Search

Monitoring plankton is important as they are an essential part of the aquatic food web as well as producers of oxygen. Modern imaging devices produce a massive amount of plankton image data which calls for automatic solutions. These images are characterized by a very large variation in both the size and the aspect ratio. Convolutional neural network (CNN) based classification methods, on the other hand, typically require a fixed size input. Simple scaling of the images into a common size contains several drawbacks. First, the information about the size of the plankton is lost. For human experts, the size information is one of the most important cues for identifying the species. Second, downscaling the images leads to the loss of fine details such as flagella essential for species recognition. Third, upscaling the images increases the size of the network. In this work, extensive experiments on various approaches to address the varying image dimensions are carried out on a challenging phytoplankton image dataset. A novel combination of methods is proposed, showing improvement over the baseline CNN. Post-print / Final draft

Plankton communities form the basis of aquatic ecosystems and elucidating their role in increasingly important environmental issues is a constantly present research question. The concealed plankton community dynamics reflect changes in environmental forcing, growth traits of competing species, and multiple food web interactions. Recent technological advances have led to the possibility of collecting real-time big data opening new horizons for testing core hypotheses in planktonic systems, derived from macroscopic realms, in community ecology, biodiversity research, and ecosystem functioning. Analyzing the big data calls for computer vision and machine learning methods capable of producing interoperable data across platforms and systems. In this paper we apply convolutional neural networks (CNN) to classify a brackish-water phytoplankton community in the Baltic Sea. For solving the classification task, we utilize compact CNN architectures requiring less computational capacity and creating an opportunity to quickly train the network. This makes it possible to (1) test various modifications to the classification method, and (2) repeat each experiment multiple times with different training and test set combinations to obtain reliable results. We further analyze the effect of large class imbalance to the CNN performance, and test relevant data augmentation techniques to improve the performance. Finally, we address the practical implications of the classification performance to aquatic research by analyzing the confused classes and their effect on the reliability of the automatic plankton recognition system, to guide further development of plankton recognition research. Our results show that it is possible to obtain good classification accuracy with relatively shallow architectures and a small amount of training data when using effective data augmentation methods even with a very unbalanced dataset.

In this paper we propose a method to match pelage patterns of the Saimaa ringed seals enabling the re-identification of individuals. First, the pelage pattern is extracted from the seal's fur using a method based on the Sato tubeness filter. After this, the similarities of the pelage pattern patches are computed using a siamese network trained with a triplet loss function and a large dataset of manually selected patches. The similarities are then used to find the best matching patches from the images in the database of known individuals. Furthermore, we employ the proposed pattern matching method to build a full framework for the ringed seal re-identification, consisting of CNN-based animal segmentation, patch correspondence detection, and ranking the images in the database of known seal individuals based on the similarity to the query image. Our experiments on challenging datasets of Saimaa ringed seals show that the proposed method achieves promising identification results, providing a useful tool for the Saimaa ringed seal monitoring. Post-print / Final draft

The recent surge of interest towards the paradoxical pleasure produced by sad music has generated a handful of theories and an array of empirical explorations on the topic. However, none of these have attempted to weigh the existing evidence in a systematic fashion. The present work puts forward an integrative framework laid out over three levels of explanation – biological, psycho-social, and cultural – to compare and integrate the existing findings in a meaningful way. First, we review the evidence pertinent to experiences of pleasure associated with sad music from the fields of neuroscience, psychophysiology, and endocrinology. Then, the psychological and interpersonal mechanisms underlying the recognition and induction of sadness in the context of music are combined with putative explanations ranging from social surrogacy and nostalgia to feelings of being moved. Finally, we address the cultural aspects of the paradox – the extent to which it is embedded in the Western notion of music as an aesthetic, contemplative object – by synthesising findings from history, ethnography, and empirical studies. Furthermore, we complement these explanations by considering the particularly significant meanings that sadness portrayed in art can evoke in some perceivers. Our central claim is that one cannot attribute the enjoyment of sadness fully to any one of these levels, but to a chain of functionalities afforded by each level. Each explanatory level has several putative explanations and its own shift towards positive valence, but none of them deliver the full transformation from a highly negative experience to a fully enjoyable experience alone. The current evidence within this framework ranges from weak to non-existent at the biological level, moderate at the psychological level, and suggestive at the cultural level. We propose a series of focussed topics for future investigation that would allow to deconstruct the drivers and constraints of the processes leading to pleasurable music-related sadness. peerReviewed

Detection, counting and characterization of bubbles, that is, transparent objects in a liquid, is important in many industrial applications. These applications include monitoring of pulp delignification and multiphase dispersion processes common in the chemical, pharmaceutical, and food industries. Typically the aim is to measure the bubble size distribution. In this paper, we present a comprehensive comparison of bubble detection methods for challenging industrial image data. Moreover, we compare the detection-based methods to a direct bubble size distribution estimation method that does not require the detection of individual bubbles. The experiments showed that the approach based on a convolutional neural network (CNN) outperforms the other methods in detection accuracy. However, the boosting-based approaches were remarkably faster to compute. The power spectrum approach for direct bubble size distribution estimation produced accurate distributions and it is fast to compute, but it does not provide the spatial locations of the bubbles. Selecting the most suitable method depends on the specific application.

Pectoral muscle segmentation is a crucial step in various computer-aided applications of breast Magnetic Resonance Imaging (MRI). Due to imaging artifact and homogeneity between the pectoral and breast regions, the pectoral muscle boundary estimation is not a trivial task. In this paper, a fully automatic segmentation method based on deep learning is proposed for accurate delineation of the pectoral muscle boundary in axial breast MR images. The proposed method involves two main steps: pectoral muscle segmentation and boundary estimation. For pectoral muscle segmentation, a model based on the U-Net architecture is used to segment the pectoral muscle from the input image. Next, the pectoral muscle boundary is estimated through candidate points detection and contour segmentation. The proposed method was evaluated quantitatively with two real-world datasets, our own private dataset, and a publicly available dataset. The first dataset includes 12 patients breast MR images and the second dataset consists of 80 patients breast MR images. The proposed method achieved a Dice score of 95% in the first dataset and 89% in the second dataset. The high segmentation performance of the proposed method when evaluated on large scale quantitative breast MR images confirms its potential applicability in future breast cancer clinical applications. Post-print / Final draft

Transmission electron microscopy (TEM) provides information about Inorganic nanoparticles that no other method is able to deliver. Yet, a major task when studying Inorganic nanoparticles using TEM is the automated analysis of the images, i.e. segmentation of individual nanoparticles. The current state-of-the-art methods generally rely on binarization routines that require parameterization, and on methods to segment the overlapping nanoparticles (NPs) using highly idealized nanoparticle shape models. It is unclear, however, that there is any way to determine the best set of parameters providing an optimal segmentation, given the great diversity of NPs characteristics, such as shape and size, that may be encountered. Towards remedying these barriers, this paper introduces a method for segmentation of NPs in Bright Field (BF) TEM images. The proposed method involves three main steps: binarization, contour evidence extraction, and contour estimation. For the binarization, a model based on the U-Net architecture is trained to convert an input image into its binarized version. The contour evidence extraction starts by recovering contour segments from a binarized image using concave contour points detection. The contour segments which belong to the same nanoparticle are grouped in the segment grouping step. The grouping is formulated as a combinatorial optimization problem and solved using the well-known branch and bound algorithm. Finally, the full contours of the NPs are estimated by an ellipse. The experiments on a real-world dataset consisting of 150 BF TEM images containing approximately 2,700 NPs show that the proposed method outperforms five current state-of-art approaches in the overlapping NPs segmentation. Post-print / Final draft

This paper considers the wood species identification from images of boards. The identification using only visual features of the surface is a challenging task even for an expert. The task becomes especially difficult when the wood species are from the same family. We propose a CNN based framework for the fine-grained classification of wood species. The framework includes a patch extraction procedure where board images are divided into image patches. Each patch is separately classified using the CNN resulting in multiple classification results per board. Finally, the patch classification results for a single board are combined. We evaluate various CNN architectures using the challenging data, consisting of species from the Pinaceae family. In addition, we propose three alternative decision rules for combining the patch classification results. By selecting a suitable amount of image patches, the proposed framework was able to achieve over 99% identification accuracy and real-time performance. Post-print / Final draft

The quality control of timber products is vital for the sawmill industry pursuing more efficient production processes. This paper considers the automatic detection of mechanical damages in wooden board surfaces occurred during the sawing process. Due to the high variation in the appearance of the mechanical damages and the presence of several other surface defects on the boards, the detection task is challenging. In this paper, an efficient convolutional neural network based framework that can be trained with a limited amount of annotated training data is proposed. The framework includes a patch extraction step to produce multiple training samples from each damaged region in the board images, followed by the patch classification and damage localization steps. In the experiments, multiple network architectures were compared: the VGG-16 architecture achieved the best results with over 92% patch classification accuracy and it enabled accurate localization of the mechanical damages. Post-print / Final draft

Tracking timber in the sawmill environment from the raw material (logs) to the end product (boards) provides various benefits including efficient process control, the optimization of sawing, and the prediction of end-product quality. In practice, the tracking of timber through the sawmilling process requires a methodology for tracing the source of materials after each production step. The tracing is especially difficult through the actual sawing step where a method is needed for identifying from which log each board comes from. In this paper, we propose an automatic method for board identification (board-to-log matching) using the existing sensors in sawmills and multimodal encoder-decoder networks. The method utilizes point clouds from laser scans of log surfaces and grayscale images of boards. First, log surface heightmaps are generated from the point clouds. Then both the heightmaps and board images are converted into ”barcode” images using convolutional encoder-decoder networks. Finally, the ”barcode” images are utilized to find matching logs for the boards. In the experimental part of the work, different encoderdecoder architectures were evaluated and the effectiveness of the proposed method was demonstrated using challenging data collected from a real sawmill. Post-print / Final draft

Material flow characterization is important in the process industries and its further automation. In this study, close-to-laminar pulp suspension flows are analyzed based on double-exposure images captured in laboratory conditions. The correlation-based methods including autocorrelation and the particle image pattern technique were studied. During the experiments, synthetic and real test data with manual ground truth were used. The particle image pattern matching method showed better performance achieving the accuracy of 90.0% for the real data set with linear motion of the suspension and 79.2% for the data set with flow distortions.

Segmentation of partially overlapping objects with a known shape is needed in an increasing amount of various machine vision applications. This paper presents a method for segmentation of clustered partially overlapping objects with a shape that can be approximated using an ellipse. The method utilizes silhouette images, which means that it requires only that the foreground (objects) and background can be distinguished from each other. The method starts with seedpoint extraction using bounded erosion and fast radial symmetry transform. Extracted seedpoints are then utilized to associate edge points to objects in order to create contour evidence. Finally, contours of the objects are estimated by fitting ellipses to the contour evidence. The experiments on one synthetic and two different real data sets showed that the proposed method outperforms two current state-of-art approaches in overlapping objects segmentation.

Segmentation of overlapping convex objects has various applications, for example, in nanoparticles and cell imaging. Often the segmentation method has to rely purely on edges between the background and foreground making the analyzed images essentially silhouette images. Therefore, to segment the objects, the method needs to be able to resolve the overlaps between multiple objects by utilizing prior information about the shape of the objects. This paper introduces a novel method for segmentation of clustered partially overlapping convex objects in silhouette images. The proposed method involves three main steps: pre-processing, contour evidence extraction, and contour estimation. Contour evidence extraction starts by recovering contour segments from a binarized image by detecting concave points. After this, the contour segments which belong to the same objects are grouped. The grouping is formulated as a combinatorial optimization problem and solved using the branch and bound algorithm. Finally, the full contours of the objects are estimated by a Gaussian process regression method. The experiments on a challenging dataset consisting of nanoparticles demonstrate that the proposed method outperforms three current state-of-art approaches in overlapping convex objects segmentation. The method relies only on edge information and can be applied to any segmentation problems where the objects are partially overlapping and have a convex shape., Comment: 16 pages, 11 Figures

Counting and tracking fish populations is important for conservation purposes as well as for the fishing industry. Various non-invasive automatic fish counters exist based on such principles as resistivity, light beams and sonar. However, such methods typically cannot make distinction between fish and other passing objects, and moreover, cannot recognize different species. Computer vision techniques provide an attractive alternative for building a more robust and versatile fish counting systems. In this paper we present the fish detection framework for noisy videos captured in water with low visibility. For this purpose, we compare three background subtraction methods for the task. Moreover, we propose necessary post-processing steps and heuristics to detect the fish and separate them from other moving objects. The results showed that by choosing an appropriate background subtraction method, it is possible to achieve a satisfying detection accuracy of 80% and 60% for two challenging datasets. The proposed method will form a basis for the future development of fish species identification methods.

The conservation efforts of the endangered Saimaa ringed seal depend on the ability to reliably estimate the population size and to track individuals. Wildlife photo-identification has been successfully utilized in monitoring for various species. Traditionally, the collected images have been analyzed by biologists. However, due to the rapid increase in the amount of image data, there is a demand for automated methods. Ringed seals have pelage patterns that are unique to each seal enabling the individual identification. In this work, two methods of Saimaa ringed seal identification based on transfer learning are proposed. The first method involves retraining of an existing convolutional neural network (CNN). The second method uses the CNN trained for image classification to extract features which are then used to train a Support Vector Machine (SVM) classifier. Both approaches show over 90% identification accuracy on challenging image data, the SVM based method being slightly better.

This paper considers the usability of stereoscopic 3D touch displays. For this purpose extensive subjective experiments were carried out and the hand movements of test subjects were recorded using a two-camera setup consisting of a high-speed camera and a standard RGB video camera with different viewing angles. This produced a large amount of video data that is very laborious to analyze manually which motivates the development of automated methods. In this paper, we propose a method for automatic video synchronization for the two cameras to enable 3D trajectory reconstruction. This together with proper finger tracking and trajectory processing techniques form a fully automated measurement framework for hand movements. We evaluated the proposed method with a large amount of hand movement videos and demonstrated its accuracy on 3D trajectory reconstruction. Finally, we computed a set of hand trajectory features from the data and show that certain features, such as the mean and maximum velocity differ statistically significantly between different target object disparity categories. With small modifications, the framework can be utilized in other similar HCI studies.

Wildlife photo-identification is a commonly used technique to track animal populations over time. Nowadays, due to large image data sets, automated photo-identification is an emerging research topic. To improve the accuracy of identification methods, it is useful to segment the animal from the background. In this paper we evaluate the suitability of co-segmentation methods for this purpose. The basic idea in co-segmentation is to detect and to segment the common object in a set of images despite the different appearance of the object and different backgrounds. Such methods provide a promising approach to process large photo-identification databases for which manual or even semi-manual approaches are very time-consuming by making it unnecessary to annotate images to train supervised segmentation methods. We compare existing co-segmentation methods on challenging wildlife photo-identification images and show that the best methods obtain promising results on the task.

The measurement and tracking of body movement within musical performances can provide valuable sources of data for studying interpersonal interaction and coordination between musicians. The continued development of tools to extract such data from video recordings will offer new opportunities to research musical movement across a diverse range of settings, including field research and other ecological contexts in which the implementation of complex motion capture systems is not feasible or affordable. Such work might also make use of the multitude of video recordings of musical performances that are already available to researchers. The present study made use of such existing data, specifically, three video datasets of ensemble performances from different genres, settings, and instrumentation (a pop piano duo, three jazz duos, and a string quartet). Three different computer vision techniques were applied to these video datasets—frame differencing, optical flow, and kernelized correlation filters (KCF)—with the aim of quantifying and tracking movements of the individual performers. All three computer vision techniques exhibited high correlations with motion capture data collected from the same musical performances, with median correlation (Pearson’s r) values of .75 to .94. The techniques that track movement in two dimensions (optical flow and KCF) provided more accurate measures of movement than a technique that provides a single estimate of overall movement change by frame for each performer (frame differencing). Measurements of performer’s movements were also more accurate when the computer vision techniques were applied to more narrowly-defined regions of interest (head) than when the same techniques were applied to larger regions (entire upper body, above the chest or waist). Some differences in movement tracking accuracy emerged between the three video datasets, which may have been due to instrument-specific motions that resulted in occlusions of the body part of interest (e.g. a violinist’s right hand occluding the head whilst tracking head movement). These results indicate that computer vision techniques can be effective in quantifying body movement from videos of musical performances, while also highlighting constraints that must be dealt with when applying such techniques in ensemble coordination research.

Three-dimensional human-computer interaction has the potential to form the next generation of user interfaces and to replace the current 2D touch displays. To study and to develop such user interfaces, it is essential to be able to measure how a human behaves while interacting with them. In practice, this can be achieved by accurately measuring hand movements in 3D by using a camera-based system and computer vision. In this work, a framework for multi-camera finger movement measurements in 3D is proposed. This includes comprehensive evaluation of state-of-the-art object trackers to select the most appropriate one to track fast gestures such as pointing actions. Moreover, the needed trajectory post-processing and 3D trajectory reconstruction methods are proposed. The developed framework was successfully evaluated in the application where 3D touch screen usability is studied with 3D stimuli. The most sustainable performance was achieved by the Structuralist Cognitive model for visual Tracking tracker complemented with the LOESS smoothing.

Segmentation of overlapping convex objects has gained a lot of attention in numerous biomedical and industrial applications. A partial overlap between two or more convex shape objects leads to a shape with concave edge points that correspond to the intersections of the object boundaries. Therefore, it is a common practice to utilize these concave points to segment the contours of overlapping objects. Although a concave point has a clear mathematical definition, the task of concave point detection (CPD) from noisy digital images with limited resolution is far from trivial. This work provides the first comprehensive comparison of CPD methods with both synthetic and real world data. We further propose a modification to an earlier CPD method and show that it outperforms the other methods. Finally, we demonstrate that by using the enhanced concave points we obtain segmentation results that outperform the state-of-the-art in the task of partially overlapping convex object segmentation.

This paper presents a novel method for the segmentation of partially overlapping convex shape objects in silhouette images. The proposed method involves two main steps: contour evidence extraction and contour estimation. Contour evidence extraction starts by recovering contour segments from a binarized image using concave contour point detection. The contour segments which belong to the same objects are grouped by utilizing a criterion defining the convexity, symmetry and ellipticity of the resulting object. The grouping is formulated as a combinatorial optimization problem and solved using the well-known branch and bound algorithm. Finally, the contour estimation is implemented through a non-linear ellipse fitting problem in which partially observed objects are modeled in the form of ellipse-shape objects. The experiments on a dataset of consisting of nanoparticles demonstrate that the proposed method outperforms four current state-of-art approaches in overlapping convex objects segmentation. The method relies only on edge information and can be applied to any segmentation problems where the objects are partially overlapping and have an approximately convex shape.

Social tags inherent in online music services such as Last.fm provide a rich source of information on musical moods. The abundance of social tags makes this data highly beneficial for developing techniques to manage and retrieve mood information, and enables study of the relationships between music content and mood representations with data substantially larger than that available for conventional emotion research. However, no systematic assessment has been done on the accuracy of social tags and derived semantic models at capturing mood information in music. We propose a novel technique called Affective Circumplex Transformation (ACT) for representing the moods of music tracks in an interpretable and robust fashion based on semantic computing of social tags and research in emotion modeling. We validate the technique by predicting listener ratings of moods in music tracks, and compare the results to prediction with the Vector Space Model (VSM), Singular Value Decomposition (SVD), Nonnegative Matrix Factorization (NMF), and Probabilistic Latent Semantic Analysis (PLSA). The results show that ACT consistently outperforms the baseline techniques, and its performance is robust against a low number of track-level mood tags. The results give validity and analytical insights for harnessing millions of music tracks and associated mood data available through social tags in application development., Comment: Preprint, 14 pages

One important aspect of assessing the quality in pulp and papermaking is dirt particle counting and classifica- tion. Knowing the number and types of dirt particles present in pulp is useful for detecting problems in the production process as early as possible and for fixing them. Since man- ual quality control is a time-consuming and laborious task, the problem calls for an automated solution using machine vision techniques. However, the ground truth required to train an automated system is difficult to ascertain, since all of the dirt particles should be manually segmented and classified based on image information. This paper proposes a frame- work for developing and tuning dirt particle detection and classification systems. To avoid manual annotation, dry pulp sheets with a single dirt type in each were exploited to gener- ate semisynthetic images with the ground truth information. To classify the dirt particles, a set of features were com

The present study assesses two types of models for melodic complexity: one based on expectancy violations and the other one related to an information-theoretic account of redundancy in music. Seven different datasets spanning artificial sequences, folk and pop songs were used to refine and assess the models. The refinement eliminated unnecessary components from both types of models. The final analysis pitted three variants of the two model types against each other and could explain from 46-74% of the variance in the ratings across the datasets. The most parsimonious models were identified with an information-theoretic criterion. This suggested that the simplified expectancy-violation models were the most efficient for these sets of data. However, the differences between all optimised models were subtle in terms both of performance and simplicity.

This study investigates whether taking genre into account is beneficial for automatic music mood annotation in terms of core affects valence, arousal, and tension, as well as several other mood scales. Novel techniques employing genre-adaptive semantic computing and audio-based modelling are proposed. A technique called the ACTwg employs genre-adaptive semantic computing of mood-related social tags, whereas ACTwg-SLPwg combines semantic computing and audio-based modelling, both in a genre-adaptive manner. The proposed techniques are experimentally evaluated at predicting listener ratings related to a set of 600 popular music tracks spanning multiple genres. The results show that ACTwg outperforms a semantic computing technique that does not exploit genre information, and ACTwg-SLPwg outperforms conventional techniques and other genre-adaptive alternatives. In particular, improvements in the prediction rates are obtained for the valence dimension which is typically the most challenging core affect dimension for audio-based annotation. The specificity of genre categories is not crucial for the performance of ACTwg-SLPwg. The study also presents analytical insights into inferring a concise tag-based genre representation for genre-adaptive music mood analysis.

Previous research on harmony perception has mainly been concerned with horizontal aspects of harmony, turning less attention to how listeners perceive psychoacoustic qualities and emotions in single isolated chords. A recent study found mild dissonances to be more preferred than consonances in single chord perception, although the authors did not systematically vary register and consonance in their study; these omissions were explored here. An online empirical experiment was conducted where participants ( N = 410) evaluated chords on the dimensions of Valence, Tension, Energy, Consonance, and Preference; 15 different chords were played with piano timbre across two octaves. The results suggest significant differences on all dimensions across chord types, and a strong correlation between perceived dissonance and tension. The register and inversions contributed to the evaluations significantly, nonmusicians distinguishing between triadic inversions similarly to musicians. The mildly dissonant minor ninth, major ninth, and minor seventh chords were rated highest for preference, regardless of musical sophistication. The role of theoretical explanations such as aggregate dyadic consonance, the inverted-U hypothesis, and psychoacoustic roughness, harmonicity, and sharpness will be discussed to account for the preference of mild dissonance over consonance in single chord perception.

An overview of the computational prediction of emotional responses to music is presented. Communication of emotions by music has received a great deal of attention during the last years and a large number of empirical studies have described the role of individual features (tempo, mode, articulation, timbre) in predicting the emotions suggested or invoked by the music. However, unlike the present work, relatively few studies have attempted to model continua of expressed emotions using a variety of musical features from audio-based representations in a correlation design. The construction of the computational model is divided into four separate phases, with a different focus for evaluation. These phases include the theoretical selection of relevant features, empirical assessment of feature validity, actual feature selection, and overall evaluation of the model. Existing research on music and emotions and extraction of musical features is reviewed in terms of these criteria. Examples drawn from recent studies of emotions within the context of film soundtracks are used to demonstrate each phase in the construction of the model. These models are able to explain the dominant part of the listeners' self-reports of the emotions expressed by music and the models show potential to generalize over different genres within Western music. Possible applications of the computational models of emotions are discussed.

Empirical studies of emotions in music have described therole of individual musical features in recognizing particular emotions. However, no attempts have been made as yet to establish if there is a link between particular emotions and a specific genre. Here this is investigated byanalysing nine separate datasets that represent categories ranging from classical (three sets), and film music (two), to popular music (two), and mixed genre (two). Atotal of 39 musical features were extracted from the audio. Models were then constructed from theseto explain self-reports of valence and arousal, by using multiple andRandom Forest regression. The models were fully validated across the datasets, suggesting low generalizability between the genres for valence (16% variance was accounted for) and moderately good generalizability between the genres for arousal (43%). In contrast, the generalizability within genres was considerably higher (43% and 62% respectively), which suggests that emotions, especially thos...

Prediction of overall visual quality based on instrumental measurements is a challenging task. Despite the several proposed models and methods, there exists a gap between the instrumental measurements of print and human visual assessment of natural images. In this work, a computational model for representing and quantifying the overall visual quality of prints is proposed. The computed overall quality should correspond to the human visual quality perception when viewing the printed images. The proposed model is a Bayesian network which connects the objective instrumental measurements to the subjective opinion distribution of human observers. This relationship can be used to score printed images, and additionally, to computationally study the connections of the attributes. A novel graphical learning approach using an iterative evolve-estimate-simulate loop learning the quality model based on psychometric data and instrumental measurements is suggested. The network structure is optimised by applying evolutionary computation (evolve). The estimation of the Bayesian network parameters is within the evolutionary loop. In this loop, the maximum likelihood approach is used (estimate). The stochastic learning process is guided by priors devised from the psychometric subjective experiments (performance through simulation). The model reveals and represents the explanatory factors between its elements providing insight to the psychophysical phenomenon of how observers perceive visual quality and which measurable entities affect the quality perception. By using true data, the design choices are demonstrated. It is also shown that the best-performing network establishes a clear and intuitively correct structure between the objective measurements and psychometric data.

Fine and sparse details appear in many quality inspection applications requiring machine vision. Especially on flat surfaces, such as paper or board, the details can be made detectable by oblique illumination. In this study, a general definition of such details is given by defining sufficient statistical properties from histograms. The statistical model allows simulation of data and comparison of methods designed for detail detection. Based on the definition, utilization of the existing thresholding methods is shown to be well motivated. The comparison shows that minimum error thresholding outperforms the other standard methods. Finally, the results are successfully applied to a paper printability inspection application, and the IGT picking assessment, in which small surface defects must be detected. The provided method and measurement system prototype provide automated assessment with results comparable to manual expert evaluations in this laborious task.

Classification of musical audio signals according to expressed mood or emotion has evident applications to content-based music retrieval in large databases. Wrapper selection is a dimension reduction method that has been proposed for improving classification performance. However, the technique is prone to lead to overfitting of the training data, which decreases the generalizability of the obtained results. We claim that previous attempts to apply wrapper selection in the field of music information retrieval (MIR) have led to disputable conclusions about the used methods due to inadequate analysis frameworks, indicative of overfitting, and biased results. This paper presents a framework based on cross-indexing for obtaining realistic performance estimate of wrapper selection by taking into account the simplicity and generalizability of the classification models. The framework is applied on sets of film soundtrack excerpts that are consensually associated with particular basic emotions, comparing Naive Bayes, k-NN, and SVM classifiers using both forward selection (FS) and backward elimination (BE). K-NN with BE yields the most promising results - 56.5% accuracy with only four features. The most useful feature subset for k-NN contains mode majorness and key clarity, combined with dynamical, rhythmical, and structural features.

Methodological support for the design of non-speech user interface sounds for human–computer interaction is still fairly scarce. To meet this challenge, this paper presents a sound design case which, as a practical design solution for a wrist-computer physical training application, outlines a prosody-based method for designing non-speech user interface sounds. The principles used in the design are based on nonverbal communicative functions of prosody in speech acts, exemplifying an interpersonal approach to sonic interaction design. The stages of the design process are justified with a theoretical analysis and three empirical sub-studies, which comprise production and recognition tasks involving four communicative functions. The final evaluation study indicates that the resulting sounds of the design process successfully served these functions. In all, this study suggests that prosody-based sound design provides widely applicable means to attribute meaningful, interaction-derived qualities to non-speech sounds for interactive applications.

Understanding how a human behaves while performing human-computer interaction tasks is essential in order to develop better user interfaces. In the case of touch and gesture based interfaces, the main interest is in the characterization of hand movements. The recent developments in imaging technology and computing hardware have made it attractive to exploit high-speed imaging for tracking the hand more accurately both in space and time. However, the tracking algorithm development has been focused on optimizing the robustness and computation speed instead of spatial accuracy, making most of them, as such, insufficient for the accurate measurements of hand movements. In this paper, state-of-the-art tracking algorithms are compared based on their suitability for the finger tracking during human-computer interaction task. Furthermore, various trajectory filtering techniques are evaluated to improve the accuracy and to obtain appropriate hand movement measurements. The experimental results showed that Kernelized Correlation Filters and Spatio-Temporal Context Learning tracking were the best tracking methods obtaining reasonable accuracy and high processing speed while Local Regression filtering and Unscented Kalman Smoother were the most suitable filtering techniques.

This paper presents a novel method for the segmentation of partially overlapping nanoparticles with a convex shape in silhouette images. The proposed method involves two main steps: contour evidence extraction and contour estimation. Contour evidence extraction starts with contour segmentation where contour segments are recovered from a binarized image by detecting concave points. After this, contour segments which belong to the same object are grouped by utilizing properties of fitted ellipses. Finally, the contour estimation is implemented through a non-linear ellipse fitting problem in which partially observed objects are modeled in the form of ellipse-shape objects. The experiments on a dataset consisting of nanoparticles demonstrate that the proposed method outperforms two current state-of-art approaches in overlapping nanoparticles segmentation. The method relies only on edge information and can be applied to any segmentation problems where the objects are partially overlapping and have an approximately elliptical shape, such as cell segmentation.

The problem of tracking a hand in video has gained a lot of attention due to its numerous applications in human computer interfaces. So far, the work has been limited to the use of standard speed videos, but the recent developments in imaging technology and computing hardware have made it attractive to exploit high-speed imaging for tracking the hand more accurately both in space and time. To produce videos of good quality, the high-speed imaging requires more light when compared to imaging with conventional frame rates. Therefore, grey-scale high-speed imaging is in common use and this makes the use of hand tracking methods relying specifically on color information unsuitable. In this work, we provide the first solid comparison of state-of-the-art general object trackers on hand tracking with a primary focus on grey-scale high-speed videos. Novel annotated high-speed video data were collected and made publicly available for evaluation purposes. The algorithms were tested with both finger and hand targets, and with grey-scale and color videos. In addition to tracking accuracies, the stability, sensitivity, and the processing speeds of the algorithms were evaluated. The experiments show that the results vary significantly in all aspects, but certain methods such as Compressive Tracking and Hough Track methods performed better overall.

Social media services such as Last.fm provide crowd-sourced mood tags which are a rich but often noisy source of information. In contrast, editorial annotations from production music libraries are meant to be incisive in nature. We compare the efficiency of these two data sources in capturing semantic information on mood expressed by music. First, a semantic computing technique devised for mood-related tags in large datasets is applied to Last.fm and I Like Music (ILM) corpora separately (250,000 tracks each). The resulting semantic estimates are then correlated with listener ratings of arousal, valence and tension. High correlations (Spearman's rho) are found between the track positions in the dimensional mood spaces and listener ratings using both data sources (0.60

The paper presents a framework for the detection of curvilinear objects in images. Such objects are challenging to be described by a geometrical model, and although they appear in a number of applications, the problem of detecting curvilinear objects has drawn limited attention. The proposed approach starts with an edge detection algorithm after which the task of object detection becomes a problem of edge linking. A state-of-the-art local linking approach called tensor voting is used to estimate the edge point saliency describing the likelihood of a point belonging to a curve, and to extract the end points and junction points of these curves. After the tensor voting, the curves are grown from high-saliency seed points utilizing a linking method proposed in this paper. In the experimental part of the work, the method was systematically tested on pulp suspension images to characterize fibers based on their length and curl index. The fiber length was estimated with the accuracy of 71.5% and the fiber curvature with the accuracy of 70.7%.

The perceptual attributes of timbre have inspired a considerable amount of multidisciplinary research, but because of the complexity of the phenomena, the approach has traditionally been confined to laboratory conditions, much to the detriment of its ecological validity. In this study, we present a purely bottom-up approach for mapping the concepts that emerge from sound qualities. A social media ( http://www.last.fm ) is used to obtain a wide sample of verbal descriptions of music (in the form of tags) that go beyond the commonly studied concept of genre, and from this the underlying semantic structure of this sample is extracted. The structure that is thereby obtained is then evaluated through a careful investigation of the acoustic features that characterize it. The results outline the degree to which such structures in music (connected to affects, instrumentation and performance characteristics) have particular timbral characteristics. Samples representing these semantic structures were then submitted to a similarity rating experiment to validate the findings. The outcome of this experiment strengthened the discovered links between the semantic structures and their perceived timbral qualities. The findings of both the computational and behavioural parts of the experiment imply that it is therefore possible to derive useful and meaningful structures from free verbal descriptions of music, that transcend musical genres, and that such descriptions can be linked to a set of acoustic features. This approach not only provides insights into the definition of timbre from an ecological perspective, but could also be implemented to develop applications in music information research that organize music collections according to both semantic and sound qualities.

In pulping and papermaking, dirt particles significantly affect the quality of paper. Knowledge of the dirt type helps to track the sources of the impurities which would considerably improve the paper making process. Dirt particle classification designed for this purpose should be adaptable because the dirt types are specific to the different processes of paper mills. This paper introduces a general approach for the adaptable classification system. The attention is paid to feature extraction and evaluation, in order to determine a suboptimal set of features for a certain data. The performance of standard classifiers on the provided data is presented, considering how the dirt particles or different types are classified. The effect of dirt particle grouping according to the particle size on the results of classification and feature evaluation is discussed. It is shown that the representative features of dirt particles from different size groups are different, which has an effect on the classification.

Measuring visual quality of printed media is important as printed products play an essential role in every day life, and for many "vision applications", printed products still dominate the market (e.g., newspapers). Measuring visual quality, especially the quality of images when the original is known (full-reference), has been an active research topic in image processing. During the course of work, several good measures have been proposed and shown to correspond with human (subjective) evaluations. Adapting these approaches to measuring visual quality of printed media has been considered only rarely and is not straightforward. In this work, the aim is to reduce the gap by presenting a complete framework starting from the original digital image and its hard-copy reproduction to a scanned digital sample which is compared to the original reference image by using existing quality measures. The proposed framework is justified by experiments where the measures are compared to a subjective evaluation performed using the printed hard copies.

The literature of visual quality is mainly concentrated on devising new physical, visual, or computational quality features which could indirectly reflect ldquotrue visual qualityrdquo. The problem is that the true visual quality is always a subjective and context sensitive judgement of a single individual or a group of individuals. Therefore, the developed methods are only loosely connected to this ultimate objective, and the existing de facto and official standards have been designed by forming a consensus among experts of a specific field (e.g., in the printing industry). In this study, we describe a large psychological experiment where true factors of the human quality experience are pair-wise resolved for dedicatedly selected samples. Then we describe a ranking measure which reveals the relationship between selected measurable quantities and the human evaluation trial. Finally by using the above framework, we devise the best combinations from a set of well-known measurable quantities. The devised combinations can be considered as optimal when agreement with the human visual quality experience is desired, and therefore, they also reveal completely novel information about measuring visual quality.

Due to the rise in performance of digital printing, image-based applications are gaining popularity. This creates needs for specifying the quality potential of printers and materials in more detail than before. Both production and end-use standpoints are relevant. This paper gives an overview of an on-going study which has the goal of determining a framework model for the visual quality potential of paper in color image printing. The approach is top-down and it is founded on the concept of a layered network model. The model and its subjective, objective and instrumental measurement layers are discussed. Some preliminary findings are presented. These are based on data from samples obtained by printing natural image contents and simple test fields on a wide range of paper grades by ink-jet in a color managed process. Color profiles were paper specific. Visual mean opinion score data by human observers could be accounted for by two or three dimensions. In the first place these are related to brightness and color brightness. Image content has a marked effect on the dimensions. This underlines the challenges in designing the test images.

Computational analysis of large musical corpora provides an approach that overcomes some of the limitations of manual analysis related to small sample sizes and subjectivity. The present paper aims to provide an overview of the computational approach to music research. It discusses the issues of music representation, musical feature extraction, digital music collections, and data mining techniques. Moreover, it provides examples of visualization of large musical collections.

The performance of autocorrelation-based meter induction was tested with two large collections of folk melodies, consisting of approximately 13 000 melodies for which the correct meters were available. The performance was measured by the proportion of melodies whose meter was correctly classified by a discriminant function. Furthermore, it was examined whether including different melodic accent types would improve the classification performance. By determining the components of the autocorrelation functions that were significant in the classification it was found that periodicity in note onset locations was the most important cue for the determination of meter. Of the melodic accents included, Thomassen's melodic accent was found to provide the most reliable cues for the determination of meter. The discriminant function analyses suggested that periodicities longer than one measure may provide cues for meter determination that are more reliable than shorter periodicities. Overall, the method predicted notated meter with an accuracy reaching 96% for binary classification and 75% for classification into nine categories of meter.

Full reference image quality algorithms are standard tools in digital image processing but have not been utilized for printed images due to a "correspondence gap" between the digital domain (a reference) and physical domain (printed sample). In this work, the authors propose a framework for applying full reference image quality algorithms to printed images. The framework consists of accurate scanning of printed samples and automatic registration and descreening procedures which bring the scans in correspondence with their digital originals. The authors complete the framework by incorporating state-of-the-art full reference algorithms to it. Using data from comprehensive psychometrical experiments of subjective quality experience, the authors benchmark the state-of-the-art methods and point out similar results in the digital domain: the best digital full reference measures, such as the recently introduced visual information fidelity algorithm, perform best also for printed media.

A method for the detection of bubble-like transparent objects with multiple interfaces in a liquid is proposed. Depending on the lighting conditions, bubble appearance varies significantly, including contrast reversal and multiple inter-reflections. We formulate the bubble detection problem as the detection of Concentric Circular Arrangements (CCA). The CCAs are recovered in a hypothesize-optimize-verify framework. The hypothesis generation proceeds by sampling from the components of the non-maximum suppressed responses of oriented ridge filters followed by CCA parameter estimation. Parameter optimization is carried out by minimizing a novel cost-function by the simplex method. The proposed method for bubble detection showed good performance in an industrial application requiring estimation of gas volume in pulp suspension, achieving 1.5% mean absolute relative error.