Deep learning for computer vision: a comparison between convolutional neural networks and hierarchical temporal memories on object recognition tasks

In recent years, Deep Learning techniques have shown to perform well on a large variety of problems both in Computer Vision and Natural Language Processing, reaching and often surpassing the state of the art on many tasks. The rise of deep learning is also revolutionizing the entire field of Machine Learning and Pattern Recognition pushing forward the concepts of automatic feature extraction and unsupervised learning in general. However, despite the strong success both in science and business, deep learning has its own limitations. It is often questioned if such techniques are only some kind of brute-force statistical approaches and if they can only work in the context of High Performance Computing with tons of data. Another important question is whether they are really biologically inspired, as claimed in certain cases, and if they can scale well in terms of "intelligence". The dissertation is focused on trying to answer these key questions in the context of Computer Vision and, in particular, Object Recognition, a task that has been heavily revolutionized by recent advances in the field. Practically speaking, these answers are based on an exhaustive comparison between two, very different, deep learning techniques on the aforementioned task: Convolutional Neural Network (CNN) and Hierarchical Temporal memory (HTM). They stand for two different approaches and points of view within the big hat of deep learning and are the best choices to understand and point out strengths and weaknesses of each of them. CNN is considered one of the most classic and powerful supervised methods used today in machine learning and pattern recognition, especially in object recognition. CNNs are well received and accepted by the scientific community and are already deployed in large corporation like Google and Facebook for solving face recognition and image auto-tagging problems. HTM, on the other hand, is known as a new emerging paradigm and a new meanly-unsupervised method, that is more biologically inspired. It tries to gain more insights from the computational neuroscience community in order to incorporate concepts like time, context and attention during the learning process which are typical of the human brain. In the end, the thesis is supposed to prove that in certain cases, with a lower quantity of data, HTM can outperform CNN.

Progettazione e implementazione di un sistema di autorizzazione elettronico per il trasporto auto di persone disabili con validazione biometrica

Notizie riguardanti scandali relativi al utilizzo inappropriato di contrassegni per disabili sono all’ordine del giorno. Situazioni meno popolari dal punto di vista mediatico, ma altrettanto gravi a livello sociale coinvolgono tutti quegli individui che si prodigano a falsificare contrassegni oppure ad utilizzarli anche in mancanza del disabile, eventualmente anche successivamente al decesso del medesimo. Tutto questo va inevitabilmente a discapito di tutti coloro che hanno reale diritto e necessità di usufruire delle agevolazioni. Lo scopo di questa tesi è quindi quello di illustrare un possibile sistema per contrastare e possibilmente debellare questo malcostume diffusissimo in Italia. La proposta è quella di dematerializzare il pass cartaceo sostituendolo con un equiva- lente elettronico, temporaneo e associato non più ad una targa, ma all’individuo stesso. Per farlo si ricorrerà all’uso di tecniche di autenticazione attraverso sistemi biometrici, quali il riconoscimento facciale, vocale, di espressioni facciali e gestures.

Tecniche di riconoscimento del volto in presenza di makeup

Il makeup, come strumento atto a modificare i tratti somatici di un individuo per aumentarne la bellezza, è largamente diffuso e socialmente accettabile al giorno d’oggi. Per la sua facile reperibilità, semplicità di utilizzo e capacità di alterare le caratteristiche principali di un volto, può diventare uno strumento pericoloso per chi volesse sottrarsi a dei controlli. In questo lavoro di tesi sono stati analizzati algoritmi presenti in letteratura che cercano di arginare gli effetti di alterazione di un viso, causati dal makeup, durante un processo di riconoscimento del volto. Inoltre è stato utilizzato un software per verificare la robustezza dei programmi commerciali in merito al problema del makeup e confrontare poi i risultati riscontrati in letteratura con quelli ottenuti dai test.

Quality of experience in skype video calls

Skype is one of the well-known applications that has guided the evolution of real-time video streaming and has become one of the most used software in everyday life. It provides VoIP audio/video calls as well as messaging chat and file transfer. Many versions are available covering all the principal operating systems like Windows, Macintosh and Linux but also mobile systems. Voice quality decreed Skype success since its birth in 2003 and peer-to-peer architecture has allowed worldwide diffusion. After video call introduction in 2006 Skype became a complete solution to communicate between two or more people. As a primarily video conferencing application, Skype assumes certain characteristics of the delivered video to optimize its perceived quality. However in the last years, and with the recent release of SkypeKit1, many new Skype video-enabled devices came out especially in the mobile world. This forced a change to the traditional recording, streaming and receiving settings allowing for a wide range of network and content dynamics. Video calls are not anymore based on static ‘chatting’ but mobile devices have opened new possibilities and can be used in several scenarios. For instance, lecture streaming or one-to-one mobile video conferences exhibit more dynamics as both caller and callee might be on move. Most of these cases are different from “head&shoulder” only content. Therefore, Skype needs to optimize its video streaming engine to cover more video types. Heterogeneous connections require different behaviors and solutions and Skype must face with this variety to maintain a certain quality independently from connection used. Part of the present work will be focused on analyzing Skype behavior depending on video content. Since Skype protocol is proprietary most of the studies so far have tried to characterize its traffic and to reverse engineer its protocol. However, questions related to the behavior of Skype, especially on quality as perceived by users, remain unanswered. We will study Skype video codecs capabilities and video quality assessment. Another motivation of our work is the design of a mechanism that estimates the perceived cost of network conditions on Skype video delivery. To this extent we will try to assess in an objective way the impact of network impairments on the perceived quality of a Skype video call. Traditional video streaming schemes lack the necessary flexibility and adaptivity that Skype tries to achieve at the edge of a network. Our contribution will lye on a testbed and consequent objective video quality analysis that we will carry out on input videos. We will stream raw video files with Skype via an impaired channel and then we will record it at the receiver side to analyze with objective quality of experience metrics.