented on DSP processor
No full textFace recognition is the established research area in 2D biometric recognition system and
broadly used in a security system. Face recognition system is a physiological biometric information processing based on the two dimensional face image. This thesis focus to develop an automatic face recognition using holistic features extracted that use the global features represented by low frequency data from face image. Holistic features are extracted using eigenface method where a linear projection technique such as PCA is
used to capture the important information in the image. Face image has low frequency
information such as shape of mouth, eye, and nose which has high discrimination
power. By using PCA, only several number of eigenvector is preserved which belong to
these features. A low dimensional feature space is classified using distance classifier.
Distance classifier is used to calculate the similarity between two data points in the
feature space based on the distance of two vectors. Euclidean distance is used for
matching process. The propose method is tested using a benchmark ORL dataset that
has 400 images of 40 persons. The best recognition rate is 97.5% when tested using 9
training images and 1 testing image represented with 35 PCA coefficients. Using less
number of PCA coefficients is able for the classifier module to be implemented using
hardware such as DSP processor. Euclidean distance classifier is tested using the
TMS320C6713 digital signal processor (DSP). The computational time is less compared
with the offline simulation using PC based
Speech recognition using MFCC and DTW classifier
No full textAccess is limited to UniMAP community.Speech recognition had been used broadly in many applications such as security
systems, healthcare, and equipment designed for handicapped. This project is about
design speech recognition by encoding and modeling the systems in the Digital Signal
Processing Toolbox, using two algorithms Mel Frequency Cepstral Coefficients
(MFCC) and Dynamic Time Warping (DTW) adapted for feature extraction and
classification. First, record the words to accomplish the simulations of the programmed
system. An experimental database is obtained by speaking 10 numbers (0-9) during the
training phase. Second, that training word has been tested to be matched in order to
recognize it. The analysis of coding was modified according to the four elements. They
are a number of sample frequency (Fs), types of window used, number of triangles
(windowing) and size of the window. From these changes elements we can get the result
and determine the best performances of speech recognition. The best performance of
this speech recognition using MFCC and DTW algorithms are 90% recognition rate.
Thus, the designed systems actually work well in the speech recognition
Defect detection based on machine vision technique
No full textAccess is limited to UniMAP community.Detection of defects has got the attention of many researchers in recent years.
Researchers also believe that in order to reduce the defect of a product or to use a more
effective. Various studies have been conducted as defects such as Defect detection of
bearing surfaces based on machine vision technique, Defect detection of apple and
defect detection of eggs. Many method can be used in defect detection project such as
scanning and image pre processing. Defect is Non-conformance of a product with the
specified requirements, or non-fulfilment of user expectations . This is a method by
which we try to create to solve problems in a more orderly. Develop this project using
features extraction and image processing
Information of face & palmpront multimodal biometric
No full textAccess is limited to UniMAP community.Multimodal Biometrics is a system that are capable of using more than one
physiological characteristic for verification or identification. It also refer to the automatic
identification or verification of an individual. Biometric is a unique. For biometric
identification, it process of trying to find out a person’s identify by comparing the
present against a biometric pattern database . Here are many behaviour function in
addition to physiological in which employed in biometric program for example
fingerprint, iris, deal with, hearing, personal, voiceprint in addition to hands print out.
Man or women identification can be separated in proof in addition to identification is
dependent upon your circumstance from the request. Within multimodal biometric
methods include many different distinct modalities. Multi-sensor, Multi-method, Multicharacteristic, Multi-capture/instance in addition to Multi-verifier is actually among
multimodal biometric program. Biometric involve some help. By way of example, can
certainly retain excessive tolerance identification placing. Also, your probability
connected with accepting the impostor is actually drastically lowered. Biometric could
also lower failure to sign-up rate in addition to hard to utilize phony biometric. This kind
of task brings together deal with in addition to arms to become more final results.
Incorporate two techniques, particularly the procedure connected with coaching in
addition to assessment method
- …
