Segmentation of mammograms pertains to assigning a meaningful label to each pixel found in the image. The segmented mammogram facilitates both the function of Computer Aided Diagnosis Systems and the development of tools used by radiologists during examination. Over the years many approaches to this problem have been presented. A surge in the popularity of new methods to image processing involving deep neural networks present new possibilities in this domain, and this thesis evaluates mammogram segmentation as an application of a specialized neural network architecture, U-net. Results are produced on publicly available datasets mini-MIAS and CBIS-DDSM. Using these two datasets together with mammograms from Hologic and FUJI, instances of U-net are trained and evaluated within and across the different datasets. A total of 10 experiments are conducted using 4 different models. Averaged over classes Pectoral, Breast and Background the best Dice scores are: 0.987 for Hologic, 0.978 for FUJI, 0.967 for mini-MIAS and 0.971 for CBIS-DDSM.

The most common approach to analysing satellite imagery is building or object segmentation,which expects an algorithm to find and segment objects with specific boundaries thatare present in the satellite imagery. The company Vricon takes satellite imagery analysisfurther with the goal of reproducing the entire world into a 3D mesh. This 3D reconstructionis performed by a set of complex algorithms excelling in different object reconstructionswhich need sufficient labeling in the original 2D satellite imagery to ensure validtransformations. Vricon believes that the labeling of areas can be used to improve the algorithmselection process further. Therefore, the company wants to investigate if multinomiallarge area classification can be performed successfully using the satellite image data availableat the company. To enable this type of classification, the company’s gold-standarddataset containing labeled objects such as individual buildings, single trees, roads amongothers, has been transformed into an large area gold-standard dataset in an unsupervisedmanner. This dataset was later used to evaluate large area classification using several stateof-the-art Deep Convolutional Neural Network (DCNN) semantic segmentation architectureson both RGB as well as RGB and Digital Surface Model (DSM) height data. Theresults yield close to 63% mIoU and close to 80% pixel accuracy on validation data withoutusing the DSM height data in the process. This thesis additionally contributes with a novelapproach for large area gold-standard creation from existing object labeled datasets.

Drones are a very active area of research and object detection is a crucial part in achieving full autonomy of any robot. We investigated how state-of-the-art object detection algorithms perform on image data from a drone. For the evaluation we collected a number of datasets in an indoor office environment with different cameras and camera placements. We surveyed the literature of object detection and selected to research the algorithm R-FCN (Region based Fully Convolutional Network) for the evaluation. The performances on the different datasets were then compared, showing that using footage from a drone may be advantageous in scenarios where the goal is to detect as many objects as possible. Further, it was shown that the network, even if trained on normal angled images, can be used for detecting objects in fish eye images and that usage of a fisheye camera can increase the total number of detected objects in a scene. / Drönare är ett mycket aktivt forskningsområde och objektigenkänning är en viktig del för att uppnå full självstyrning för robotar. Vi undersökte hur dagens bästa objektigenkänningsalgoritmer presterar på bilddata från en drönare. Vi gjorde en literatturstudie och valde att undersöka algoritmen R-FCN (Region based Fully Convolutional Network). För att evaluera algoritmen spelades flera dataset in i en kontorsmiljö med olika kameror och kameraplaceringar. Prestandan på de olika dataseten jämfördes sedan och det visades att användningen av bilder från en drönare kan vara fördelaktig då målet är att hitta så många objekt som möjligt. Vidare visades att nätverket, även om det är tränat på bilder från en vanlig kamera, kan användas för att hitta objekt i vidvinklade bilder och att användningen av en vidvinkelkamera kan öka det totala antalet detekterade objekt i en scen.

In order to reduce bicycle-vehicle collisions, we design and implement a cost effectiveembedded system to warn cyclists of approaching vehicles. The system uses an Odroid C2 singleboard computer (SBC) to do vehicle and lane detection in real time using only vision. The system warns cyclist are warned of approaching cars using both a smartphone app and an LED indicator. Due to the limited performance of the Odroid C2 and other low power and low cost SBCs,we found that existing detection algorithms run either too slowly or do not have sufficient accuracy to be practical. Our solution to these limitations is to create a custom fully convolutional network(FCN) which is small enough to run at real time speeds on the Odroid C2 but robust enough tohave decent accuracy. We show that this FCN runs significantly faster than Tiny YOLOv3 andMobileNetv2 while getting similar accuracy when all are trained on a limited dataset. Since no dataset exists that separates the fronts of vehicles from other poses and is in the context of city and country roads, we create our own. Creating a dataset to train any detector hastraditionally been time consuming. We present and implement a way to efficiently do this usingminimal hand annotation by generating semi-synthetic images by cropping relatively few positive images into many background images. This creates a wider background class variance than wouldotherwise be possible.

Intra-prediction is a method for coding standalone frames in video coding. Until now, this has mainly been done using linear formulae. Using an Artificial Neural Network (ANN) may improve the prediction accuracy, leading to improved coding efficiency. In this degree project, Fully Connected Networks (FCN) and Convolutional Neural Networks (CNN) were used for intra-prediction. Experiments were done on samples from different image sizes, block sizes, and block contents, and their effect on the results were compared and discussed. The results show that ANN methods have the potential to perform better or on par with the video coder High Efficiency Video Coding (HEVC) in the intra-prediction task. The proposed ANN designs perform better on smaller block sizes, but different designs could lead to better performance on larger block sizes. It was found that training one network for each HEVC mode and using the most suitable network to predict each block improved performance of the ANN approach. / Intra-prediktion är en metod för kodning av stillbilder i videokodning. Hittills har detta främst gjorts med hjälp av linjära formler. Användning av artificialla neuronnät (ANN) skulle kunna öka prediktionsnoggrannheten och ge högre effektivitet vid kodning. I detta examensarbete användes fully connected networks (FCN) och convolutional neural networks (CNN) för att utföra intra-prediktion. Experiment gjordes på prover från olika bildstorlekar, blockstorlekar och blockinnehåll, och de olika parametrarnas effekt på resultaten jämfördes och diskuterades. Resultaten visar att ANN-metoder har potential att prestera bättre eller lika bra som videokodaren High Efficiency Video Coding (HEVC) för intra-prediktion. De föreslagna ANN-designerna presterar bättre på mindre blockstorlekar, men andra ANN-designs skulle kunna ge bättre prestanda för större blockstorlekar. Det konstaterades att prestandan för ANN-metoderna kunde ökas genom att träna ett nätverk för varje HEVC-mode och använda det mest passande nätverket för varje block.

Colorectal cancer is the second cause of cancer death in the world. Aiming to early detect and prevent this type of cancer, clinicians perform screenings through the colon searching for polyps (colorectal cancer precursor lesions).If found, these lesions are susceptible of being removed in order to further ana-lyze their malignancy degree. Automatic polyp segmentation is of primary impor-tance when it comes to computer-aided medical diagnosis using images obtained in colonoscopy screenings. These results allow for more precise medical diagnosis which can lead to earlier detection.This project proposed a neural network based solution for semantic segmenta-tion, using the U-net architecture.Combining different data augmentation techniques to alleviate the problem of data scarcity and conducting experiments on the different hyperparameters of the network, the U-net scored a mean Intersection over Union (IoU) of 0,6814. A final approach that combines prediction maps of different models scored a mean IoU of 0,7236.

The main result of this thesis is a deep learning model named BearNet, which can be trained to detect an arbitrary amount of objects as a set of points. The model is trained using the Weighted Hausdorff distance as loss function. BearNet has been applied and tested on two problems from the industry. These are: From an intensity image, detect two pocket points of an EU-pallet which an autonomous forklift could utilize when determining where to insert its forks. From a depth image, detect the start, bend and end points of a straw attached to a juice package, in order to help determine if the straw has been attached correctly. In the development process of BearNet I took inspiration from the designs of U-Net, UNet++ and a high resolution network named HRNet. Further, I used a dataset containing RGB-images from a surveillance camera located inside a mall, on which the aim was to detect head positions of all pedestrians. In an attempt to reproduce a result from another study, I found that the mall dataset suffers from training set contamination when a model is trained, validated, and tested on it with random sampling. Hence, I propose that the mall dataset is evaluated with a sequential data split strategy, to limit the problem. I found that the BearNet architecture is well suited for both the EU-pallet and straw datasets, and that it can be successfully used on either RGB,  intensity or depth images. On the EU-pallet and straw datasets, BearNet consistently produces point estimates within five and six pixels of ground truth, respectively. I also show that the straw dataset only constitutes a small subset of all the challenges that exist in the problem domain related to the attachment of a straw to a juice package, and that one therefore cannot train a robust deep learning model on it. As an example of this, models trained on the straw dataset cannot correctly handle samples in which there is no straw visible.

This master’s thesis evaluates automatic data annotation and machine learning predictions of iron ore pellets using tools provided by Amazon Web Services (AWS) in the cloud. The main tool in focus is Amazon SageMaker which is capable of automatic data annotation as well as building, training and deploying machine learning models quickly. Three different models was trained using SageMakers built in semantic segmentation algorithm, PSP, FCN and DeepLabV3. The dataset used for training and evaluation contains 180 images of iron ore pellets collected from LKAB’s experimental blast furnace in Luleå, Sweden. The Amazon Web Services solution for automatic annotation was shown to be of no use when annotating microscopic images of iron ore pellets. Ilastik which is an interactive learning and segmentation toolkit showed far superiority for the task at hand. Out of the three trained networks Fully-Convolutional Network (FCN) performed best looking at inference and training times, it was the quickest network to train and performed within 1% worse than the fastest in regard to inference time. The Fully-Convolutional Network had an average accuracy of 85.8% on the dataset, where both PSP & DeepLabV3 was showing similar performance. From the results in this thesis it was concluded that there are benefits of running deep neural networks as a cloud service for analysis and management ofiron ore pellets.

In this thesis is handled the problem of mushroom detection and recognition in natural environment. Convolutional neural networks are used. The beginning of this thesis is dedicated to the theory of neural networks. Further is solved the problem of object detection and classification. Using neural network trained for classification is solved also the task of localization. Results of trained CNNs are analised.

[pt] A partir de melhorias incrementais em uma conhecida rede neural convolucional (U-Net), diferentes técnicas são avaliadas quanto às suas performances na tarefa de segmentação semântica em imagens sísmicas. Mais especificamente, procura-se a identificação e delineamento de estruturas salinas no subsolo, o que é de grande relevância na indústria de óleo e gás para a exploração de petróleo em camadas pré-sal, por exemplo. Além disso, os desafios apresentados no tratamento destas imagens sísmicas se assemelham em muito aos encontrados em tarefas de áreas médicas como identificação de tumores e segmentação de tecidos, o que torna o estudo da tarefa em questão ainda mais valioso. Este trabalho pretende sugerir uma metodologia adequada de abordagem à tarefa e produzir redes neurais capazes de segmentar imagens sísmicas com bons resultados dentro das métricas utilizadas. Para alcançar estes objetivos, diferentes estruturas de redes, transferência de aprendizado e técnicas de aumentação de dados são testadas em dois datasets com diferentes níveis de complexidade. / [en] Through incremental improvements in a well-known convolutional neural network (U-Net), different techniques are evaluated regarding their performance on the task of semantic segmentation of seismic images. More specifically, the objective is the better identification and outline of subsurface salt structures, which is a task of great relevance for the oil and gas industry in the exploration of pre-salt layers, for example. Besides that application, the challenges imposed by the treatment of seismic images also resemble those found in medical fields like tumor detection and tissue segmentation, which makes the study of this task even more valuable. This work seeks to suggest a suitable methodology for the task and to yield neural networks that are capable of performing semantic segmentation of seismic images with good results regarding specific metrics. For that purpose, different network structures, transfer learning and data augmentation techniques are applied in two datasets with different levels of complexity.