Facial Thermograms Research Articles

Design and emotional responses: is there coherence between what is said and what is felt? A study using biofeedback and virtual reality

Identifying users’ experience when using products is one of the major challenges for design. Analyzing users’ psychophysiological reactions to an experience using biofeedback can produce more reliable results than using subjective evaluations, such as structured interviews and questionnaires. Two case studies were conducted to identify emotions users actually felt and to check whether there is some correspondence with what they reported after using two computational systems. The first system investigated users’ emotions during training on a vehicle driving simulator, and the second analyzed the emotions experienced during a car racing game, both in a virtual reality environment. User’s opinions about their emotional state were obtained using self-report techniques (using the Geneva Emotions Wheel—GEW and Positive and Negative Affective Schedule—PANAS questionnaires) and applying EEG (brain activity with Frontal Alpha Asymmetry Index—FAAI) and infrared thermography (facial thermograms). The training experiment presented the greater concordance between the psychophysiological and the self-report responses. Results evidenced the importance of undertaking multimodal studies in design research to determine users’ emotional experiences in a virtual reality context.

Differentiation of twins using facial thermograms

Differentiation of twins using facial thermograms

ThermICA: Novel Approach for a Multivariate Analysis of Facial Thermal Responses.

Infrared Thermography (IRT) has been used to monitor skin temperature variation in a contactless manner, in both clinical medicine and psychophysiology. Here, we introduce a new methodology to obtain information about autonomic correlates related to perspiration, peripheral vasomotility, and respiration from infrared recordings. Our approach involves a model-based decomposition of facial thermograms using Independent Component Analysis (ICA) and an ad-hoc preprocessing procedure. We tested our approach on 30 healthy volunteers whose psychophysiological state was stimulated as part of an experimental protocol. Within-subject ICA analysis identified three independent components demonstrating correlations with the reference physiological signals. Moreover, a linear combination of independent components effectively predicted each physiological signal, achieving median correlations of 0.9 for electrodermal activity, 0.8 for respiration, and 0.73 for photoplethysmography peaks envelope. In addition, we performed a cross-validated inter-subject analysis, which allows to predict physiological signals from facial thermograms of unseen subjects. Our findings validate the efficacy of features extracted from both original and thermal-derived signals for differentiating experimental conditions. This outcome emphasizes the sensitivity and promise of our approach, advocating for expanded investigations into thermal imaging within biomedical signal analysis. It underscores its potential for enhancing objective assessments of emotional states.

Optimization of Image Capture Distance for Facial Thermograms in Dentistry

Thermography has not yet been validated for the screening of oral disorders and no clear guidelines or methodology for this purpose have been defined in the literature. The current pilot study was aimed as an initial step to evaluate the influence of shooting distances on the detection of the temperature asymmetries on the face for the purpose of dental thermography. Facial thermograms were taken in three views at three shooting distances for each participant. The mean temperature of the overall image and at the region of interest (ROI) were measured from the analysis software. Thirty adult volunteers participated in this study [n = 30, mean age: 25.8 ± 6.0]. The differences between the mean temperature values at the ROI for all different shooting distances within each profile view were statistically significant [Front: H(2) = 80.176, p < 0.001; Left: H(2) = 21.399, p < 0.001; Right: H(2) = 49.451, p < 0.001]. The mean ROI temperature was influenced by personal effects (p < 0.001), medications (p < 0.001), undergoing dental treatments (p < 0.001) as well as the consumption of food (p < 0.001). This study concludes that the detection of temperature asymmetries on the face in adult volunteers are affected by the capture distance as well as factors such as medication, oral-care, and alimentation. Therefore, it is advised that personal as well as medical histories are obtained in detail prior to making the facial thermograms.

Quantitative assessment of Bell's palsy-related facial thermal asymmetry using infrared thermography: A preliminary study.

The temperature distribution of normal human skin is symmetrical. Facial paralysis generally changes this thermal symmetry. The aim of this study is to analyze facial thermal asymmetry during the early onset of Bell's palsy, and to assess the feasibility of the diagnosis of early-onset Bell's palsy using infrared thermography (IRT). Fifteen subjects with Bell's palsy and 15 healthy volunteers were considered in this study. The infrared thermal images of the front, left, and right sides of all the subjects were collected and analyzed. Each group of facial thermograms was divided into 16 symmetrical regions of interest (ROIs) with respect to the left and right sides. Three different temperature difference calculation methods were used to express the degree of thermal symmetry between the left- and right-side ROIs, namely, the mean temperature difference (ΔTroi), maximum temperature difference (ΔTmax), and minimum temperature difference (ΔTmin). Among the facial ROIs, there were significant differences in the thermal symmetries of the frontal region, medial canthus region, and infraorbital region between subjects with and without Bell's palsy (p<0.05). Based on the results, ΔTroi was more effective than the other two methods for the diagnosis of early-onset Bell's palsy. The area under the ROC curve (AUC) of ΔTroi in the infraorbital region was 0.818; and the sensitivity and specificity were 0.867 and 0.800, respectively. Subjects with early-onset Bell's palsy exhibited thermal asymmetry on the left and right sides of their faces. The diagnosis of early-onset Bell's palsy using IRT is therefore necessary. Nevertheless, more effective thermal symmetry analysis methods will be investigated further in future research.

Automated detection of orofacial pain from thermograms using machine learning and deep learning approaches

AbstractThe main objectives of this study are (i) to perform automated segmentation of facial regions from thermograms using k‐means clustering algorithm and to classify the data into normal and orofacial pain (OFP) categories using various machine learning classifiers (ii) to implement the convolutional neural network (CNN) for classification of normal and OFP subjects which involves automated feature extraction and feature selection process. Fifty normal and 50 diseased cases suffering from orofacial pain were included in the study. Facial thermograms were segmented using k‐means algorithm, then statistical features were extracted and classified into normal and OFP using various machine learning classifier. Further, the deep learning networks such as VGG‐16 and DenseNet‐121 were used for automated feature extraction and classification of facial thermograms. The facial temperature variations of 3.46%, 3.4%, and 3.27% were observed in the front, right and left side facial regions respectively between the normal and the OFP subjects. Machine learning classifiers such as support vector machine (SVM) and random forest (RF) classifier provided the highest accuracy of 99%. On the other hand, deep learning models such as modified VGG‐16 achieved an average accuracy of 97% compared to modified DenseNet‐121 which produced an average accuracy of 68% in classification of normal and OFP thermograms. Thus, computer aided diagnosis of facial thermography could be used as a viable screening device for a reliable identification of tooth pathology before the occurrence of structural changes and complications.

A computer aided diagnostic method for the evaluation of type II diabetes mellitus in facial thermograms.

Almost 50% of individuals around the globe are unaware of diabetes and its complications. So, an early screening of diabetes is very important at this current situation. To overcome the difficulties such as pain and discomfort to the subjects obtained from the biochemical diagnostic procedures; an infrared thermography is the diagnostic technique which measures the skin surface temperature noninvasively. Thus, the aim of our proposed study was to evaluate the type II diabetes in facial thermograms and to develop a computer aided diagnosis (CAD) system to classify the normal and diabetes. The facial thermograms (n = 160) including male (n = 79) and female (n = 81) were captured using FLIR A 305sc infrared thermal camera. The Haralick textural features were extracted from the facial thermograms based on gray level co-occurrence matrix algorithm. The TROI, TMAX, and TTOT are the statistical temperature parameters exhibited a significant negative correlation with HbA1c (r = - 0.421, - 0.411, - 0.242, p < 0.01 (TROI); r = - 0.259, p < 0.01(TMAX) and - 0.173, p < 0.05 (TTOT)). An optimal regression equation has been constructed by using the significant facial variables and standard HbA1c values. The model has achieved sensitivity, specificity, and accuracy rate as 91.42%, 88.57%, and 90% respectively. The anthropometrical variables, extracted textural features and temperature parameters were fed into the classifiers and their performances were compared. The Support Vector Machine outperformed the Linear Discriminant Analysis (84.37%) and k-Nearest Neighbor (81.25%) classifiers with the maximum accuracy rate of 89.37%. The developed CAD system has achieved 89.37% of accuracy rate for the classification of diabetes. Thus, the facial thermography could be used as the basic non-invasive prognostic tool for the evaluation of type II diabetes mellitus.

Computer Aided Face Liveness Detection with Facial Thermography

Face is the most commonly used biometric these days due to its wide potential in numerous security applications. Spoofing attack is a fierce risk for security of face acknowledgment frameworks and can be limited by identifying face liveness. An innovative idea of detecting face liveness with facial thermography is presented in this paper. This paper is an effort to implement the incipient concept of face liveness detection approach by temperature sensation utilizing facial thermography. Computer Aided Face Liveness Detection Algorithm with facial thermography has been proposed. The proposed algorithm performs expeditious and precise analysis of the temperature distribution of individual face characteristic areas. The experimental results show that the proposed algorithm significantly increases the security of face recognition system by detecting face liveness. The efficiency of the proposed method has been evaluated prosperously by considering facial thermograms of 100 subjects from In-House facial thermography dataset. Maximum reliability has been procured during face liveness detection with temperature sensation.

Thermographic assessment of facial temperature in patients undergoing orthognathic surgery

This study was conducted to assess the usefulness of thermography for quantifying facial temperature before and after orthognathic surgery and intermaxillary fixation, and the effects of these orthognathic procedures on facial temperature. Facial thermograms of 10 patients who underwent bilateral sagittal split ramus osteotomy (SSRO, one-jaw group) and another 10 patients who underwent Le Fort I osteotomy and bilateral SSRO (two-jaw group) were taken 1 day before orthognathic surgery (T1) and at release of intermaxillary fixation 7 days later (T2). Two thermograms taken 30 s (TG1) and 3 min (TG2) after the start of recording at T1 and T2 were used. A square (26 × 26 pixels) was marked on each thermogram and the mean facial temperature for each square was measured. Three-way analysis of variance was used for statistical comparisons. Facial temperatures were significantly higher at T2 than at T1 on TG1 and TG2, and were significantly higher on TG2 than on TG1 at T1 and T2. The two-jaw group had a significantly higher facial temperature than the one-jaw group. Thermography was useful for quantitative assessment of facial temperature in patients undergoing orthognathic surgery. Changes in facial temperature were due predominantly to inflammation after surgery, rather than to sarcopenia.

Facial thermography: a potential complimentary tool for evaluation of dental disorders

The aim and objectives of the study was to analyze the skin surface temperature distribution in dental disorders using thermal imaging and to segment the region of interest using k-means algorithm and to perform statistical feature extraction for the total population studied. Thermal images were obtained for left profile, right profile, and front profile for the total population to be studied. The thermal image was segmented using k-means algorithm and the features were extracted from the segmented output image for both normal and dental disorder subjects. The results obtained from the study depicts that the mean temperature difference between the abnormal diseased subjects and the healthy controls in the front, left and right facial region was found to be 8.75%, 7.89% and 9.3% respectively. Among the regions examined in the facial thermogram, right facial region depicts the highest percentage difference of 9.3% found between the diseased subjects and normal group. From this data it is safe to infer that, presence of infections, significantly increases the temperature of the region. Hence thermography was used as a complimentary diagnostic tool in diagnosis of dental disorders.

An automated approach to enhance the thermographic evaluation on orofacial regions in lateral facial thermograms

Segmentation of characteristic facial regions has often been an initial step of thermographic analysis in face recognition and clinical diagnosis. Moreover, fast and accurate thermographic analysis on characteristic areas is highly reliant on segmentation approach. Usually, frontal and lateral projections are used to capture the facial thermograms. The significant role of lateral facial thermography to diagnose the various problems associated with orofacial regions has been remarkable in many studies. So far, no study has presented an automatic approach for the segmentation of characteristic areas in lateral facial thermograms. For this purpose, an automatic approach to segment the characteristic areas in lateral facial thermograms is proposed. The dataset of 140 facial thermograms with 1 left and 1 right lateral view per subject is created. Initially, image binarization is performed using optimal temperature thresholding for better visualization of facial geometry. Then, the automatic localization of characteristic points is performed at two levels, based on (a) geometrical features of the face, and (b) local thermal patterns. At last, the characteristic points and auxiliary points are used to segment the characteristic areas in the orofacial region of the face. To evaluate the segmentation performance of the proposed methodology, the automatically localized characteristic points are compared with manually marked using Euclidean distance based comparison criterion. With the localization error δch_pt≤0.05, the proposed automatic approach shows 92.04% of overall localization accuracy and 85% of overall segmentation accuracy. The key conclusion is that the proposed algorithm can potentially automate the process of thermographic analysis on characteristic areas to assist the diagnosis of problems in the orofacial region.

Performance Evaluation of Filters of Discrete Wavelet Transforms for Biometrics

&lt;p&gt;Biometrics associated with automated methods of identifying a person or verifying the identity of a person based on physiological or behavioral characteristics. Commonly used biometric features are facial features, fingerprints, voice, facial thermo grams, iris, posture/gait, palm print, hand geometry etc. Compared with other biometric characteristics iris is the most stable and hence the most reliable biometric characteristic over the period of a lifetime. This proposed work provides comparative study of various filters of Wavelet Transforms in terms of size and PSNR of images&lt;em&gt;.&lt;/em&gt;&lt;/p&gt;

Detection of Driver's Fight or Flight Reaction by Spatio-Temporal Spectrum Differential Analysis ofFacial Skin Thermogram

Before a person has a car accident, he may have several “close calls.” These “close calls” may cause a person to experience tension and fear. People experience the “fight or flight reaction” (FFR) under such circumstances, as it is known that people exhibit the FFR when they feel anxiety, strain, or threat. If the manifestation of the FFR in a driver can be determined using a biological measurement, it would be an extremely effective indicator that might help in the prevention of car accidents. In this research, we conducted FFR-arousing experiments using a driving simulator, and the STSDA method was used to detect spatio-temporal changes in the skin temperature on facial skin thermograms accompanying the occurrence of the FFR.

Skin heat transfer model of facial thermograms and its application in face recognition

It has been found that facial thermograms vary with ambient temperature, as well as other internal and external conditions, and result in severe decline in the facial recognition rate. To tackle this problem, a skin heat transfer (SHT) model based on thermal physiology is derived in this paper. The proposed model converts the facial thermograms into blood-perfusion data, which is revealed to reduce the within-class scatter of face images. The advantage of the derived blood-perfusion data over the raw thermograms for recognition is analyzed by the normalized reverse cumulative histogram. It is shown that blood-perfusion data are more consistent in representing facial features. The experiments conducted on both same-session and time-lapse data have further demonstrated that (1) the blood-perfusion data are less sensitive to ambient temperature, physiological and psychological conditions if the human bodies are in the steady state; (2) for time-lapse data, the performance with the blood-perfusion data is nearly identical to that of the same-session data, while the recognition rate with the temperature data dramatically decreases in this case. The major contributions of this work are the well-grounded infrared data preprocessing and the corresponding face recognition system.

A Method of Selecting Acupoints for Acupuncture Treatment of Peripheral Facial Paralysis by Thermography

The purpose of this study is to select acupoints for acupuncture treatment of peripheral facial paralysis according to the temperature on the face of the patient detected by thermogram, to determine an objective acupoint selection method for acupuncture treatment. In the test group of 60 cases of facial paralysis, the infrared thermogram on the face was detected at the first visit, and then acupuncture was given at the acupoints on the affected side with a temperature difference of over 0.5 degrees C from the healthy side for one therapeutic course, and in each successive course the acupoints were re-determined according to the results of thermogram examination and were administrated till the end of the total therapeutic course, and 120 cases of the control group were treated with acupuncture at conventionally selected acupoints. The results showed that the cured and basically cured rate was 90.0% (54 cases) in the test group and 77.5% (93 cases) in the control group with a significant difference between the two groups (p < 0.05); and the total sessions of acupuncture were less and the course of treatment was shorter in the test group than those in the control group (both p < 0.001). The utilization rate of the acupoints selected by facial thermogram in the test group was in order of Dicang (ST 4, 92.3%), Yingxiang (LI 20, 90.6%), Taiyang (EX-HN 5, 85.5%), Yangbai (GB 14, 76.6%), Quanliao (SI 18, 72.3%), and so on. In conclusion, acupuncture at the acupoints selected by thermogram for treatment of facial paralysis in the cured rate, the therapeutic course and sessions of acupuncture is significantly superior to acupuncture at the conventionally selected acupoints, and the thermogram-aided acupoint selection method is beneficial to objectivity and modernization of acupoint selection for acupuncture and moxibustion treatments.

顔面熱画像の空間周波数特徴による個人識別

顔面熱画像の空間周波数特徴による個人識別

Extracranial vascular changes and the source of pain in migraine headache.

The extracranial circulation of 66 migrainous patients was assessed during unilateral headache by recording the pulse amplitude of the superficial temporal artery and its main frontal branch, by facial thermography, and by changes in the intensity of headache when temporal or carotid arteries were compressed. Amplitude of pulsation of the superficial temporal artery did not differ between headache and headache-free sides but the amplitude of its frontal branch was increased on the headache side, specifically in a subgroup of patients whose headache was relieved by compressing the superficial temporal artery ("extracranial vascular" group). Facial thermograms demonstrated significant differences in heat loss from the temples and orbits between migrainous patients and controls, frontotemporal changes being more conspicuous in the extracranial vascular group. It was concluded that dilatation of the superficial temporal artery and its branches contributes substantially to migraine headache in only a minority of patients.

Facial thermography in the diagnosis of cerebrovascular disease and in evaluation of carotid endarterectomy

Some 60% of strokes are due to extracranial occlusive arterial lesions, most frequently at the bifurcation of the common carotid artery. Since these lesions are accessible to endarterectomy, their prestroke diagnosis is very important. Facial thermography quickly supplies reliqble information on the circulatory area in which these lesions occur, and this information can be atraumatically obtained in an out-patient setting. The success rate of facial thermography versus aortic arch angiography was 83% and 80%, respectively, in our case material, and this rate corresponds with data in the literature. In a series of 23 patients with facial thermograms and angiograms obtained before and after endarterectomy, facial thermography proved to be a useful diagnostic and prognostic aid in neurological out-patient guidance after carotid endarterectomy. By virtue of its rapidity and atraumatic character, because it can be carried out by technicians and because the findings are suitable for computer data processing, facial thermography would seem to be suitable for potential stroke screening of a high-risk asymptomatic population.

Maxillary sinusitis and bronchial asthma: Correlation of roentgenograms, cultures, and thermograms

Roentgenographic evidence of sinusitis is found more frequently in patients with bronchial asthma than in normals. Evidence for overt bacterial infection of the maxillary sinuses was sought in a sequential series of adult asthmatic patients. Twenty-one patients with maxillary sinus abnormality noted on roentgenograms were studied by facial thermography and culture of sinus contents. Cultures were obtained from 25 maxillary sinuses by a double-lumen technique that minimized nasal contamination. Twenty sinus cultures, including those from 9 patients in asthmatic relapse at the time of study, yielded no bacteria. Five sinus cultures, including those from 3 patients in asthmatic relapse, yielded aerobic bacteria. Two of the latter were organisms that are commonly thought of as pathogens and were obtained from the only two patients with more than three upper respiratory symptoms. Nasal cultures taken prior to puncture grew aerobic bacteria or fungi from 23 of 25 specimens. There was no correlation between the results of nasal cultures and the results of sinus cultures. Results of facial thermograms did not correlate with culture results. Overt bacterial infection apparently does not account for the abnormality of paranasal sinus roentgenograms found in the majority of adult patients with bronchial asthma.

The normal thermographic patterns of the human head

The facial, lateral, axial, and dorsal thermograms of 52 healthy young volunteers were studied. A high degree of asymmetry was encountered. The supra-orbital areas could be distinguished in the majority of the cases. Several distinct thermal patterns matching the vascular anatomy were found to exist. An intra-cranial tumour cannot be detected on the basis of asymmetry but only from disturbance of the thermographic patterns.