Interactive exploration of image collections on mobile devices

Image collections are ever growing and hence visual information is becoming more and more important. Moreover, the classical paradigm of taking pictures has changed, first with the spread of digital cameras and, more recently, with mobile devices equipped with integrated cameras. Clearly, these image repositories need to be managed, and tools for effectively and efficiently searching image databases are highly sought after, especially on mobile devices where more and more images are being stored. In this paper, we present an image browsing system for interactive exploration of image collections on mobile devices. Images are arranged so that visually similar images are grouped together while large image repositories become accessible through a hierarchical, browsable tree structure, arranged on a hexagonal lattice. The developed system provides an intuitive and fast interface for navigating through image databases using a variety of touch gestures. © 2012 Springer-Verlag.

Interactive browsing of image collections on mobile devices

Image collections are growing at a rapid rate and hence visual information is becoming more and more important. Clearly, these image repositories need to be managed, and tools for effectively and efficiently searching image databases are highly sought after, especially on mobile devices where more and more images are being stored. In this paper, we present an image browsing system for interactive exploration of image collections on mobile devices. Images are arranged so that visually similar images are grouped together while large image repositories become accessible through a hierarchical, browsable tree structure, arranged on a hexagonal lattice. The developed system provides an intuitive and fast interface for navigating through image databases using a variety of touch gestures.

Thermal imaging as a biometrics approach to facial signature authentication

This dissertation develops an image processing framework with unique feature extraction and similarity measurements for human face recognition in the thermal mid-wave infrared portion of the electromagnetic spectrum. The goals of this research is to design specialized algorithms that would extract facial vasculature information, create a thermal facial signature and identify the individual. The objective is to use such findings in support of a biometrics system for human identification with a high degree of accuracy and a high degree of reliability. This last assertion is due to the minimal to no risk for potential alteration of the intrinsic physiological characteristics seen through thermal infrared imaging. The proposed thermal facial signature recognition is fully integrated and consolidates the main and critical steps of feature extraction, registration, matching through similarity measures, and validation through testing our algorithm on a database, referred to as C-X1, provided by the Computer Vision Research Laboratory at the University of Notre Dame. Feature extraction was accomplished by first registering the infrared images to a reference image using the functional MRI of the Brain’s (FMRIB’s) Linear Image Registration Tool (FLIRT) modified to suit thermal infrared images. This was followed by segmentation of the facial region using an advanced localized contouring algorithm applied on anisotropically diffused thermal images. Thermal feature extraction from facial images was attained by performing morphological operations such as opening and top-hat segmentation to yield thermal signatures for each subject. Four thermal images taken over a period of six months were used to generate thermal signatures and a thermal template for each subject, the thermal template contains only the most prevalent and consistent features. Finally a similarity measure technique was used to match signatures to templates and the Principal Component Analysis (PCA) was used to validate the results of the matching process. Thirteen subjects were used for testing the developed technique on an in-house thermal imaging system. The matching using an Euclidean-based similarity measure showed 88% accuracy in the case of skeletonized signatures and templates, we obtained 90% accuracy for anisotropically diffused signatures and templates. We also employed the Manhattan-based similarity measure and obtained an accuracy of 90.39% for skeletonized and diffused templates and signatures. It was found that an average 18.9% improvement in the similarity measure was obtained when using diffused templates. The Euclidean- and Manhattan-based similarity measure was also applied to skeletonized signatures and templates of 25 subjects in the C-X1 database. The highly accurate results obtained in the matching process along with the generalized design process clearly demonstrate the ability of the thermal infrared system to be used on other thermal imaging based systems and related databases. A novel user-initialization registration of thermal facial images has been successfully implemented. Furthermore, the novel approach at developing a thermal signature template using four images taken at various times ensured that unforeseen changes in the vasculature did not affect the biometric matching process as it relied on consistent thermal features.

MRI Registration for Human Hip Kinematics

Measurement of joint kinematics can provide knowledge to help improve joint prosthesis design, as well as identify joint motion patterns that may lead to joint degeneration or injury. More investigation into how the hip translates in live human subjects during high amplitude motions is needed. This work presents a design of a non-invasive method using the registration between images from conventional Magnetic Resonance Imaging (MRI) and open MRI to calculate three dimensional hip joint kinematics. The method was tested on a single healthy subject in three different poses. MRI protocols for the conventional gantry, high-resolution MRI and the open gantry, lowresolution MRI were developed. The scan time for the low-resolution protocol was just under 6 minutes. High-resolution meshes and low resolution contours were derived from segmentation of the high-resolution and low-resolution images, respectively. Low-resolution contours described the poses as scanned, whereas the meshes described the bones’ geometries. The meshes and contours were registered to each other, and joint kinematics were calculated. The segmentation and registration were performed for both cortical and sub-cortical bone surfaces. A repeatability study was performed by comparing the kinematic results derived from three users’ segmentations of the sub-cortical bone surfaces from a low-resolution scan. The root mean squared error of all registrations was below 1.92mm. The maximum range between segmenters in translation magnitude was 0.95mm, and the maximum deviation from the average of all orientations was 1.27◦. This work demonstrated that this method for non-invasive measurement of hip kinematics is promising for measuring high-range-of-motion hip motions in vivo.

Registration-by-regression of coronary CTA and X-ray angiography

We evaluate the integration of 3D preoperative computed tomography angiography of the coronary arteries with intraoperative 2D X-ray angiographies by a recently proposed novel registration-by-regression method. The method relates image features of 2D projection images to the transformation parameters of the 3D image. We compared different sets of features and studied the influence of preprocessing the training set. For the registration evaluation, a gold standard was developed from eight X-ray angiography sequences from six different patients. The alignment quality was measured using the 3D mean target registration error (mTRE). The registration-by-regression method achieved moderate accuracy (median mTRE of 15 mm) on real images. It does therefore not provide yet a complete solution to the 3D–2D registration problem but it could be used as an initialisation method to eliminate the need for manual initialisation.

Three-dimensional, in-silico breast phantom for multimodality image simulations

We report on the construction of anatomically realistic three-dimensional in-silico breast phantoms with adjustable sizes, shapes and morphologic features. The concept of multiscale spatial resolution is implemented for generating breast tissue images from multiple modalities. Breast epidermal boundary and subcutaneous fat layer is generated by fitting an ellipsoid and 2nd degree polynomials to reconstructive surgical data and ultrasound imaging data. Intraglandular fat is simulated by randomly distributing and orienting adipose ellipsoids within a fibrous region immediately within the dermal layer. Cooper’s ligaments are simulated as fibrous ellipsoidal shells distributed within the subcutaneous fat layer. Individual ductal lobes are simulated following a random binary tree model which is generated based upon probabilistic branching conditions described by ramification matrices, as originally proposed by Bakic et al [3, 4]. The complete ductal structure of the breast is simulated from multiple lobes that extend from the base of the nipple and branch towards the chest wall. As lobe branching progresses, branches are reduced in height and radius and terminal branches are capped with spherical lobular clusters. Biophysical parameters are mapped onto the complete anatomical model and synthetic multimodal images (Mammography, Ultrasound, CT) are generated for phantoms of different adipose percentages (40%, 50%, 60%, and 70%) and are analytically compared with clinical examples. Results demonstrate that the in-silico breast phantom has applications in imaging performance evaluation and, specifically, great utility for solving image registration issues in multimodality imaging.

Sistema de realidade aumentada no procedimento cirúrgico de remoção de pedras nos rins

A inovação tecnológica e as facilidades que gera tem tido um impacto crescente em diversas área, inclusivamente na medicina. A rápida evolução por parte de algumas tecnologias, como é o caso da Realidade Aumentada (RA), criam excelentes oportunidades, nomeadamente para intervenções cirúrgicas laparoscópicas, que apresentam especialmente problemas ao nível da exposição do doente a radiação. O presente documento detalha todo o processo de investigação e desenvolvimento realizado com a pretensão de criar um sistema de navegação por RA que auxilie o procedimento cirúrgico laparoscópico de remoção de pedras nos rins. Com este objetivo em perspetiva, e numa parceria com a empresa ECmedica LTD, foram desenvolvidos quatro protótipo funcionais. Com o intuito de compreender as melhores práticas de sistemas de input, interface e sistema de registo a aplicar, estes integraram aspetos inovadores tais como a utilização de uma sonda ultra-som, como substituta do raioX, e um registo feito através de sensores magnéticos. Apoiados numa metodologia de design centrado no utilizador e em instrumentos de análise como entrevistas e observação natural, os protótipos foram testados, obtendo respostas esclarecedoras relativamente ao objetivos dos protótipos. Foi observado que a RA é vista pelos médicos como uma solução com potencial, com as soluções apresentadas ao nível de inputs, interface e registo a serem bem recebidas. A projeção bidimensional oferecida pela imagem ultra-som foi encarada como insuficientes, sendo sugerida a sua substituição por um aumento tridimensional capaz de facilitar a correta inserção da agulha.

Image summarisation: human action description from static images

Dissertação de Mestrado, Processamento de Linguagem Natural e Indústrias da Língua, Faculdade de Ciências Humanas e Sociais, Universidade do Algarve, 2014

Representing image captions as concept graphs using semantic information

Conceptual interpretation of languages has gathered peak interest in the world of artificial intelligence. The challenge in modeling various complications involved in a language is the main motivation behind our work. Our main focus in this work is to develop conceptual graphical representation for image captions. We have used discourse representation structure to gain semantic information which is further modeled into a graphical structure. The effectiveness of the model is evaluated by a caption based image retrieval system. The image retrieval is performed by computing subgraph based similarity measures. Best retrievals were given an average rating of . ± . out of 4 by a group of 25 human judges. The experiments were performed on a subset of the SBU Captioned Photo Dataset. This purpose of this work is to establish the cognitive sensibility of the approach to caption representations

Representing image captions as concept graphs using semantic information

Conceptual interpretation of languages has gathered peak interest in the world of artificial intelligence. The challenge in modeling various complications involved in a language is the main motivation behind our work. Our main focus in this work is to develop conceptual graphical representation for image captions. We have used discourse representation structure to gain semantic information which is further modeled into a graphical structure. The effectiveness of the model is evaluated by a caption based image retrieval system. The image retrieval is performed by computing subgraph based similarity measures. Best retrievals were given an average rating of . ± . out of 4 by a group of 25 human judges. The experiments were performed on a subset of the SBU Captioned Photo Dataset. This purpose of this work is to establish the cognitive sensibility of the approach to caption representations.

Image Processing Algorithms applied to Radio SLAM using MIMO Radars

Radio Simultaneous Location and Mapping (SLAM) consists of the simultaneous tracking of the target and estimation of the surrounding environment, to build a map and estimate the target movements within it. It is an increasingly exploited technique for automotive applications, in order to improve the localization of obstacles and the target relative movement with respect to them, for emergency situations, for example when it is necessary to explore (with a drone or a robot) environments with a limited visibility, or for personal radar applications, thanks to its versatility and cheapness. Until today, these systems were based on light detection and ranging (lidar) or visual cameras, high-accuracy and expensive approaches that are limited to specific environments and weather conditions. Instead, in case of smoke, fog or simply darkness, radar-based systems can operate exactly in the same way. In this thesis activity, the Fourier-Mellin algorithm is analyzed and implemented, to verify the applicability to Radio SLAM, in which the radar frames can be treated as images and the radar motion between consecutive frames can be covered with registration. Furthermore, a simplified version of that algorithm is proposed, in order to solve the problems of the Fourier-Mellin algorithm when working with real radar images and improve the performance. The INRAS RBK2, a MIMO 2x16 mmWave radar, is used for experimental acquisitions, consisting of multiple tests performed in Lab-E of the Cesena Campus, University of Bologna. The different performances of Fourier-Mellin and its simplified version are compared also with the MatchScan algorithm, a classic algorithm for SLAM systems.

Effect of phosphate-bonded investments on titanium reaction layer and crown fit

This study analyzed the reaction layer and measured the marginal crown fit of cast titanium applied to different phosphate-bonded investments, prepared under the following conditions (liquid concentration/casting temperature): Rema Exakt (RE) - 100%/237°C, 75%/287°C, Castorit Super C (CS)-100%/70°C, 75%/141°C and Rematitan Plus (RP)- 100%/430°C (special to titanium cast, as the control group). The reaction layer was studied using the Vickers hardness test, and analyzed by two way ANOVA and Tukey's HSD tests (α = 0.05). Digital photographs were taken of the crowns seated on the die, the misfit was measured using an image analysis system and One-way ANOVA, and Tukey's test was applied (α = 0.05). The hardness decreased from the surface (601.17 VHN) to 150 μm (204.03 VHN). The group CS 75%/141°C presented higher hardness than the other groups, revealing higher surface contamination, but there were no differences among the groups at measurements deeper than 150 μm. The castings made with CS - 100%/70°C presented the lowest levels of marginal misfit, followed by RE -100%/237°C. The conventional investments CS (100%) and RE (100%) showed better marginal fit than RP, but the CS (75%) had higher surface contamination.

Effectiveness of two systems for the spraying of pesticides in citrus trees

Citriculture normally uses high application volumes in pesticide solutions (of 2.000 to 5.000 L ha(-1)) to control pests and diseases that affect the crop, which generates an increase in operational costs. For this reason, diverse systems of application are being developed to reduce application volumes and improve the uniformity of pesticide deposition. The goal of this work was to evaluate the efficiency of two application systems of pesticides in citrus trees. One system used a prototype for terrestrial application with rotary disc atomizers that are widely used in agricultural aviation, and the other system used hollow cone tip hydraulics. For the treatment of the trees the insecticide Metidation was used at the dose of 180 gr per hectare. To study the droplet spectrum, water-sensitive papers were installed at different positions in the trees canopy, and for the study of insecticide deposition leaves of the treated plants were collected. The water-sensitive papers were collected and analyzed using a computerized image analysis system (e-Sprinkle, EMBRAPA, Sao Paulo, Brazil), and the leaves analyzed by the technique of gas chromatography. Pesticide deposition was similar in both application system, although the solution volume used by the application system equipped with rotary disc atomizers was one quarter of the volume used by the application system equipped with hydraulic tips, reducing considerably the cost of the phytosanitary treatments.

Collagen and Elastic Content of Abdominal Skin After Surgical Weight Loss

Collapsed skin folds after bariatric weight loss are often managed by plastic procedures, but changes in dermal composition and architecture have rarely been documented. Given the potential consequences on surgical outcome, a prospective histochemical study was designed. The hypothesis was that a deranged dermal fiber pattern would accompany major changes in adipose tissue. Female surgical candidates undergoing postbariatric abdominoplasty (n = 40) and never obese women submitted to control procedures (n = 40) were submitted to double abdominal biopsy, respectively in the epigastrium and hypogastrium. Histomorphometric assessment of collagen and elastic fibers was executed by the Image Analyzer System (Kontron Electronic 300, Zeiss, Germany). Depletion of collagen, but not of elastic fibers, in cases with massive weight loss was confirmed. Changes were somewhat more severe in epigastrium (P = 0.001) than hypogastrium (P = 0.007). Correlation with age did not occur. (1) Patients displayed lax, soft skin lacking sufficient collagen fiber network. (2) Elastic fiber content was not damaged, and was even moderately increased in epigastrium; (3) Preoperative obesity negatively correlated with hypogastric collagen concentration; (4) Future studies should pinpoint the roles of obesity, and especially of massive weight loss, on dermal architecture and response to surgery.

Collagen is reduced and disrupted in human aneurysms and dissections of ascending aorta

In ascending aorta aneurysms, there is an enlargement of the whole vessel, whereas aortic dissections (ADs) are characterized by the cleavage of the wall into 2 sheets at the external half. We searched if alterations in collagen could be related to these diseases. Sections of aortas from 14 case patients with acute dissections, 10 case patients with aneurysms, and 9 control subjects were stained with picrosirius. Slides were analyzed under polarized microscopy to evaluate the structure of collagen fibers. The proportion of collagen was calculated in each half of the medial layer by color detection in a computerized image analysis system. Collagen appearance under polarized light was consistent with collagenolysis. The mean collagen proportions at the inner and outer halves, respectively, were 0.50 +/- 0.13 and 0.40 +/- 0.08 in the control group, 0.20 +/- 0.10 and 0.18 +/- 0.12 in the AD group, and 0.33 +/- 0.12 and 0.19 +/- 0.12 in the aneurysm group. The AD (P < .01) and control (P = .04) groups had less collagen at the external half, no difference was found in the aneurysm group (P = .71). In both halves, there was less collagen in the case patients than in the control subjects (all P < .01), but at the internal half, the decrease was significantly greater in the case patients with aneurysms than in those with dissections (P = .03; at the external half, P = .99). Aortic dissections and aneurysms show a decrease in collagen content that could be related to a weakness of the wall underlying the diseases, but the locations of the decrease differ: in dissections, it is situated mostly at the external portion of the media (site of cleavage), whereas in aneurysms, it is more diffuse, consistent with the global enlargement. (c) 2008 Elsevier Inc. All rights reserved.