A contribution to semantic description of images and videos: an application of soft biometrics

Humans have a high ability to extract visual data information acquired by sight. Trought a learning process, which starts at birth and continues throughout life, image interpretation becomes almost instinctively. At a glance, one can easily describe a scene with reasonable precision, naming its main components. Usually, this is done by extracting low-level features such as edges, shapes and textures, and associanting them to high level meanings. In this way, a semantic description of the scene is done. An example of this, is the human capacity to recognize and describe other people physical and behavioral characteristics, or biometrics. Soft-biometrics also represents inherent characteristics of human body and behaviour, but do not allow unique person identification. Computer vision area aims to develop methods capable of performing visual interpretation with performance similar to humans. This thesis aims to propose computer vison methods which allows high level information extraction from images in the form of soft biometrics. This problem is approached in two ways, unsupervised and supervised learning methods. The first seeks to group images via an automatic feature extraction learning , using both convolution techniques, evolutionary computing and clustering. In this approach employed images contains faces and people. Second approach employs convolutional neural networks, which have the ability to operate on raw images, learning both feature extraction and classification processes. Here, images are classified according to gender and clothes, divided into upper and lower parts of human body. First approach, when tested with different image datasets obtained an accuracy of approximately 80% for faces and non-faces and 70% for people and non-person. The second tested using images and videos, obtained an accuracy of about 70% for gender, 80% to the upper clothes and 90% to lower clothes. The results of these case studies, show that proposed methods are promising, allowing the realization of automatic high level information image annotation. This opens possibilities for development of applications in diverse areas such as content-based image and video search and automatica video survaillance, reducing human effort in the task of manual annotation and monitoring.

A three-dimensional representation method for noisy point clouds based on growing self-organizing maps accelerated on GPUs

The research described in this thesis was motivated by the need of a robust model capable of representing 3D data obtained with 3D sensors, which are inherently noisy. In addition, time constraints have to be considered as these sensors are capable of providing a 3D data stream in real time. This thesis proposed the use of Self-Organizing Maps (SOMs) as a 3D representation model. In particular, we proposed the use of the Growing Neural Gas (GNG) network, which has been successfully used for clustering, pattern recognition and topology representation of multi-dimensional data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models, without considering time constraints. It is proposed a hardware implementation leveraging the computing power of modern GPUs, which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). The proposed methods were applied to different problem and applications in the area of computer vision such as the recognition and localization of objects, visual surveillance or 3D reconstruction.

Efficient Image and Video Representations for Retrieval

Image (Video) retrieval is an interesting problem of retrieving images (videos) similar to the query. Images (Videos) are represented in an input (feature) space and similar images (videos) are obtained by finding nearest neighbors in the input representation space. Numerous input representations both in real valued and binary space have been proposed for conducting faster retrieval. In this thesis, we present techniques that obtain improved input representations for retrieval in both supervised and unsupervised settings for images and videos. Supervised retrieval is a well known problem of retrieving same class images of the query. We address the practical aspects of achieving faster retrieval with binary codes as input representations for the supervised setting in the first part, where binary codes are used as addresses into hash tables. In practice, using binary codes as addresses does not guarantee fast retrieval, as similar images are not mapped to the same binary code (address). We address this problem by presenting an efficient supervised hashing (binary encoding) method that aims to explicitly map all the images of the same class ideally to a unique binary code. We refer to the binary codes of the images as `Semantic Binary Codes' and the unique code for all same class images as `Class Binary Code'. We also propose a new class­ based Hamming metric that dramatically reduces the retrieval times for larger databases, where only hamming distance is computed to the class binary codes. We also propose a Deep semantic binary code model, by replacing the output layer of a popular convolutional Neural Network (AlexNet) with the class binary codes and show that the hashing functions learned in this way outperforms the state­ of ­the art, and at the same time provide fast retrieval times. In the second part, we also address the problem of supervised retrieval by taking into account the relationship between classes. For a given query image, we want to retrieve images that preserve the relative order i.e. we want to retrieve all same class images first and then, the related classes images before different class images. We learn such relationship aware binary codes by minimizing the similarity between inner product of the binary codes and the similarity between the classes. We calculate the similarity between classes using output embedding vectors, which are vector representations of classes. Our method deviates from the other supervised binary encoding schemes as it is the first to use output embeddings for learning hashing functions. We also introduce new performance metrics that take into account the related class retrieval results and show significant gains over the state­ of­ the art. High Dimensional descriptors like Fisher Vectors or Vector of Locally Aggregated Descriptors have shown to improve the performance of many computer vision applications including retrieval. In the third part, we will discuss an unsupervised technique for compressing high dimensional vectors into high dimensional binary codes, to reduce storage complexity. In this approach, we deviate from adopting traditional hyperplane hashing functions and instead learn hyperspherical hashing functions. The proposed method overcomes the computational challenges of directly applying the spherical hashing algorithm that is intractable for compressing high dimensional vectors. A practical hierarchical model that utilizes divide and conquer techniques using the Random Select and Adjust (RSA) procedure to compress such high dimensional vectors is presented. We show that our proposed high dimensional binary codes outperform the binary codes obtained using traditional hyperplane methods for higher compression ratios. In the last part of the thesis, we propose a retrieval based solution to the Zero shot event classification problem - a setting where no training videos are available for the event. To do this, we learn a generic set of concept detectors and represent both videos and query events in the concept space. We then compute similarity between the query event and the video in the concept space and videos similar to the query event are classified as the videos belonging to the event. We show that we significantly boost the performance using concept features from other modalities.

Interfaces for Intelligent Environments

Presentaciones de la asignatura Interfaces para Entornos Inteligentes del Máster en Tecnologías de la Informática/Machine Learning and Data Mining.

A comparative study of navigation meshes

International audience

Contribuciones sobre métodos óptimos y subóptimos de aproximaciones poligonales de curvas 2-D

Esta tesis versa sobre el an álisis de la forma de objetos 2D. En visión articial existen numerosos aspectos de los que se pueden extraer información. Uno de los más usados es la forma o el contorno de esos objetos. Esta característica visual de los objetos nos permite, mediante el procesamiento adecuado, extraer información de los objetos, analizar escenas, etc. No obstante el contorno o silueta de los objetos contiene información redundante. Este exceso de datos que no aporta nuevo conocimiento debe ser eliminado, con el objeto de agilizar el procesamiento posterior o de minimizar el tamaño de la representación de ese contorno, para su almacenamiento o transmisión. Esta reducción de datos debe realizarse sin que se produzca una pérdida de información importante para representación del contorno original. Se puede obtener una versión reducida de un contorno eliminando puntos intermedios y uniendo los puntos restantes mediante segmentos. Esta representación reducida de un contorno se conoce como aproximación poligonal. Estas aproximaciones poligonales de contornos representan, por tanto, una versión comprimida de la información original. El principal uso de las mismas es la reducción del volumen de información necesario para representar el contorno de un objeto. No obstante, en los últimos años estas aproximaciones han sido usadas para el reconocimiento de objetos. Para ello los algoritmos de aproximaci ón poligonal se han usado directamente para la extracci ón de los vectores de caracter ísticas empleados en la fase de aprendizaje. Las contribuciones realizadas por tanto en esta tesis se han centrado en diversos aspectos de las aproximaciones poligonales. En la primera contribución se han mejorado varios algoritmos de aproximaciones poligonales, mediante el uso de una fase de preprocesado que acelera estos algoritmos permitiendo incluso mejorar la calidad de las soluciones en un menor tiempo. En la segunda contribución se ha propuesto un nuevo algoritmo de aproximaciones poligonales que obtiene soluciones optimas en un menor espacio de tiempo que el resto de métodos que aparecen en la literatura. En la tercera contribución se ha propuesto un algoritmo de aproximaciones que es capaz de obtener la solución óptima en pocas iteraciones en la mayor parte de los casos. Por último, se ha propuesto una versi ón mejorada del algoritmo óptimo para obtener aproximaciones poligonales que soluciona otro problema de optimización alternativo.

Mutual Information-based RBM Neural Networks

(Deep) neural networks are increasingly being used for various computer vision and pattern recognition tasks due to their strong ability to learn highly discriminative features. However, quantitative analysis of their classication ability and design philosophies are still nebulous. In this work, we use information theory to analyze the concatenated restricted Boltzmann machines (RBMs) and propose a mutual information-based RBM neural networks (MI-RBM). We develop a novel pretraining algorithm to maximize the mutual information between RBMs. Extensive experimental results on various classication tasks show the eectiveness of the proposed approach.

A RBES for Generating Automatically Personalized Menus

Food bought at supermarkets in, for instance, North America or the European Union, give comprehensive information about ingredients and allergens. Meanwhile, the menus of restaurants are usually incomplete and cannot be normally completed by the waiter. This is specially important when traveling to countries with a di erent culture. A curious example is "calamares en su tinta" (squid in its own ink), a common dish in Spain. Its brief description would be "squid with boiled rice in its own (black) ink", but an ingredient of its sauce is flour, a fact very important for celiacs. There are constraints based on religious believes, due to food allergies or to illnesses, while others just derive from personal preferences. Another complicated situation arise in hospitals, where the doctors' nutritional recommendations have to be added to the patient's usual constraints. We have therefore designed and developed a Rule Based Expert System (RBES) that can address these problems. The rules derive directly from the recipes of the di fferent dishes and contain the information about the required ingredients and ways of cooking. In fact, we distinguish: ingredients and ways of cooking, intermediate products (like sauces, that aren't always made explicit) and final products (the dishes listed in the menu of the restaurant). For a certain restaurant, customer and instant, the input to the RBES are: actualized stock of ingredients and personal characteristics of that customer. The RBES then prepares a "personalized menu" using set operations and knowledge extraction (thanks to an algebraic inference engine [1]). The RBES has been implemented in the computer algebra system MapleTM2015. A rst version of this work was presented at "Applications of Computer Algebra 2015" (ACA'2015) conference. The corresponding abstract is available at [2].

Comparative study of human age estimation based on hand-crafted and deep face features

In the past few years, human facial age estimation has drawn a lot of attention in the computer vision and pattern recognition communities because of its important applications in age-based image retrieval, security control and surveillance, biomet- rics, human-computer interaction (HCI) and social robotics. In connection with these investigations, estimating the age of a person from the numerical analysis of his/her face image is a relatively new topic. Also, in problems such as Image Classification the Deep Neural Networks have given the best results in some areas including age estimation. In this work we use three hand-crafted features as well as five deep features that can be obtained from pre-trained deep convolutional neural networks. We do a comparative study of the obtained age estimation results with these features.

Sviluppo di un algoritmo di Object Detection per la privacy in ambito industriale

In questa tesi è descritto il lavoro svolto presso un'azienda informatica locale, allo scopo di ricerca ed implementazione di un algoritmo per individuare ed offuscare i volti presenti all'interno di video di e-learning in ambito industriale, al fine di garantire la privacy degli operai presenti. Tale algoritmo sarebbe stato poi da includere in un modulo software da inserire all'interno di un applicazione web già esistente per la gestione di questi video. Si è ricercata una soluzione ad hoc considerando le caratteristiche particolare del problema in questione, studiando le principali tecniche della Computer Vision per comprendere meglio quale strada percorrere. Si è deciso quindi di implementare un algoritmo di Blob Tracking basato sul colore.

Edge centrality via the Holevo quantity

In the study of complex networks, vertex centrality measures are used to identify the most important vertices within a graph. A related problem is that of measuring the centrality of an edge. In this paper, we propose a novel edge centrality index rooted in quantum information. More specifically, we measure the importance of an edge in terms of the contribution that it gives to the Von Neumann entropy of the graph. We show that this can be computed in terms of the Holevo quantity, a well known quantum information theoretical measure. While computing the Von Neumann entropy and hence the Holevo quantity requires computing the spectrum of the graph Laplacian, we show how to obtain a simplified measure through a quadratic approximation of the Shannon entropy. This in turns shows that the proposed centrality measure is strongly correlated with the negative degree centrality on the line graph. We evaluate our centrality measure through an extensive set of experiments on real-world as well as synthetic networks, and we compare it against commonly used alternative measures.

The average mixing matrix signature

Laplacian-based descriptors, such as the Heat Kernel Signature and the Wave Kernel Signature, allow one to embed the vertices of a graph onto a vectorial space, and have been successfully used to find the optimal matching between a pair of input graphs. While the HKS uses a heat di↵usion process to probe the local structure of a graph, the WKS attempts to do the same through wave propagation. In this paper, we propose an alternative structural descriptor that is based on continuoustime quantum walks. More specifically, we characterise the structure of a graph using its average mixing matrix. The average mixing matrix is a doubly-stochastic matrix that encodes the time-averaged behaviour of a continuous-time quantum walk on the graph. We propose to use the rows of the average mixing matrix for increasing stopping times to develop a novel signature, the Average Mixing Matrix Signature (AMMS). We perform an extensive range of experiments and we show that the proposed signature is robust under structural perturbations of the original graphs and it outperforms both the HKS and WKS when used as a node descriptor in a graph matching task.

Dynamic Match Analysis

Recent technological development has enabled research- ers to gather data from different performance scenarios while considering players positioning and action events within a specific time frame. This technology varies from global positioning systems to radio frequency devices and computer vision tracking, to name the most common, and aims to collect players’ time motion data and enable the dynamical analysis of performance. Team sports—and in particular, invasion games—present a complex dynamic by nature based on the interaction between 2 opposing sides trying to outperform 1 another. During match and training situations, players’ actions are coupled to their performance context at different interaction levels. As expected, ball, teammates’, and opponents’ positioning play an important role in this interaction process. But other factors, such as final score, teams’ development level, and players’ expertise, seem to affect the match dynamics. In this symposium, we will focus on how different constraints affect invasion games dynamics during both match and training situations. This relation will be established while underpinning the importance of these effects to game teaching and performance optimization. Regarding the match, different performance indicators based on spatial-temporal relations between players and teams will be presented to reveal the interaction processes that form the crucial component of game analysis. Considering the training, this symposium will address the relationship of small-sided games with full- sized matches and will present how players’ dynamical interaction affects different performance indicators.