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.

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.

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.

Hand tracking in high-speed camera videos

Visual object tracking has been one of the most popular research topics in the field of computer vision recently. Specifically, hand tracking has attracted significant attention since it would enable many useful practical applications. However, hand tracking is still a very challenging problem which cannot be considered solved. The fact that almost every aspect of hand appearance can change is the fundamental reason for this difficulty. This thesis focused on 2D-based hand tracking in high-speed camera videos. During the project, a toolbox for this purpose was collected which contains nine different tracking methods. In the experiments, these methods were tested and compared against each other with both high-speed videos recorded during the project and publicly available normal speed videos. The results revealed that tracking accuracies varied considerably depending on the video and the method. Therefore, no single method was clearly the best in all videos, but three methods, CT, HT, and TLD, performed better than the others overall. Moreover, the results provide insights about the suitability of each method to different types and situations of hand tracking.

Automatic traffic sign inventory- and condition analysis

This thesis researches automatic traffic sign inventory and condition analysis using machine vision and pattern recognition methods. Automatic traffic sign inventory and condition analysis can be used to more efficient road maintenance, improving the maintenance processes, and to enable intelligent driving systems. Automatic traffic sign detection and classification has been researched before from the viewpoint of self-driving vehicles, driver assistance systems, and the use of signs in mapping services. Machine vision based inventory of traffic signs consists of detection, classification, localization, and condition analysis of traffic signs. The produced machine vision system performance is estimated with three datasets, from which two of have been been collected for this thesis. Based on the experiments almost all traffic signs can be detected, classified, and located and their condition analysed. In future, the inventory system performance has to be verified in challenging conditions and the system has to be pilot tested.

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.

Efficient Optimization Algorithms for Nonlinear Data Analysis

Identification of low-dimensional structures and main sources of variation from multivariate data are fundamental tasks in data analysis. Many methods aimed at these tasks involve solution of an optimization problem. Thus, the objective of this thesis is to develop computationally efficient and theoretically justified methods for solving such problems. Most of the thesis is based on a statistical model, where ridges of the density estimated from the data are considered as relevant features. Finding ridges, that are generalized maxima, necessitates development of advanced optimization methods. An efficient and convergent trust region Newton method for projecting a point onto a ridge of the underlying density is developed for this purpose. The method is utilized in a differential equation-based approach for tracing ridges and computing projection coordinates along them. The density estimation is done nonparametrically by using Gaussian kernels. This allows application of ridge-based methods with only mild assumptions on the underlying structure of the data. The statistical model and the ridge finding methods are adapted to two different applications. The first one is extraction of curvilinear structures from noisy data mixed with background clutter. The second one is a novel nonlinear generalization of principal component analysis (PCA) and its extension to time series data. The methods have a wide range of potential applications, where most of the earlier approaches are inadequate. Examples include identification of faults from seismic data and identification of filaments from cosmological data. Applicability of the nonlinear PCA to climate analysis and reconstruction of periodic patterns from noisy time series data are also demonstrated. Other contributions of the thesis include development of an efficient semidefinite optimization method for embedding graphs into the Euclidean space. The method produces structure-preserving embeddings that maximize interpoint distances. It is primarily developed for dimensionality reduction, but has also potential applications in graph theory and various areas of physics, chemistry and engineering. Asymptotic behaviour of ridges and maxima of Gaussian kernel densities is also investigated when the kernel bandwidth approaches infinity. The results are applied to the nonlinear PCA and to finding significant maxima of such densities, which is a typical problem in visual object tracking.

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.

Eye Fundus Image Analysis for Automatic Detection of Diabetic Retinopathy

Diabetes is a rapidly increasing worldwide problem which is characterised by defective metabolism of glucose that causes long-term dysfunction and failure of various organs. The most common complication of diabetes is diabetic retinopathy (DR), which is one of the primary causes of blindness and visual impairment in adults. The rapid increase of diabetes pushes the limits of the current DR screening capabilities for which the digital imaging of the eye fundus (retinal imaging), and automatic or semi-automatic image analysis algorithms provide a potential solution. In this work, the use of colour in the detection of diabetic retinopathy is statistically studied using a supervised algorithm based on one-class classification and Gaussian mixture model estimation. The presented algorithm distinguishes a certain diabetic lesion type from all other possible objects in eye fundus images by only estimating the probability density function of that certain lesion type. For the training and ground truth estimation, the algorithm combines manual annotations of several experts for which the best practices were experimentally selected. By assessing the algorithm’s performance while conducting experiments with the colour space selection, both illuminance and colour correction, and background class information, the use of colour in the detection of diabetic retinopathy was quantitatively evaluated. Another contribution of this work is the benchmarking framework for eye fundus image analysis algorithms needed for the development of the automatic DR detection algorithms. The benchmarking framework provides guidelines on how to construct a benchmarking database that comprises true patient images, ground truth, and an evaluation protocol. The evaluation is based on the standard receiver operating characteristics analysis and it follows the medical practice in the decision making providing protocols for image- and pixel-based evaluations. During the work, two public medical image databases with ground truth were published: DIARETDB0 and DIARETDB1. The framework, DR databases and the final algorithm, are made public in the web to set the baseline results for automatic detection of diabetic retinopathy. Although deviating from the general context of the thesis, a simple and effective optic disc localisation method is presented. The optic disc localisation is discussed, since normal eye fundus structures are fundamental in the characterisation of DR.

The neural processes generating visual phenomenal consciousness: ERP and neuronavigated brain stimulation studies

One of the greatest conundrums to the contemporary science is the relation between consciousness and brain activity, and one of the specifi c questions is how neural activity can generate vivid subjective experiences. Studies focusing on visual consciousness have become essential in solving the empirical questions of consciousness. Th e main aim of this thesis is to clarify the relation between visual consciousness and the neural and electrophysiological processes of the brain. By applying electroencephalography and functional magnetic resonance image-guided transcranial magnetic stimulation (TMS), we investigated the links between conscious perception and attention, the temporal evolution of visual consciousness during stimulus processing, the causal roles of primary visual cortex (V1), visual area 2 (V2) and lateral occipital cortex (LO) in the generation of visual consciousness and also the methodological issues concerning the accuracy of targeting TMS to V1. Th e results showed that the fi rst eff ects of visual consciousness on electrophysiological responses (about 140 ms aft er the stimulus-onset) appeared earlier than the eff ects of selective attention, and also in the unattended condition, suggesting that visual consciousness and selective attention are two independent phenomena which have distinct underlying neural mechanisms. In addition, while it is well known that V1 is necessary for visual awareness, the results of the present thesis suggest that also the abutting visual area V2 is a prerequisite for conscious perception. In our studies, the activation in V2 was necessary for the conscious perception of change in contrast for a shorter period of time than in the case of more detailed conscious perception. We also found that TMS in LO suppressed the conscious perception of object shape when TMS was delivered in two distinct time windows, the latter corresponding with the timing of the ERPs related to the conscious perception of coherent object shape. Th e result supports the view that LO is crucial in conscious perception of object coherency and is likely to be directly involved in the generation of visual consciousness. Furthermore, we found that visual sensations, or phosphenes, elicited by the TMS of V1 were brighter than identically induced phosphenes arising from V2. Th ese fi ndings demonstrate that V1 contributes more to the generation of the sensation of brightness than does V2. Th e results also suggest that top-down activation from V2 to V1 is probably associated with phosphene generation. The results of the methodological study imply that when a commonly used landmark (2 cm above the inion) is used in targeting TMS to V1, the TMS-induced electric fi eld is likely to be highest in dorsal V2. When V1 was targeted according to the individual retinotopic data, the electric fi eld was highest in V1 only in half of the participants. Th is result suggests that if the objective is to study the role of V1 with TMS methodology, at least functional maps of V1 and V2 should be applied with computational model of the TMS-induced electric fi eld in V1 and V2. Finally, the results of this thesis imply that diff erent features of attention contribute diff erently to visual consciousness, and thus, the theoretical model which is built up of the relationship between visual consciousness and attention should acknowledge these diff erences. Future studies should also explore the possibility that visual consciousness consists of several processing stages, each of which have their distinct underlying neural mechanisms.

Measuring Effectiveness of Marketing Message: The Role of Verbal, Visual and Brand Elements

The aim of this paper is to study the role of verbal, visual and brand elements while meas-uring effectiveness of marketing message. The thesis is written in the context of mobile gaming industry. The object of the study is marketing message. To achieve the aim, the main research question was formulated: How do the elements of marketing message, such as verbal, visual and brand, affect the consumer’s attitude toward the ad, emotional response and attention capture? The theory development chapter lays on three corner stones – analysis of previous litera-ture on marketing message and its elements, namely verbal, visual and brand; overview of literature on attitude formation and particularly attitude toward the ad. In addition, investiga-tion of key points of emotional response and attention capture literature finalizes the chap-ter. The empirical part consists of experiment, conducted with 27 participants. Experiment includes the self-report semantically anchored scale, measuring the attitude toward the ad, as well as autonomic measures – eye tracking (attention capture) and facial expressions (emotional response). The results of the experiment showed that the size of the brand element – the logo – has an effect on the attention capture and the overall attitude toward the ad. The bigger the logo, the more time people spend viewing it, and they realise the message is more educa-tional and factual. The measure related to the visual element – the visual complexity – in-creases the intensity of participant’s facial expression. While the measure of verbal ele-ment – the contrast between text and background colours – leads to a better attitude to-ward the ad. The higher the contrast between text and background, the more known the message appears to the viewer.

Hardware Accelarated Visual Tracking Algorithms. A Systematic Literature Review

Many industrial applications need object recognition and tracking capabilities. The algorithms developed for those purposes are computationally expensive. Yet ,real time performance, high accuracy and small power consumption are essential measures of the system. When all these requirements are combined, hardware acceleration of these algorithms becomes a feasible solution. The purpose of this study is to analyze the current state of these hardware acceleration solutions, which algorithms have been implemented in hardware and what modifications have been done in order to adapt these algorithms to hardware.