Computer vision in aseptic pharmaceutical manufacturing: a deep learning-based approach to vial inspection and pack formation during a lyophilizer loading cycle

Vision systems are powerful tools playing an increasingly important role in modern industry, to detect errors and maintain product standards. With the enlarged availability of affordable industrial cameras, computer vision algorithms have been increasingly applied in industrial manufacturing processes monitoring. Until a few years ago, industrial computer vision applications relied only on ad-hoc algorithms designed for the specific object and acquisition setup being monitored, with a strong focus on co-designing the acquisition and processing pipeline. Deep learning has overcome these limits providing greater flexibility and faster re-configuration. In this work, the process to be inspected consists in vials’ pack formation entering a freeze-dryer, which is a common scenario in pharmaceutical active ingredient packaging lines. To ensure that the machine produces proper packs, a vision system is installed at the entrance of the freeze-dryer to detect eventual anomalies with execution times compatible with the production specifications. Other constraints come from sterility and safety standards required in pharmaceutical manufacturing. This work presents an overview about the production line, with particular focus on the vision system designed, and about all trials conducted to obtain the final performance. Transfer learning, alleviating the requirement for a large number of training data, combined with data augmentation methods, consisting in the generation of synthetic images, were used to effectively increase the performances while reducing the cost of data acquisition and annotation. The proposed vision algorithm is composed by two main subtasks, designed respectively to vials counting and discrepancy detection. The first one was trained on more than 23k vials (about 300 images) and tested on 5k more (about 75 images), whereas 60 training images and 52 testing images were used for the second one.

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.

Elaborazione di video tramite un software web per la computer vision

La tesi tratta i temi di computer vision connessi alle problematiche di inserimento in una piattaforma Web. Nel testo sono spiegate alcune soluzioni per includere una libreria software per l'emotion recognition in un'applicazione web e tecnologie per la registrazione di un video, catturando le immagine da una webcam.

Robotics and neurodevelopmental disorder: design and implementation of a system of engagement metrics in human-robot interactions.

In the recent decades, robotics has become firmly embedded in areas such as education, teaching, medicine, psychology and many others. We focus here on social robotics; social robots are designed to interact with people in a natural and interpersonal way, often to achieve positive results in different applications. To interact and cooperate with humans in their daily-life activities, robots should exhibit human-like intelligence. The rapid expansion of social robotics and the existence of various kinds of robots on the market have allowed research groups to carry out multiple experiments. The experiments carried out have led to the collections of various kinds of data, which can be used or processed for psychological studies, and studies in other fields. However, there are no tools available in which data can be stored, processed and shared with other research groups. This thesis proposes the design and implementation of visual tool for organizing dataflows in Human Robot Interaction (HRI).

A ROS-based Workspace Control and Trajectory Planner for a seven degrees of freedom Robotic arm

In this Bachelor Thesis I want to provide readers with tools and scripts for the control of a 7DOF manipulator, backed up by some theory of Robotics and Computer Science, in order to better contextualize the work done. In practice, we will see most common software, and developing environments, used to cope with our task: these include ROS, along with visual simulation by VREP and RVIZ, and an almost "stand-alone" ROS extension called MoveIt!, a very complete programming interface for trajectory planning and obstacle avoidance. As we will better appreciate and understand in the introduction chapter, the capability of detecting collision objects through a camera sensor, and re-plan to the desired end-effector pose, are not enough. In fact, this work is implemented in a more complex system, where recognition of particular objects is needed. Through a package of ROS and customized scripts, a detailed procedure will be provided on how to distinguish a particular object, retrieve its reference frame with respect to a known one, and then allow navigation to that target. Together with technical details, the aim is also to report working scripts and a specific appendix (A) you can refer to, if desiring to put things together.

Generative Neural Networks for image iper-resolution and improvement of Optical Character Recognition's performances

The usage of Optical Character Recognition’s (OCR, systems is a widely spread technology into the world of Computer Vision and Machine Learning. It is a topic that interest many field, for example the automotive, where becomes a specialized task known as License Plate Recognition, useful for many application from the automation of toll road to intelligent payments. However, OCR systems need to be very accurate and generalizable in order to be able to extract the text of license plates under high variable conditions, from the type of camera used for acquisition to light changes. Such variables compromise the quality of digitalized real scenes causing the presence of noise and degradation of various type, which can be minimized with the application of modern approaches for image iper resolution and noise reduction. Oneclass of them is known as Generative Neural Networks, which are very strong ally for the solution of this popular problem.

Analysis of morphological and functional heterogeneity in ct perfusion images of lung tumours

Questa tesi si propone di innovare lo stato dell’arte dei metodi di analisi dell’eterogeneità in lesioni polmonari attualmente utilizzati, affiancando l’analisi funzionale (emodinamica) a quella morfologica, grazie allo sviluppo di nuove feature specifiche. Grazie alla collaborazione tra il Computer Vision Group (CVG) dell’Università di Bologna e l’Unità Operativa di Radiologia dell’IRCCS-IRST di Meldola (Istituto di Ricovero e Cura a Carattere Scientifico – Istituto Scientifico Romagnolo per lo Studio e la Cura dei Tumori), è stato possibile analizzare un adeguato numero di casi reali di pazienti affetti da lesioni polmonari primitive, effettuando un’analisi dell’eterogeneità sia su sequenze di immagini TC baseline sia contrast-enhanced, consentendo quindi un confronto tra eterogeneità morfologica e funzionale. I risultati ottenuti sono infine discussi sulla base del confronto con le considerazioni di natura clinica effettuate in cieco da due esperti radiologi dell’IRCCS-IRST.

Analysis and development of interface components and procedures for the design and commissioning toolchains in automation systems

The objective of the thesis project, developed within the Line Control & Software Engineering team of G.D company, is to analyze and identify the appropriate tool to automate the HW configuration process using Beckhoff technologies by importing data from an ECAD tool. This would save a great deal of time, since the I/O topology created as part of the electrical planning is presently imported manually in the related SW project of the machine. Moreover, a manual import is more error-prone because of human mistake than an automatic configuration tool. First, an introduction about TwinCAT 3, EtherCAT and Automation Interface is provided; then, it is analyzed the official Beckhoff tool, XCAD Interface, and the requirements on the electrical planning to use it: the interface is realized by means of the AutomationML format. Finally, due to some limitations observed, the design and implementation of a company internal tool is performed. Tests and validation of the tool are performed on a sample production line of the company.

Machine learning and convolutional neural networks for melanomas identification

Il machine learning negli ultimi anni ha acquisito una crescente popolarità nell’ambito della ricerca scientifica e delle sue applicazioni. Lo scopo di questa tesi è stato quello di studiare il machine learning nei suoi aspetti generali e applicarlo a problemi di computer vision. La tesi ha affrontato le difficoltà del dover spiegare dal punto di vista teorico gli algoritmi alla base delle reti neurali convoluzionali e ha successivamente trattato due problemi concreti di riconoscimento immagini: il dataset MNIST (immagini di cifre scritte a mano) e un dataset che sarà chiamato ”MELANOMA dataset” (immagini di melanomi e nevi sani). Utilizzando le tecniche spiegate nella sezione teorica si sono riusciti ad ottenere risultati soddifacenti per entrambi i dataset ottenendo una precisione del 98% per il MNIST e del 76.8% per il MELANOMA dataset

Neural Radiance Fields for Relighting and View Synthesis

Neural scene representation and neural rendering are new computer vision techniques that enable the reconstruction and implicit representation of real 3D scenes from a set of 2D captured images, by fitting a deep neural network. The trained network can then be used to render novel views of the scene. A recent work in this field, Neural Radiance Fields (NeRF), presented a state-of-the-art approach, which uses a simple Multilayer Perceptron (MLP) to generate photo-realistic RGB images of a scene from arbitrary viewpoints. However, NeRF does not model any light interaction with the fitted scene; therefore, despite producing compelling results for the view synthesis task, it does not provide a solution for relighting. In this work, we propose a new architecture to enable relighting capabilities in NeRF-based representations and we introduce a new real-world dataset to train and evaluate such a model. Our method demonstrates the ability to perform realistic rendering of novel views under arbitrary lighting conditions.

Continual learning on nano drones

Miniaturized flying robotic platforms, called nano-drones, have the potential to revolutionize the autonomous robots industry sector thanks to their very small form factor. The nano-drones’ limited payload only allows for a sub-100mW microcontroller unit for the on-board computations. Therefore, traditional computer vision and control algorithms are too computationally expensive to be executed on board these palm-sized robots, and we are forced to rely on artificial intelligence to trade off accuracy in favor of lightweight pipelines for autonomous tasks. However, relying on deep learning exposes us to the problem of generalization since the deployment scenario of a convolutional neural network (CNN) is often composed by different visual cues and different features from those learned during training, leading to poor inference performances. Our objective is to develop and deploy and adaptation algorithm, based on the concept of latent replays, that would allow us to fine-tune a CNN to work in new and diverse deployment scenarios. To do so we start from an existing model for visual human pose estimation, called PULPFrontnet, which is used to identify the pose of a human subject in space through its 4 output variables, and we present the design of our novel adaptation algorithm, which features automatic data gathering and labeling and on-device deployment. We therefore showcase the ability of our algorithm to adapt PULP-Frontnet to new deployment scenarios, improving the R2 scores of the four network outputs, with respect to an unknown environment, from approximately [−0.2, 0.4, 0.0,−0.7] to [0.25, 0.45, 0.2, 0.1]. Finally we demonstrate how it is possible to fine-tune our neural network in real time (i.e., under 76 seconds), using the target parallel ultra-low power GAP 8 System-on-Chip on board the nano-drone, and we show how all adaptation operations can take place using less than 2mWh of energy, a small fraction of the available battery power.

Studio ed implementazione di algoritmi di stereo vision in ambito mobile: l'applicazione "SuperStereo"

L'analisi di un'immagine con strumenti automatici si è sviluppata in quella che oggi viene chiamata "computer vision", la materia di studio proveniente dal mondo informatico che si occupa, letteralmente, di "vedere oltre", di estrarre da una figura una serie di aspetti strutturali, sotto forma di dati numerici. Tra le tante aree di ricerca che ne derivano, una in particolare è dedicata alla comprensione di un dettaglio estremamente interessante, che si presta ad applicazioni di molteplici tipologie: la profondità. L'idea di poter recuperare ciò che, apparentemente, si era perso fermando una scena ed imprimendone l'istante in un piano a due dimensioni poteva sembrare, fino a non troppi anni fa, qualcosa di impossibile. Grazie alla cosiddetta "visione stereo", invece, oggi possiamo godere della "terza dimensione" in diversi ambiti, legati ad attività professionali piuttosto che di svago. Inoltre, si presta ad utilizzi ancora più interessanti quando gli strumenti possono vantare caratteristiche tecniche accessibili, come dimensioni ridotte e facilità d'uso. Proprio quest'ultimo aspetto ha catturato l'attenzione di un gruppo di lavoro, dal quale è nata l'idea di sviluppare una soluzione, chiamata "SuperStereo", capace di permettere la stereo vision usando uno strumento estremamente diffuso nel mercato tecnologico globale: uno smartphone e, più in generale, qualsiasi dispositivo mobile appartenente a questa categoria.