Medical Infrared Thermography (MIT) offers a potential non-invasive, non-contact and radiation free imaging modality for assessment of abnormal inflammation having pain in the human body. The assessment of inflammation mainly depends on the emission of heat from the skin surface. Arthritis is a disease of joint damage that generates inflammation in one or more anatomical joints of the body. Osteoarthritis (OA) is the most frequent appearing form of arthritis, and rheumatoid arthritis (RA) is the most threatening form of them. In this study, the inflammatory analysis has been performed on the infrared images of patients suffering from RA and OA. For the analysis, a dataset of 30 bilateral knee thermograms has been captured from the patient of RA and OA by following a thermogram acquisition standard. The thermograms are pre-processed, and areas of interest are extracted for further processing. The investigation of the spread of inflammation is performed along with the statistical analysis of the pre-processed thermograms. The objectives of the study include: i) Generation of a novel thermogram acquisition standard for inflammatory pain disease ii) Analysis of the spread of the inflammation related to RA and OA using K-means clustering. iii) First and second order statistical analysis of pre-processed thermograms. The conclusion reflects that, in most of the cases, RA oriented inflammation affects bilateral knees whereas inflammation related to OA present in the unilateral knee. Also due to the spread of inflammation in OA, contralateral asymmetries are detected through the statistical analysis.
The non-invasive, painless, radiation-free and cost-effective infrared breast thermography (IBT) makes a significant contribution to improving the survival rate of breast cancer patients by early detecting the disease. This paper presents a set of standard breast thermogram acquisition protocols to improve the potentiality and accuracy of infrared breast thermograms in early breast cancer detection. By maintaining all these protocols, an infrared breast thermogram acquisition setup has been established at the Regional Cancer Centre (RCC) of Government Medical College (AGMC), Tripura, India. The acquisition of breast thermogram is followed by the breast thermogram interpretation, for identifying the presence of any abnormality. However, due to the presence of complex vascular patterns, accurate interpretation of breast thermogram is a very challenging task. The bilateral symmetry of the thermal patterns in each breast thermogram is quantitatively computed by statistical feature analysis. A series of statistical features are extracted from a set of 20 thermograms of both healthy and unhealthy subjects. Finally, the extracted features are analyzed for breast abnormality detection. The key contributions made by this paper can be highlighted as — a) the designing of a standard protocol suite for accurate acquisition of breast thermograms, b) creation of a new breast thermogram dataset by maintaining the protocol suite, and c) statistical analysis of the thermograms for abnormality detection. By doing so, this proposed work can minimize the rate of false findings in breast thermograms and thus, it will increase the utilization potentiality of breast thermograms in early breast cancer detection.
The development of the latest face databases is providing researchers different and realistic problems that play an important role in the development of efficient algorithms for solving the difficulties during automatic recognition of human faces. This paper presents the creation of a new visual face database, named the Department of Electronics and Information Technology-Tripura University (DeitY-TU) face database. It contains face images of 524 persons belonging to different nontribes and Mongolian tribes of north-east India, with their anthropometric measurements for identification. Database images are captured within a room with controlled variations in illumination, expression, and pose along with variability in age, gender, accessories, make-up, and partial occlusion. Each image contains the combined primary challenges of face recognition, i.e., illumination, expression, and pose. This database also represents some new features: soft biometric traits such as mole, freckle, scar, etc., and facial anthropometric variations that may be helpful for researchers for biometric recognition. It also gives an equivalent study of the existing two-dimensional face image databases. The database has been tested using two baseline algorithms: linear discriminant analysis and principal component analysis, which may be used by other researchers as the control algorithm performance score.
Pose and illumination invariant face recognition problem is now-a-days an emergent problem in the field of information security. In this paper, gradient based fusion method of gradient visual and corresponding infrared face images have been proposed to overcome the problem of illumination varying conditions. This technique mainly extracts illumination insensitive features under different conditions for effective face recognition purpose. The gradient image is computed from a visible light image. Information fusion is performed in the gradient map domain. The image fusion of infrared image and corresponding visual gradient image is done in wavelet domain by taking the maximum information of approximation and detailed coefficients. These fused images have been taken for dimension reduction using Independent Component Analysis (ICA). The reduced face images are taken for training and testing purposes from different classes of different datasets of IRIS face database. SVM multiclass strategy ‘one-vs.-all’ have been taken in the experiment. For training support vector machine, Sequential Minimal Optimization (SMO) algorithm has been used. Linear kernel and Polynomial kernel with degree 3 are used in SVM kernel functions. The experiment results show that the proposed approach generates good classification accuracies for the face images under different lighting conditions.
Due to the various factors like illumination, expression, and pose variation etc., human face seem different in multiple
occasions. To determine the efficiency of the different face recognition algorithms, it requires benchmark face images.
This paper presents a comprehensive study of the available 2D face databases and also introduces the creation of a visual
face database, North-East Indian (NEI) Face Database, which is under development in the Biometrics Laboratory of
Tripura University, India. It contains high quality face images of 292 individuals of different tribe and non-tribe people
of Mongolian origin collected from the North-Eastern states of India. The database contains four different types of
illumination variations, eight different expressions, faces wearing glasses and each of these variations are being clicked
concurrently from five different angles to provide pose variation using five CMOS sensor cameras, in a controlled indoor
environment. Three different resolutions are being used for capturing the database images. Some baseline face
recognition algorithms have also been tested using the Support Vector Machines (SVM) classifier on the NEI face
database, which may be used as the control algorithm performance score by other researchers.
We present an approach for human face recognition using eye region extraction/replacement method under low illumination and varying expression conditions. For conducting experiments, two different sets of face images, namely visual and corresponding thermal, are used from Imaging, Robotics, and Intelligent Systems (IRIS) thermal/visual face data. A decomposition and reconstruction technique of Daubechies wavelet co-efficient (db4) is used to generate the fused image by replacing the eye region in the visual image with the same region from the corresponding thermal image. After that, independent component analysis over the natural logarithm domain (Log-ICA) is used for feature extraction/dimensionality reduction, and finally, a classifier is used to classify the fused face images. Two different image sets, i.e., training and test image sets, are mainly prepared using the IRIS thermal/visual face database for finding the accuracy of the proposed system. Experimental results show the proposed method is more efficient than other image fusion techniques which have used region extraction techniques for dark faces.
In this paper, an image fusion technique based on weighted average of Daubechies wavelet transform (db2) coefficients
from visual face image and their corresponding thermal images have been presented. Further, a comparative study has
been conducted for dimensionality reduction based on Principal Component Analysis (PCA) and Independent
Component Analysis (ICA). Fused images thus obtained are classified using a multi-layer perceptron (MLP). For
experiments IRIS Thermal/Visual Face Database has been used. Experimental results show that the performance of ICA
architecture-I is better than the other two approaches i.e. PCA and ICA-II. The average success rate for PCA, ICA-I and
ICA-II are 91.13%, 94.44% and 89.72% respectively. However, approaches presented here achieves maximum success
rate of 100% in some cases, especially in case of varying illumination.
In this paper we have investigated an approach to recognize thermal face images for face recognition using line features
and Radial Basis Function (RBF) neural network as classifier for them. The proposed method comprises of three steps.
In the first step, line features are extracted from thermal polar images and feature vectors are constructed using these
line. In the second step feature vectors thus obtained are passed through eigenspace projection for the dimensionality
reduction of feature vectors. Finally, the images projected into eigenspace are classified using a Radial Basis Function
(RBF) neural network. In the experiments we have used Object Tracking and Classification beyond Visible Spectrum
(OTCBVS) database. Experimental results show that the proposed approach significantly improves the verification and
identification performance and the maximum success rate is 100% whereas on an average it is 94.44%.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.