Comparison of Local Feature Detectors and Descriptors for Visual Object Categorization

Local features are used in many computer vision tasks including visual object categorization, content-based image retrieval and object recognition to mention a few. Local features are points, blobs or regions in images that are extracted using a local feature detector. To make use of extracted local features the localized interest points are described using a local feature descriptor. A descriptor histogram vector is a compact representation of an image and can be used for searching and matching images in databases. In this thesis the performance of local feature detectors and descriptors is evaluated for object class detection task. Features are extracted from image samples belonging to several object classes. Matching features are then searched using random image pairs of a same class. The goal of this thesis is to find out what are the best detector and descriptor methods for such task in terms of detector repeatability and descriptor matching rate.

Bag-of-Features Approach to Unsupervised Visual Object Categorisation

The large and growing number of digital images is making manual image search laborious. Only a fraction of the images contain metadata that can be used to search for a particular type of image. Thus, the main research question of this thesis is whether it is possible to learn visual object categories directly from images. Computers process images as long lists of pixels that do not have a clear connection to high-level semantics which could be used in the image search. There are various methods introduced in the literature to extract low-level image features and also approaches to connect these low-level features with high-level semantics. One of these approaches is called Bag-of-Features which is studied in the thesis. In the Bag-of-Features approach, the images are described using a visual codebook. The codebook is built from the descriptions of the image patches using clustering. The images are described by matching descriptions of image patches with the visual codebook and computing the number of matches for each code. In this thesis, unsupervised visual object categorisation using the Bag-of-Features approach is studied. The goal is to find groups of similar images, e.g., images that contain an object from the same category. The standard Bag-of-Features approach is improved by using spatial information and visual saliency. It was found that the performance of the visual object categorisation can be improved by using spatial information of local features to verify the matches. However, this process is computationally heavy, and thus, the number of images must be limited in the spatial matching, for example, by using the Bag-of-Features method as in this study. Different approaches for saliency detection are studied and a new method based on the Hessian-Affine local feature detector is proposed. The new method achieves comparable results with current state-of-the-art. The visual object categorisation performance was improved by using foreground segmentation based on saliency information, especially when the background could be considered as clutter.

Local Features in Image and Video Processing - Object Class Matching and Video Shot Detection

The usage of digital content, such as video clips and images, has increased dramatically during the last decade. Local image features have been applied increasingly in various image and video retrieval applications. This thesis evaluates local features and applies them to image and video processing tasks. The results of the study show that 1) the performance of different local feature detector and descriptor methods vary significantly in object class matching, 2) local features can be applied in image alignment with superior results against the state-of-the-art, 3) the local feature based shot boundary detection method produces promising results, and 4) the local feature based hierarchical video summarization method shows promising new new research direction. In conclusion, this thesis presents the local features as a powerful tool in many applications and the imminent future work should concentrate on improving the quality of the local features.

Generative Part-Based Gabor Object Detector

Object detection is a fundamental task of computer vision that is utilized as a core part in a number of industrial and scientific applications, for example, in robotics, where objects need to be correctly detected and localized prior to being grasped and manipulated. Existing object detectors vary in (i) the amount of supervision they need for training, (ii) the type of a learning method adopted (generative or discriminative) and (iii) the amount of spatial information used in the object model (model-free, using no spatial information in the object model, or model-based, with the explicit spatial model of an object). Although some existing methods report good performance in the detection of certain objects, the results tend to be application specific and no universal method has been found that clearly outperforms all others in all areas. This work proposes a novel generative part-based object detector. The generative learning procedure of the developed method allows learning from positive examples only. The detector is based on finding semantically meaningful parts of the object (i.e. a part detector) that can provide additional information to object location, for example, pose. The object class model, i.e. the appearance of the object parts and their spatial variance, constellation, is explicitly modelled in a fully probabilistic manner. The appearance is based on bio-inspired complex-valued Gabor features that are transformed to part probabilities by an unsupervised Gaussian Mixture Model (GMM). The proposed novel randomized GMM enables learning from only a few training examples. The probabilistic spatial model of the part configurations is constructed with a mixture of 2D Gaussians. The appearance of the parts of the object is learned in an object canonical space that removes geometric variations from the part appearance model. Robustness to pose variations is achieved by object pose quantization, which is more efficient than previously used scale and orientation shifts in the Gabor feature space. Performance of the resulting generative object detector is characterized by high recall with low precision, i.e. the generative detector produces large number of false positive detections. Thus a discriminative classifier is used to prune false positive candidate detections produced by the generative detector improving its precision while keeping high recall. Using only a small number of positive examples, the developed object detector performs comparably to state-of-the-art discriminative methods.

Muon detector link system test set-up

CERNin tutkimuskeskuksen rakenteilla olevan hadronikiihdyttimen eräs tarkoitus on todistaa Higgsin bosonin olemassaolo. Higgsin bosonin löytyminen yhtenäistäisi nykyisen hiukkasfysiikan teorian ja antaisi selityksen sille kuinka hiukkaset saavat massansa. Kiihdyttimen CMS koeasema on tarkoitettu erityisesti myonien ilmaisuun. Tämä työ liittyy CMS koeaseman RPC-ilmaisintyypin linkkijärjestelmään, jonka tarkoituksena on käsitellä ilmaisimelta tulevia myonien aiheuttamia signaaleja ja lähettää tiedot tärkeäksi katsotuista törmäystapahtumista tallennettavaksi analysointia varten. Työssä on toteutettu linkkijärjestelmän ohjaus- ja linkkikorteille testiympäristö, jolla voidaan todeta järjestelmän eri osien keskinäinen yhteensopivuus ja toimivuus. Työn alkuosassa esitellään ilmaisimen linkkijärjestelmän eri osat ja niiden merkitykset. Työn loppuosassa käydään läpi eri testimenetelmiä ja analysoidaan niiden antamia tuloksia.

Muon Detector Link System Test Setup Software

Euroopan hiukkastutkimuslaitoksen CERNin rakenteilla olevan LHC-hiukkaskiihdyttimen CMS-koeasema on tarkoitettu erityisesti myonin ilmaisuun. Tässä työssä on esitelty CMS-koeaseman RPC-ilmaisintyypin linkkijärjestelmä ja sen testaamiseen tarkoitetut laitteet sekä laitteiden testaamiseen tarvittavat ohjelmistot. Työssä on selvitetty ohjelmien toimivuus ja keskinäinen yhteensopivuus.

Supervised localimage feature detection

This thesis is about detection of local image features. The research topic belongs to the wider area of object detection, which is a machine vision and pattern recognition problem where an object must be detected (located) in an image. State-of-the-art object detection methods often divide the problem into separate interest point detection and local image description steps, but in this thesis a different technique is used, leading to higher quality image features which enable more precise localization. Instead of using interest point detection the landmark positions are marked manually. Therefore, the quality of the image features is not limited by the interest point detection phase and the learning of image features is simplified. The approach combines both interest point detection and local description into one phase for detection. Computational efficiency of the descriptor is therefore important, leaving out many of the commonly used descriptors as unsuitably heavy. Multiresolution Gabor features has been the main descriptor in this thesis and improving their efficiency is a significant part. Actual image features are formed from descriptors by using a classifierwhich can then recognize similar looking patches in new images. The main classifier is based on Gaussian mixture models. Classifiers are used in one-class classifier configuration where there are only positive training samples without explicit background class. The local image feature detection method has been tested with two freely available face detection databases and a proprietary license plate database. The localization performance was very good in these experiments. Other applications applying the same under-lying techniques are also presented, including object categorization and fault detection.

Local and Global Feature Extraction for Invariant Object Recognition

Perceiving the world visually is a basic act for humans, but for computers it is still an unsolved problem. The variability present innatural environments is an obstacle for effective computer vision. The goal of invariant object recognition is to recognise objects in a digital image despite variations in, for example, pose, lighting or occlusion. In this study, invariant object recognition is considered from the viewpoint of feature extraction. Thedifferences between local and global features are studied with emphasis on Hough transform and Gabor filtering based feature extraction. The methods are examined with respect to four capabilities: generality, invariance, stability, and efficiency. Invariant features are presented using both Hough transform and Gabor filtering. A modified Hough transform technique is also presented where the distortion tolerance is increased by incorporating local information. In addition, methods for decreasing the computational costs of the Hough transform employing parallel processing and local information are introduced.

Modelling additional costs caused by a new product feature

Työn tavoitteena oli mallintaa uuden tuoteominaisuuden aiheuttamat lisäkustannukset ja suunnitella päätöksenteon työkalu Timberjack Oy:n kuormatraktorivalmistuksen johtoryhmälle. Tarkoituksena oli luoda karkean tason malli, joka sopisi eri tyyppisten tuoteominaisuuksien kustannuksien selvittämiseen. Uuden tuoteominaisuuden vaikutusta yrityksen eri toimintoihin selvitettiin haastatteluin. Haastattelukierroksen tukena käytettiin kysymyslomaketta. Haastattelujen tavoitteena oli selvittää prosessit, toiminnot ja resurssit, jotka ovat välttämättömiä uuden tuoteominaisuuden tuotantoon saattamisessa ja tuotannossa. Malli suunniteltiin haastattelujen ja tietojärjestelmästä hankitun tiedon pohjalta. Mallin rungon muodostivat ne prosessit ja toiminnot, joihin uudella tuoteominaisuudella on vaikutusta. Huomioon otettiin sellaiset resurssit, joita uusi tuoteominaisuus kuluttaa joko välittömästi, tai välillisesti. Tarkasteluun sisällytettiin ainoastaan lisäkustannukset. Uuden tuoteominaisuuden toteuttamisesta riippumattomat, joka tapauksessa toteutuvat yleiskustannukset jätettiin huomioimatta. Malli on yleistys uuden tuoteominaisuuden aiheuttamista lisäkustannuksista, koska tarkoituksena on, että se sopii eri tyyppisten tuoteominaisuuksien aiheuttamien kustannusten selvittämiseen. Lisäksi malli soveltuu muiden pienehköjen tuotemuutosten kustannusten kartoittamiseen.

Particle detector link system modifications in RE1/1 sector

The large hadron collider constructed at the European organization for nuclear research, CERN, is the world’s largest single measuring instrument ever built, and also currently the most powerful particle accelerator that exists. The large hadron collider includes six different experiment stations, one of which is called the compact muon solenoid, or the CMS. The main purpose of the CMS is to track and study residue particles from proton-proton collisions. The primary detectors utilized in the CMS are resistive plate chambers (RPCs). To obtain data from these detectors, a link system has been designed. The main idea of the link system is to receive data from the detector front-end electronics in parallel form, and to transmit it onwards in serial form, via an optical fiber. The system is mostly ready and in place. However, a problem has occurred with innermost RPC detectors, located in sector labeled RE1/1; transmission lines for parallel data suffer from signal integrity issues over long distances. As a solution to this, a new version of the link system has been devised, a one that fits in smaller space and can be located within the CMS, closer to the detectors. This RE1/1 link system has been so far completed only partially, with just the mechanical design and casing being done. In this thesis, link system electronics for RE1/1 sector has been designed, by modifying the existing link system concept to better meet the requirements of the RE1/1 sector. In addition to completion of the prototype of the RE1/1 link system electronics, some testing for the system has also been done, to ensure functionality of the design.

Electric field distribution in silicon edgeless detector

This Master’s Thesis work reports about electric field distribution in recently developed silicon edgeless detector with a new current terminating structure. This structure enables the essential reduction of insensitive detector area as well as allows separation of the current flowing through the active area from the current flowing at the cut edge. The reliable operation of this detector is strongly needed due to the installation inside LHC. In accordance with formulated problems SEM was used as an investigation tool for collecting the data about electric field distribution.

The Detector Control Systems for the CMS Resistive Plate Chamber at LHC

The RPC Detector Control System (RCS) is the main subject of this PhD work. The project, involving the Lappeenranta University of Technology, the Warsaw University and INFN of Naples, is aimed to integrate the different subsystems for the RPC detector and its trigger chain in order to develop a common framework to control and monitoring the different parts. In this project, I have been strongly involved during the last three years on the hardware and software development, construction and commissioning as main responsible and coordinator. The CMS Resistive Plate Chambers (RPC) system consists of 912 double-gap chambers at its start-up in middle of 2008. A continuous control and monitoring of the detector, the trigger and all the ancillary sub-systems (high voltages, low voltages, environmental, gas, and cooling), is required to achieve the operational stability and reliability of a so large and complex detector and trigger system. Role of the RPC Detector Control System is to monitor the detector conditions and performance, control and monitor all subsystems related to RPC and their electronics and store all the information in a dedicated database, called Condition DB. Therefore the RPC DCS system has to assure the safe and correct operation of the sub-detectors during all CMS life time (more than 10 year), detect abnormal and harmful situations and take protective and automatic actions to minimize consequential damages. The analysis of the requirements and project challenges, the architecture design and its development as well as the calibration and commissioning phases represent themain tasks of the work developed for this PhD thesis. Different technologies, middleware and solutions has been studied and adopted in the design and development of the different components and a big challenging consisted in the integration of these different parts each other and in the general CMS control system and data acquisition framework. Therefore, the RCS installation and commissioning phase as well as its performance and the first results, obtained during the last three years CMS cosmic runs, will be

Feature selection using Fuzzy Entropy measures with Yu's Similarity measure

In this study, feature selection in classification based problems is highlighted. The role of feature selection methods is to select important features by discarding redundant and irrelevant features in the data set, we investigated this case by using fuzzy entropy measures. We developed fuzzy entropy based feature selection method using Yu's similarity and test this using similarity classifier. As the similarity classifier we used Yu's similarity, we tested our similarity on the real world data set which is dermatological data set. By performing feature selection based on fuzzy entropy measures before classification on our data set the empirical results were very promising, the highest classification accuracy of 98.83% was achieved when testing our similarity measure to the data set. The achieved results were then compared with some other results previously obtained using different similarity classifiers, the obtained results show better accuracy than the one achieved before. The used methods helped to reduce the dimensionality of the used data set, to speed up the computation time of a learning algorithm and therefore have simplified the classification task

The Design and Implementation of a Power Management Feature to a Configuration Management System

Green IT is a term that covers various tasks and concepts that are related to reducing the environmental impact of IT. At enterprise level, Green IT has significant potential to generate sustainable cost savings: the total amount of devices is growing and electricity prices are rising. The lifecycle of a computer can be made more environmentally sustainable using Green IT, e.g. by using energy efficient components and by implementing device power management. The challenge using power management at enterprise level is how to measure and follow-up the impact of power management policies? During the thesis a power management feature was developed to a configuration management system. The feature can be used to automatically power down and power on PCs using a pre-defined schedule and to estimate the total power usage of devices. Measurements indicate that using the feature the device power consumption can be monitored quite precisely and the power consumption can be reduced, which generates electricity cost savings and reduces the environmental impact of IT.

Scaling up stepwise feature introduction to construction of large software systems

Developing software is a difficult and error-prone activity. Furthermore, the complexity of modern computer applications is significant. Hence,an organised approach to software construction is crucial. Stepwise Feature Introduction – created by R.-J. Back – is a development paradigm, in which software is constructed by adding functionality in small increments. The resulting code has an organised, layered structure and can be easily reused. Moreover, the interaction with the users of the software and the correctness concerns are essential elements of the development process, contributing to high quality and functionality of the final product. The paradigm of Stepwise Feature Introduction has been successfully applied in an academic environment, to a number of small-scale developments. The thesis examines the paradigm and its suitability to construction of large and complex software systems by focusing on the development of two software systems of significant complexity. Throughout the thesis we propose a number of improvements and modifications that should be applied to the paradigm when developing or reengineering large and complex software systems. The discussion in the thesis covers various aspects of software development that relate to Stepwise Feature Introduction. More specifically, we evaluate the paradigm based on the common practices of object-oriented programming and design and agile development methodologies. We also outline the strategy to testing systems built with the paradigm of Stepwise Feature Introduction.