A high efficient biometrics approach for unconstrained iris segmentation and recognition

This dissertation develops an innovative approach towards less-constrained iris biometrics. Two major contributions are made in this research endeavor: (1) Designed an award-winning segmentation algorithm in the less-constrained environment where image acquisition is made of subjects on the move and taken under visible lighting conditions, and (2) Developed a pioneering iris biometrics method coupling segmentation and recognition of the iris based on video of moving persons under different acquisitions scenarios. The first part of the dissertation introduces a robust and fast segmentation approach using still images contained in the UBIRIS (version 2) noisy iris database. The results show accuracy estimated at 98% when using 500 randomly selected images from the UBIRIS.v2 partial database, and estimated at 97% in a Noisy Iris Challenge Evaluation (NICE.I) in an international competition that involved 97 participants worldwide involving 35 countries, ranking this research group in sixth position. This accuracy is achieved with a processing speed nearing real time. The second part of this dissertation presents an innovative segmentation and recognition approach using video-based iris images. Following the segmentation stage which delineates the iris region through a novel segmentation strategy, some pioneering experiments on the recognition stage of the less-constrained video iris biometrics have been accomplished. In the video-based and less-constrained iris recognition, the test or subject iris videos/images and the enrolled iris images are acquired with different acquisition systems. In the matching step, the verification/identification result was accomplished by comparing the similarity distance of encoded signature from test images with each of the signature dataset from the enrolled iris images. With the improvements gained, the results proved to be highly accurate under the unconstrained environment which is more challenging. This has led to a false acceptance rate (FAR) of 0% and a false rejection rate (FRR) of 17.64% for 85 tested users with 305 test images from the video, which shows great promise and high practical implications for iris biometrics research and system design.

A novel 3-D segmentation algorithm for anatomic liver and tumor volume calculations for liver cancer treatment planning

Three-Dimensional (3-D) imaging is vital in computer-assisted surgical planning including minimal invasive surgery, targeted drug delivery, and tumor resection. Selective Internal Radiation Therapy (SIRT) is a liver directed radiation therapy for the treatment of liver cancer. Accurate calculation of anatomical liver and tumor volumes are essential for the determination of the tumor to normal liver ratio and for the calculation of the dose of Y-90 microspheres that will result in high concentration of the radiation in the tumor region as compared to nearby healthy tissue. Present manual techniques for segmentation of the liver from Computed Tomography (CT) tend to be tedious and greatly dependent on the skill of the technician/doctor performing the task. ^ This dissertation presents the development and implementation of a fully integrated algorithm for 3-D liver and tumor segmentation from tri-phase CT that yield highly accurate estimations of the respective volumes of the liver and tumor(s). The algorithm as designed requires minimal human intervention without compromising the accuracy of the segmentation results. Embedded within this algorithm is an effective method for extracting blood vessels that feed the tumor(s) in order to plan effectively the appropriate treatment. ^ Segmentation of the liver led to an accuracy in excess of 95% in estimating liver volumes in 20 datasets in comparison to the manual gold standard volumes. In a similar comparison, tumor segmentation exhibited an accuracy of 86% in estimating tumor(s) volume(s). Qualitative results of the blood vessel segmentation algorithm demonstrated the effectiveness of the algorithm in extracting and rendering the vasculature structure of the liver. Results of the parallel computing process, using a single workstation, showed a 78% gain. Also, statistical analysis carried out to determine if the manual initialization has any impact on the accuracy showed user initialization independence in the results. ^ The dissertation thus provides a complete 3-D solution towards liver cancer treatment planning with the opportunity to extract, visualize and quantify the needed statistics for liver cancer treatment. Since SIRT requires highly accurate calculation of the liver and tumor volumes, this new method provides an effective and computationally efficient process required of such challenging clinical requirements.^

Positron emission tomography (PET) tumor segmentation and quantification: Development of new algorithms

Tumor functional volume (FV) and its mean activity concentration (mAC) are the quantities derived from positron emission tomography (PET). These quantities are used for estimating radiation dose for a therapy, evaluating the progression of a disease and also use it as a prognostic indicator for predicting outcome. PET images have low resolution, high noise and affected by partial volume effect (PVE). Manually segmenting each tumor is very cumbersome and very hard to reproduce. To solve the above problem I developed an algorithm, called iterative deconvolution thresholding segmentation (IDTS) algorithm; the algorithm segment the tumor, measures the FV, correct for the PVE and calculates mAC. The algorithm corrects for the PVE without the need to estimate camera's point spread function (PSF); also does not require optimizing for a specific camera. My algorithm was tested in physical phantom studies, where hollow spheres (0.5-16 ml) were used to represent tumors with a homogeneous activity distribution. It was also tested on irregular shaped tumors with a heterogeneous activity profile which were acquired using physical and simulated phantom. The physical phantom studies were performed with different signal to background ratios (SBR) and with different acquisition times (1-5 min). The algorithm was applied on ten clinical data where the results were compared with manual segmentation and fixed percentage thresholding method called T50 and T60 in which 50% and 60% of the maximum intensity respectively is used as threshold. The average error in FV and mAC calculation was 30% and -35% for 0.5 ml tumor. The average error FV and mAC calculation were ~5% for 16 ml tumor. The overall FV error was ∼10% for heterogeneous tumors in physical and simulated phantom data. The FV and mAC error for clinical image compared to manual segmentation was around -17% and 15% respectively. In summary my algorithm has potential to be applied on data acquired from different cameras as its not dependent on knowing the camera's PSF. The algorithm can also improve dose estimation and treatment planning.^

A methodology for hierarchical image segmentation evaluation

This paper proposes a method to evaluate hierarchical image segmentation procedures, in order to enable comparisons between different hierarchical algorithms and of these with other (non-hierarchical) segmentation techniques (as well as with edge detectors) to be made. The proposed method builds up on the edge-based segmentation evaluation approach by considering a set of reference human segmentations as a sample drawn from the population of different levels of detail that may be used in segmenting an image. Our main point is that, since a hierarchical sequence of segmentations approximates such population, those segmentations in the sequence that best capture each human segmentation level of detail should provide the basis for the evaluation of the hierarchical sequence as a whole. A small computational experiment is carried out to show the feasibility of our approach.

Segmentation hiérarchique du domaine sémantique pour l'accélération d'un modèle de langage

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

Beszállítófejlesztés és lean beszállítófejlesztés = Supplier development and lean supplier development

A tanulmány általános áttekintést ad a beszállítófejlesztésről. A szakmában elterjedt fogalmak, a meghatározó koncepcionális keretek, az ajánlott szervezeti megoldások és az eredményes megvalósítást támogató és gátló tényezők számba vétele arra szolgál, hogy tág kontextusban értelmezhessük a lean beszállítófejlesztést. A lean beszállítófejlesztés intézményesített szervezeti rutinok halmazát jelenti – a japán autóipari nagyvállalatok gyakorlata alapján. Egyszerre van jelen az ad hoc problémamegoldás és a folyamatorientált, tág és stratégiai beszállítófejlesztés. A kulcsbeszállítók állnak a középpontban. A beszállítókkal való együttműködésben a bilaterális kapcsolatok (beszerző-beszállító) és a multilaterális kapcsolatok (beszerző és beszállítók csoportja) is fontos szereppel bírnak. A tevékenységek megvalósításában több tucat alkalmazott főállásban vesz részt. Ezek az alkalmazottak a beszerző vállalat termelési rendszerének, működési filozófiájának is szakértői. A globális nagyvállalatoknál – adott régióban is – több osztály, esetenként egymástól függetlenül is foglalkozik a beszállítók fejlesztésével. A sikeres megvalósítást és részvételt, elköteleződést támogatja, hogy az ösztönzési rutinok is formalizáltak és intézményesítettek (pl. hatalmi kérdések, elért haszon megosztása, partnerek felelőssége). _____ Our study reviews supplier development (SD) and lean supplier development literature. The first part gives an overview about general SD and related definitions, conceptual frameworks, organisational settings and supporting/impeding factors influencing the success of SD efforts. The second part of the study positions lean supplier development in this general SD context. Lean SD is built on sets of institutionalized organisational routines – based on daily practice of Japanese automotive companies. Lean SD contains of different SD approaches. It is pervaded by both ad hoc problem solving activities and process-focused, wide and strategic approaches at the same time. The efforts are focused on key suppliers. The SD is organised through bilateral (purchaser firm and supplier firm) and multilateral (purchaser firm and supplier firms) relations. At global automotive companies more dozens full time employees work on SD. These employees are expert of the production system and operating philosophy of the purchaser company. Global firms – even in a particular geographical area – have usually more departments responsible for SD. Eventually these departments work independently from each other. To achieve the expected performance improvement and real involvement and commitment it is critical to formalize and institutionalize routines influencing motivation as well (eg., power, gain sharing, responsibilities).

Segmentation hiérarchique du domaine sémantique pour l'accélération d'un modèle de langage

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

Multi-scale colorectal tumour segmentation using a novel coarse to fine strategy

This paper addresses the problem of colorectal tumour segmentation in complex real world imagery. For efficient segmentation, a multi-scale strategy is developed for extracting the potentially cancerous region of interest (ROI) based on colour histograms while searching for the best texture resolution. To achieve better segmentation accuracy, we apply a novel bag-of-visual-words method based on rotation invariant raw statistical features and random projection based l2-norm sparse representation to classify tumour areas in histopathology images. Experimental results on 20 real world digital slides demonstrate that the proposed algorithm results in better recognition accuracy than several state of the art segmentation techniques.

SUPPLIER INVOLVEMENT IN NEW PRODUCT DEVELOPMENT: A CASE STUDY FROM THE SEMICONDUCTOR INDUSTRY

Global competition requires that the companies adapt themselves to technological changes rapidly, develop new products, reduce the cost, shorten the time to market, and increase the quality. In this context, supplier involvement in New Product Development (NPD) is determinant for a company to respond to the requirements of the increasingly dynamic markets. The main purpose of the paper is to demonstrate the importance of supplier involvement in NPD, buyer-supplier relationships and their effects on buyer’s NPD process, highlighting the benefits of supplier involvement, the barriers, the strategic aspects and industry aspects. These issues are addressed with a case study from the semiconductor industry. Besides helping to understand NPD in the semiconductor industry, the contribution and fi ndings of this work are clear: the results achieved confirm the findings of studies referred in the literature review, and confirm that the semiconductor industry sector requires a closer and more complex relationship structure with suppliers, given the specificities and challenges of the sector, such as rapid technological changes, permanent innovation, global competition, reduction of cost and time-to-market cycle, increased capacity, among other. The main contribution of the paper to the scientific literature and to managers is the better understanding of the buyer-supplier relationships in NPD in the semiconductor industry.

ICTM: an interval tessellation-based model for reliable topographic segmentation

This work introduces a tessellation-based model for the declivity analysis of geographic regions. The analysis of the relief declivity, which is embedded in the rules of the model, categorizes each tessellation cell, with respect to the whole considered region, according to the (positive, negative, null) sign of the declivity of the cell. Such information is represented in the states assumed by the cells of the model. The overall configuration of such cells allows the division of the region into subregions of cells belonging to a same category, that is, presenting the same declivity sign. In order to control the errors coming from the discretization of the region into tessellation cells, or resulting from numerical computations, interval techniques are used. The implementation of the model is naturally parallel since the analysis is performed on the basis of local rules. An immediate application is in geophysics, where an adequate subdivision of geographic areas into segments presenting similar topographic characteristics is often convenient.

Typologie de la flottille chalutière du port de Sète par une méthode de segmentation

This work aims to define a typology of trawler f1eet in Sète, the main fishing harbour along the French Mediterranean coast, using several multivariate analysis methods. The fishing ships taken to account are represented by annual profiles of landing specific compositions. Five fishing strategies have been identified. A segmentation method using symbolic objects allows a formaI characterisation of the different strategies. These strategies are studied according to several general characteristics usually used for management rules elaboration (power, length, ship age). The typological analysis allows to characterise two main exploitation ways, one directed to the catch of a few species (Engraulis encrasicolus, Sardina pilchardus), the other characterised by the exploitation of a great diversity of species. By this way, it is possible to estimate how the catch of low represented species can significantly contribute to the exploitation of a resource.

Automatic Glaucoma Detection Based on Optic Disc Segmentation and Texture Feature Extraction

The use of digital image processing techniques is prominent in medical settings for the automatic diagnosis of diseases. Glaucoma is the second leading cause of blindness in the world and it has no cure. Currently, there are treatments to prevent vision loss, but the disease must be detected in the early stages. Thus, the objective of this work is to develop an automatic detection method of Glaucoma in retinal images. The methodology used in the study were: acquisition of image database, Optic Disc segmentation, texture feature extraction in different color models and classification of images in glaucomatous or not. We obtained results of 93% accuracy

Réseau calculant asynchrone dédié à la segmentation d'images

National audience