Retinal Image Analysis Using Machine Vision

The topic of this thesis is studying how lesions in retina caused by diabetic retinopathy can be detected from color fundus images by using machine vision methods. Methods for equalizing uneven illumination in fundus images, detecting regions of poor image quality due toinadequate illumination, and recognizing abnormal lesions were developed duringthe work. The developed methods exploit mainly the color information and simpleshape features to detect lesions. In addition, a graphical tool for collecting lesion data was developed. The tool was used by an ophthalmologist who marked lesions in the images to help method development and evaluation. The tool is a general purpose one, and thus it is possible to reuse the tool in similar projects.The developed methods were tested with a separate test set of 128 color fundus images. From test results it was calculated how accurately methods classify abnormal funduses as abnormal (sensitivity) and healthy funduses as normal (specificity). The sensitivity values were 92% for hemorrhages, 73% for red small dots (microaneurysms and small hemorrhages), and 77% for exudates (hard and soft exudates). The specificity values were 75% for hemorrhages, 70% for red small dots, and 50% for exudates. Thus, the developed methods detected hemorrhages accurately and microaneurysms and exudates moderately.

Project for Active and Robot Vision Course

Tässä työssä raportoidaan harjoitustyön kehittäminen ja toteuttaminen Aktiivisen- ja robottinäön kurssille. Harjoitustyössä suunnitellaan ja toteutetaan järjestelmä joka liikuttaa kappaleita robottikäsivarrella kolmiuloitteisessa avaruudessa. Kappaleidenpaikkojen määrittämiseen järjestelmä käyttää digitaalisia kuvia. Tässä työssä esiteltävässä harjoitustyötoteutuksessa käytettiin raja-arvoistusta HSV-väriavaruudessa kappaleiden segmentointiin kuvasta niiden värien perusteella. Segmentoinnin tuloksena saatavaa binäärikuvaa suodatettiin mediaanisuotimella kuvan häiriöiden poistamiseksi. Kappaleen paikkabinäärikuvassa määritettiin nimeämällä yhtenäisiä pikseliryhmiä yhtenäisen alueen nimeämismenetelmällä. Kappaleen paikaksi määritettiin suurimman nimetyn pikseliryhmän paikka. Kappaleiden paikat kuvassa yhdistettiin kolmiuloitteisiin koordinaatteihin kalibroidun kameran avulla. Järjestelmä liikutti kappaleita niiden arvioitujen kolmiuloitteisten paikkojen perusteella.

Minimum error contrast enhancement

Contrast enhancement is an image processing technique where the objective is to preprocess the image so that relevant information can be either seen or further processed more reliably. These techniques are typically applied when the image itself or the device used for image reproduction provides poor visibility and distinguishability of different regions of interest inthe image. In most studies, the emphasis is on the visualization of image data,but this human observer biased goal often results to images which are not optimal for automated processing. The main contribution of this study is to express the contrast enhancement as a mapping from N-channel image data to 1-channel gray-level image, and to devise a projection method which results to an image with minimal error to the correct contrast image. The projection, the minimum-error contrast image, possess the optimal contrast between the regions of interest in the image. The method is based on estimation of the probability density distributions of the region values, and it employs Bayesian inference to establish the minimum error projection.

Towards desired crystalline product properties: In-situ monitoring of batch crystallization

The objective of industrial crystallization is to obtain a crystalline product which has the desired crystal size distribution, mean crystal size, crystal shape, purity, polymorphic and pseudopolymorphic form. Effective control of the product quality requires an understanding of the thermodynamics of the crystallizing system and the effects of operation parameters on the crystalline product properties. Therefore, obtaining reliable in-line information about crystal properties and supersaturation, which is the driving force of crystallization, would be very advantageous. Advanced techniques, such asRaman spectroscopy, attenuated total reflection Fourier transform infrared (ATR FTIR) spectroscopy, and in-line imaging techniques, offer great potential for obtaining reliable information during crystallization, and thus giving a better understanding of the fundamental mechanisms (nucleation and crystal growth) involved. In the present work, the relative stability of anhydrate and dihydrate carbamazepine in mixed solvents containing water and ethanol were investigated. The kinetics of the solvent mediated phase transformation of the anhydrate to hydrate in the mixed solvents was studied using an in-line Raman immersion probe. The effects of the operation parameters in terms of solvent composition, temperature and the use of certain additives on the phase transformation kineticswere explored. Comparison of the off-line measured solute concentration and the solid-phase composition measured by in-line Raman spectroscopy allowedthe identification of the fundamental processes during the phase transformation. The effects of thermodynamic and kinetic factors on the anhydrate/hydrate phase of carbamazepine crystals during cooling crystallization were also investigated. The effect of certain additives on the batch cooling crystallization of potassium dihydrogen phosphate (KDP) wasinvestigated. The crystal growth rate of a certain crystal face was determined from images taken with an in-line video microscope. An in-line image processing method was developed to characterize the size and shape of thecrystals. An ATR FTIR and a laser reflection particle size analyzer were used to study the effects of cooling modes and seeding parameters onthe final crystal size distribution of an organic compound C15. Based on the obtained results, an operation condition was proposed which gives improved product property in terms of increased mean crystal size and narrowersize distribution.

Spektrikuvien tiivistäminen itseorganisoituvan kartan avulla.

Vuosi vuodelta kasvava tietokoneiden prosessointikyky on mahdollistanut harmaataso- ja RGB-värikuvia tarkempien spektrikuvien käsittelyn järjellisessä ajassa ilman suuria kustannuksia. Ongelmana on kuitenkin, ettei talletus- ja tiedonsiirtomedia ole kehittynyt prosessointikyvyn vauhdissa. Ratkaisu tähän ongelmaan on spektrikuvien tiivistäminen talletuksen ja tiedonsiirron ajaksi. Tässä työssä esitellään menetelmä, jossa spektrikuva tiivistetään kahdessa vaiheessa: ensin ryhmittelemällä itseorganisoituvan kartan (SOM) avulla ja toisessa vaiheessa jatketaan tiivistämistä perinteisin menetelmin. Saadut tiivistyssuhteet ovat merkittäviä vääristymän pysyessä siedettävänä. Työ on tehty Lappeenrannan teknillisen korkeakoulun Tietotekniikan osaston Tietojenkäsittelytekniikan tutkimuslaboratoriossa osana laajempaa kuvantiivistyksen tutkimushanketta.

Wood Volume Measurement Using Color Images

Tämä työ käsittelee puutukkien tilavuuden mittaamista värikonenäön avulla. Värikuvat on saatu Simpeleellä olevan metsäteollisuusyrityksen hiomosta. Työssä esitetään perusteellisesti matemaattinen teoria, joka liittyy käytettyihin kuvankäsittelymenetelmiin, kuten luokitteluun, kohinan poistoon ja tukkien segmentointiin. Esitetyt menetelmät implementointiin käytännössä ja eri menetelmillä saatuja tuloksia vertailtiin keskenään. Kuvankäsittelyalgoritmit on implementoitu Matlab 6.0:n avulla. Pääasiassa käytettiin uusinta Image Processing Toolboxia, joka on versio 3.0. Tämä työn näkökulma on pääasiassa käytäntöön soveltava, koska metsäteollsuus on korkealla tasolla Suomessa ja siellä on paljon alan yrityksiä, joissa tässä työssä kehitettyä menetelmää voidaan hyödyntää.

Environmental Monitoring using Image Analysis

Tärkeä tehtävä ympäristön tarkkailussa on arvioida ympäristön nykyinen tila ja ihmisen siihen aiheuttamat muutokset sekä analysoida ja etsiä näiden yhtenäiset suhteet. Ympäristön muuttumista voidaan hallita keräämällä ja analysoimalla tietoa. Tässä diplomityössä on tutkittu vesikasvillisuudessa hai vainuja muutoksia käyttäen etäältä hankittua mittausdataa ja kuvan analysointimenetelmiä. Ympäristön tarkkailuun on käytetty Suomen suurimmasta järvestä Saimaasta vuosina 1996 ja 1999 otettuja ilmakuvia. Ensimmäinen kuva-analyysin vaihe on geometrinen korjaus, jonka tarkoituksena on kohdistaa ja suhteuttaa otetut kuvat samaan koordinaattijärjestelmään. Toinen vaihe on kohdistaa vastaavat paikalliset alueet ja tunnistaa kasvillisuuden muuttuminen. Kasvillisuuden tunnistamiseen on käytetty erilaisia lähestymistapoja sisältäen valvottuja ja valvomattomia tunnistustapoja. Tutkimuksessa käytettiin aitoa, kohinoista mittausdataa, minkä perusteella tehdyt kokeet antoivat hyviä tuloksia tutkimuksen onnistumisesta.

Offset-print mottling measurement using machine vision

Mottling is one of the key defects in offset-printing. Mottling can be defined as unwanted unevenness of print. In this work, diameter of a mottle spot is defined between 0.5-10.0 mm. There are several types of mottling, but the reason behind the problem is still not fully understood. Several commercial machine vision products for the evaluation of print unevenness have been presented. Two of these methods used in these products have been implemented in this thesis. The one is the cluster method and the other is the band-pass method. The properties of human vision system have been taken into account in the implementation of these two methods. An index produced by the cluster method is a weighted sum of the number of found spots, and an index produced by band-pass method is a weighted sum of coefficients of variations of gray-levels for each spatial band. Both methods produce larger indices for visually poor samples, so they can discern good samples from the poor ones. The difference between the indices for good and poor samples is slightly larger produced by the cluster method. 11 However, without the samples evaluated by human experts, the goodness of these results is still questionable. This comparison will be left to the next phase of the project.

Unsupervised visual object categorization

The number of digital images has been increasing exponentially in the last few years. People have problems managing their image collections and finding a specific image. An automatic image categorization system could help them to manage images and find specific images. In this thesis, an unsupervised visual object categorization system was implemented to categorize a set of unknown images. The system is unsupervised, and hence, it does not need known images to train the system which needs to be manually obtained. Therefore, the number of possible categories and images can be huge. The system implemented in the thesis extracts local features from the images. These local features are used to build a codebook. The local features and the codebook are then used to generate a feature vector for an image. Images are categorized based on the feature vectors. The system is able to categorize any given set of images based on the visual appearance of the images. Images that have similar image regions are grouped together in the same category. Thus, for example, images which contain cars are assigned to the same cluster. The unsupervised visual object categorization system can be used in many situations, e.g., in an Internet search engine. The system can categorize images for a user, and the user can then easily find a specific type of image.

A comparison of electricity spot prices simulation using ARMA-GARCH and mean-reverting models

The aim of this work is to compare two families of mathematical models for their respective capability to capture the statistical properties of real electricity spot market time series. The first model family is ARMA-GARCH models and the second model family is mean-reverting Ornstein-Uhlenbeck models. These two models have been applied to two price series of Nordic Nord Pool spot market for electricity namely to the System prices and to the DenmarkW prices. The parameters of both models were calibrated from the real time series. After carrying out simulation with optimal models from both families we conclude that neither ARMA-GARCH models, nor conventional mean-reverting Ornstein-Uhlenbeck models, even when calibrated optimally with real electricity spot market price or return series, capture the statistical characteristics of the real series. But in the case of less spiky behavior (System prices), the mean-reverting Ornstein-Uhlenbeck model could be seen to partially succeeded in this task.

Computational visual quality of digitally printed images

The problem of understanding how humans perceive the quality of a reproduced image is of interest to researchers of many fields related to vision science and engineering: optics and material physics, image processing (compression and transfer), printing and media technology, and psychology. A measure for visual quality cannot be defined without ambiguity because it is ultimately the subjective opinion of an “end-user” observing the product. The purpose of this thesis is to devise computational methods to estimate the overall visual quality of prints, i.e. a numerical value that combines all the relevant attributes of the perceived image quality. The problem is limited to consider the perceived quality of printed photographs from the viewpoint of a consumer, and moreover, the study focuses only on digital printing methods, such as inkjet and electrophotography. The main contributions of this thesis are two novel methods to estimate the overall visual quality of prints. In the first method, the quality is computed as a visible difference between the reproduced image and the original digital (reference) image, which is assumed to have an ideal quality. The second method utilises instrumental print quality measures, such as colour densities, measured from printed technical test fields, and connects the instrumental measures to the overall quality via subjective attributes, i.e. attributes that directly contribute to the perceived quality, using a Bayesian network. Both approaches were evaluated and verified with real data, and shown to predict well the subjective evaluation results.

Pulsatile Blood Flow Simulations in Computed Tomography(CT) Scan-Based and Idealized Geometries of Human Aorta

Blood flow in human aorta is an unsteady and complex phenomenon. The complex patterns are related to the geometrical features like curvature, bends, and branching and pulsatile nature of flow from left ventricle of heart. The aim of this work was to understand the effect of aorta geometry on the flow dynamics. To achieve this, 3D realistic and idealized models of descending aorta were reconstructed from Computed Tomography (CT) images of a female patient. The geometries were reconstructed using medical image processing code. The blood flow in aorta was assumed to be laminar and incompressible and the blood was assumed to be Newtonian fluid. A time dependent pulsatile and parabolic boundary condition was deployed at inlet. Steady and unsteady blood flow simulations were performed in real and idealized geometries of descending aorta using a Finite Volume Method (FVM) code. Analysis of Wall Shear Stress (WSS) distribution, pressure distribution, and axial velocity profiles were carried out in both geometries at steady and unsteady state conditions. The results obtained in thesis work reveal that the idealization of geometry underestimates the values of WSS especially near the region with sudden change of diameter. However, the resultant pressure and velocity in idealized geometry are close to those in real geometry

Application of Computational Fluid Dynamics in Modeling Blood Flow in Human Thoracic Aorta

The aim of this study was to simulate blood flow in thoracic human aorta and understand the role of flow dynamics in the initialization and localization of atherosclerotic plaque in human thoracic aorta. The blood flow dynamics in idealized and realistic models of human thoracic aorta were numerically simulated in three idealized and two realistic thoracic aorta models. The idealized models of thoracic aorta were reconstructed with measurements available from literature, and the realistic models of thoracic aorta were constructed by image processing Computed Tomographic (CT) images. The CT images were made available by South Karelia Central Hospital in Lappeenranta. The reconstruction of thoracic aorta consisted of operations, such as contrast adjustment, image segmentations, and 3D surface rendering. Additional design operations were performed to make the aorta model compatible for the numerical method based computer code. The image processing and design operations were performed with specialized medical image processing software. Pulsatile pressure and velocity boundary conditions were deployed as inlet boundary conditions. The blood flow was assumed homogeneous and incompressible. The blood was assumed to be a Newtonian fluid. The simulations with idealized models of thoracic aorta were carried out with Finite Element Method based computer code, while the simulations with realistic models of thoracic aorta were carried out with Finite Volume Method based computer code. Simulations were carried out for four cardiac cycles. The distribution of flow, pressure and Wall Shear Stress (WSS) observed during the fourth cardiac cycle were extensively analyzed. The aim of carrying out the simulations with idealized model was to get an estimate of flow dynamics in a realistic aorta model. The motive behind the choice of three aorta models with distinct features was to understand the dependence of flow dynamics on aorta anatomy. Highly disturbed and nonuniform distribution of velocity and WSS was observed in aortic arch, near brachiocephalic, left common artery, and left subclavian artery. On the other hand, the WSS profiles at the roots of branches show significant differences with geometry variation of aorta and branches. The comparison of instantaneous WSS profiles revealed that the model with straight branching arteries had relatively lower WSS compared to that in the aorta model with curved branches. In addition to this, significant differences were observed in the spatial and temporal profiles of WSS, flow, and pressure. The study with idealized model was extended to study blood flow in thoracic aorta under the effects of hypertension and hypotension. One of the idealized aorta models was modified along with the boundary conditions to mimic the thoracic aorta under the effects of hypertension and hypotension. The results of simulations with realistic models extracted from CT scans demonstrated more realistic flow dynamics than that in the idealized models. During systole, the velocity in ascending aorta was skewed towards the outer wall of aortic arch. The flow develops secondary flow patterns as it moves downstream towards aortic arch. Unlike idealized models, the distribution of flow was nonplanar and heavily guided by the artery anatomy. Flow cavitation was observed in the aorta model which was imaged giving longer branches. This could not be properly observed in the model with imaging containing a shorter length for aortic branches. The flow circulation was also observed in the inner wall of the aortic arch. However, during the diastole, the flow profiles were almost flat and regular due the acceleration of flow at the inlet. The flow profiles were weakly turbulent during the flow reversal. The complex flow patterns caused a non-uniform distribution of WSS. High WSS was distributed at the junction of branches and aortic arch. Low WSS was distributed at the proximal part of the junction, while intermedium WSS was distributed in the distal part of the junction. The pulsatile nature of the inflow caused oscillating WSS at the branch entry region and inner curvature of aortic arch. Based on the WSS distribution in the realistic model, one of the aorta models was altered to induce artificial atherosclerotic plaque at the branch entry region and inner curvature of aortic arch. Atherosclerotic plaque causing 50% blockage of lumen was introduced in brachiocephalic artery, common carotid artery, left subclavian artery, and aortic arch. The aim of this part of the study was first to study the effect of stenosis on flow and WSS distribution, understand the effect of shape of atherosclerotic plaque on flow and WSS distribution, and finally to investigate the effect of lumen blockage severity on flow and WSS distributions. The results revealed that the distribution of WSS is significantly affected by plaque with mere 50% stenosis. The asymmetric shape of stenosis causes higher WSS in branching arteries than in the cases with symmetric plaque. The flow dynamics within thoracic aorta models has been extensively studied and reported here. The effects of pressure and arterial anatomy on the flow dynamic were investigated. The distribution of complex flow and WSS is correlated with the localization of atherosclerosis. With the available results we can conclude that the thoracic aorta, with complex anatomy is the most vulnerable artery for the localization and development of atherosclerosis. The flow dynamics and arterial anatomy play a role in the localization of atherosclerosis. The patient specific image based models can be used to diagnose the locations in the aorta vulnerable to the development of arterial diseases such as atherosclerosis.

Machine vision methods for process measurements in pulping

The papermaking industry has been continuously developing intelligent solutions to characterize the raw materials it uses, to control the manufacturing process in a robust way, and to guarantee the desired quality of the end product. Based on the much improved imaging techniques and image-based analysis methods, it has become possible to look inside the manufacturing pipeline and propose more effective alternatives to human expertise. This study is focused on the development of image analyses methods for the pulping process of papermaking. Pulping starts with wood disintegration and forming the fiber suspension that is subsequently bleached, mixed with additives and chemicals, and finally dried and shipped to the papermaking mills. At each stage of the process it is important to analyze the properties of the raw material to guarantee the product quality. In order to evaluate properties of fibers, the main component of the pulp suspension, a framework for fiber characterization based on microscopic images is proposed in this thesis as the first contribution. The framework allows computation of fiber length and curl index correlating well with the ground truth values. The bubble detection method, the second contribution, was developed in order to estimate the gas volume at the delignification stage of the pulping process based on high-resolution in-line imaging. The gas volume was estimated accurately and the solution enabled just-in-time process termination whereas the accurate estimation of bubble size categories still remained challenging. As the third contribution of the study, optical flow computation was studied and the methods were successfully applied to pulp flow velocity estimation based on double-exposed images. Finally, a framework for classifying dirt particles in dried pulp sheets, including the semisynthetic ground truth generation, feature selection, and performance comparison of the state-of-the-art classification techniques, was proposed as the fourth contribution. The framework was successfully tested on the semisynthetic and real-world pulp sheet images. These four contributions assist in developing an integrated factory-level vision-based process control.

Chromatographic recovery of chemicals from acidic biomass hydrolysates

Lignocellulosic biomasses (e.g., wood and straws) are a potential renewable source for the production of a wide variety of chemicals that could be used to replace those currently produced by petrochemical industry. This would lead to lower greenhouse gas emissions and waste amounts, and to economical savings. There are many possible pathways available for the manufacturing of chemicals from lignocellulosic biomasses. One option is to hydrolyze the cellulose and hemicelluloses of these biomasses into monosaccharides using concentrated sulfuric acid as catalyst. This process is an efficient method for producing monosaccharides which are valuable platforn chemicals. Also other valuable products are formed in the hydrolysis. Unfortunately, the concentrated acid hydrolysis has been deemed unfeasible mainly due to high chemical consumption resulting from the need to remove sulfuric acid from the obtained hydrolysates prior to the downstream processing of the monosaccharides. Traditionally, this has been done by neutralization with lime. This, however, results in high chemical consumption. In addition, the by-products formed in the hydrolysis are not removed and may, thus, hinder the monosaccharide processing. In order to improve the feasibility of the concentrated acid hydrolysis, the chemical consumption should be decreased by recycling of sulfuric acid without neutralization. Furthermore, the monosaccharides and the other products formed in the hydrolysis should be recovered selectively for efficient downstream processing. The selective recovery of the hydrolysis by-products would have additional economical benefits on the process due to their high value. In this work, the use of chromatographic fractionation for the recycling of sulfuric acid and the selective recovery of the main components from the hydrolysates formed in the concentrated acid hydrolysis was investigated. Chromatographic fractionation based on the electrolyte exclusion with gel type strong acid cation exchange resins in acid (H+) form as a stationary phase was studied. A systematic experimental and model-based study regarding the separation task at hand was conducted. The phenomena affecting the separation were determined and their effects elucidated. Mathematical models that take accurately into account these phenomena were derived and used in the simulation of the fractionation process. The main components of the concentrated acid hydrolysates (sulfuric acid, monosaccharides, and acetic acid) were included into this model. Performance of the fractionation process was investigated experimentally and by simulations. Use of different process options was also studied. Sulfuric acid was found to have a significant co-operative effect on the sorption of the other components. This brings about interesting and beneficial effects in the column operations. It is especially beneficial for the separation of sulfuric acid and the monosaccharides. Two different approaches for the modelling of the sorption equilibria were investigated in this work: a simple empirical approach and a thermodynamically consistent approach (the Adsorbed Solution theory). Accurate modelling of the phenomena observed in this work was found to be possible using the simple empirical models. The use of the Adsorbed Solution theory is complicated by the nature of the theory and the complexity of the studied system. In addition to the sorption models, a dynamic column model that takes into account the volume changes of the gel type resins as changing resin bed porosity was also derived. Using the chromatography, all the main components of the hydrolysates can be recovered selectively, and the sulfuric acid consumption of the hydrolysis process can be lowered considerably. Investigation of the performance of the chromatographic fractionation showed that the highest separation efficiency in this separation task is obtained with a gel type resin with a high crosslinking degree (8 wt. %); especially when the hydrolysates contain high amounts of acetic acid. In addition, the concentrated acid hydrolysis should be done with as low sulfuric acid concentration as possible to obtain good separation performance. The column loading and flow rate also have large effects on the performance. In this work, it was demonstrated that when recycling of the fractions obtained in the chromatographic fractionation are recycled to preceding unit operations these unit operations should included in the performance evaluation of the fractionation. When this was done, the separation performance and the feasibility of the concentrated acid hydrolysis process were found to improve considerably. Use of multi-column chromatographic fractionation processes, the Japan Organo process and the Multi-Column Recycling Chromatography process, was also investigated. In the studied case, neither of these processes could compete with the single-column batch process in the productivity. However, due to internal recycling steps, the Multi-Column Recycling Chromatography was found to be superior to the batch process when the product yield and the eluent consumption were taken into account.