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 work examines the use of convolutional neural networks with a focus on semantic and instance segmentation of cells from microscopic images. The theoretical part contains a description of deep neural networks and a summary of widely used convolutional architectures for image segmentation. The practical part of the work is devoted to the creation of a convolutional neural network model based on the U-Net architecture. It also contains cell segmentation of predicted images using three methods, namely thresholding, the watershed and the random walker.

<div>U-net is an image segmentation technique developed primarily for medical image analysis that can precisely segment images using a scarce amount of training data. These traits provide U-net with a high utility within the medical imaging community and have resulted in extensive adoption of U-net as the primary tool for segmentation tasks in medical imaging. The success of U-net is evident in its widespread use in nearly all major image modalities from CT scans and MRI to X-rays and microscopy. Furthermore, while U-net is largely a segmentation tool, there have been instances of the use of U-net in other applications. Given that U-net's potential is still increasing, this review examines the numerous developments and breakthroughs in the U-net architecture and provides observations on recent trends. We also discuss the many innovations that have advanced in deep learning and discuss how these tools facilitate U-net. In addition, we review the different image modalities and application areas that have been enhanced by U-net.</div><div>In recent years, deep learning for health care is rapidly infiltrating and transforming medical fields thanks to the advances in computing power, data availability, and algorithm development. In particular, U-Net, a deep learning technique, has achieved remarkable success in medical image segmentation and has become one of the premier tools in this area. While the accomplishments of U-Net and other deep learning algorithms are evident, there still exist many challenges in medical image processing to achieve human-like performance. In this thesis, we propose a U-net architecture that integrates a residual skip connections and recurrent feedback with EfficientNet as a pretrained encoder. Residual connections help feature propagation in deep neural networks and significantly improve performance against networks with a similar number of parameters while recurrent connections ameliorate gradient learning. We also propose a second model that utilizes densely connected layers aiding deeper neural networks. And the proposed third model that incorporates fractal expansions to bypass diminishing gradients. EfficientNet is a family of powerful pretrained encoders that streamline neural network design. The use of EfficientNet as an encoder provides the network with robust feature extraction that can be used by the U-Net decoder to create highly accurate segmentation maps. The proposed networks are evaluated against state-of-the-art deep learning based segmentation techniques to demonstrate their superior performance.</div>

This master´s thesis deals with blood vessel segmentation in retinal image data. The theoretical part is focused on the basic description of anatomy and physiology of the eye and methods of observing the back of the eye. This thesis also describes the principles of classical and convolutional neural networks and segmentation techniques that are used to segment blood vessel in retinal images. In the practical part, a segmentation method using convolutional neural network U-net is implemented. This neural network is trained on the three datasets. Two datasets include images from experimental video ophthalmoscope. Because it impossible to compare the results of these two datasets with any other methods of retinal blood vessel segmentation, U-net is trained on other dataset that is HRF database. This dataset includes fundus images. The results of testing on this dataset serves for comparing results with other methods of retinal blood vessel segmentation.

Diplomova praca sa zameriava na oblast zaostrovania obrazkov tvari. V teoretickej casti prace budu prezentovane moderne metody zaostrovania obrazkov pomocou jedineho obrazku a metody editacie obrazkov. Prakticka cast sa zameria na pristupy rekonstrukcie obrazkov zo sekvencie poskodenych obrazkov. Viacere modely neuronovych sieti so vstupom pre viacero obrazkov budu zhotovene a vyhodnotene. Alternativny pristup v podobe balika nastrojov na editaciu obrazkov bude taktiez predstaveny. Tieto nastroje budu vyuzivat najmodernejsie pristupy k editacii obrazkov s cielom spojit vizualne prvky tvari zo vstupnej sekvencie obrazkov do jedneho finalneho vystupu. V zavere prace budu vsetky metody navzajom porovnane.

The thesis deals with the classification of the retinal blood vessels in retinal image data. The first part of the thesis deals with the anatomy of the human eye and focuses on the description of the retina and its blood circulation. It further describes the principle of fundus camera and experimental video ophthalmoscope. The second part of the thesis is devoted to a literature search of academic publications that deal with the classification of the retinal vessels into arteries and veins. Subsequently, the principle of selected machine learning methods is presented. Based on the literature research, two methods for the classification of the blood vessels were proposed, the first one using the SVM classifier and the second one using the convolutional neural network U-Net. At the end, the analysis of vascular pulsations was performed. The practical part of the thesis was carried out in Matlab programming interface and images from the RITE, IOSTAR and AFIO database were used for classification and the retinal video sequences taken with an experimental video ophthalmoscope were processed in the analysis of pulsations.

In cancer diagnosis there is a goal of having the treatment being tailored to each patient. This in order to increase efficiency and reduce side effects. Using more data on each patient can help in achieving this. One such data source is histological images on tissues, such as lymph nodes. This report sets out to find a method in which such images on lymph nodes can be automatically segmented. This so that they can later be analysed and maybe tell in what stage a cancer is in. Such work is today done by hand, and this makes it a subjective process, that might differ between doctors and institutions. If there was a method done by a computer, the process would be replicable and objective. Also, a lot of time would be saved. The results show that such a method is reachable in this early stage of development. It is also quite efficient when segmenting the lymph node itself. The segmentation of smaller areas of the lymph nodes is not as efficient, but with further work in the area it might improve enough to be useful. Some issues are still had since the method relies in part on a person to decide a parameter in order to get a clean segmentation. The final conclusion is that one model is to prefer compared to the others and that further work on this might make it a useful tool in analysing histological images.

Image segmentation through neural networks and deep learning have, in the recent decade, become a successful tool for automated decision-making. For Luossavaara-Kiirunavaara Aktiebolag (LKAB), this means identifying the amount of slag inside a furnace through computer vision.  There are many prominent convolutional neural network architectures in the literature, and this thesis explores two: a modified U-Net and the PSPNet. The architectures were combined with three loss functions and three class weighting schemes resulting in 18 model configurations that were evaluated and compared. This thesis also explores transfer learning techniques for neural networks tasked with identifying slag in images from inside a furnace. The benefit of transfer learning is that the network can learn to find features from already labeled data of another context. Finally, the thesis explored how temporal information could be utilised by adding an LSTM layer to a model taking pairs of images as input, instead of one. The results show (1) that the PSPNet outperformed the U-Net for all tested configurations in all relevant metrics, (2) that the model is able to find more complex features while converging quicker by using transfer learning, and (3) that utilising temporal information reduced the variance of the predictions, and that the modified PSPNet using an LSTM layer showed promise in handling images with outlying characteristics.

Much research has been done on the use of machine learning to extract features such as buildings, lakes et cetera from satellite imagery, and while this dataset is valuable for many use cases, it is limited to time periods in which satellites were used. Historical maps have a much greater range of available time periods but the viability of using machine learning to extract data from these has not been investigated to any great extent. This case study uses a real-world use case to show the efficacy of using a U-Net convolutional neural network to extract features drawn on hand-drawn maps. By implementing a random forest as a pre-screener to the U-Net the goal was to filter out noise that could lead to false positives. By filtering out the noise the hope was to increase the accuracy of the U-Net. The pre-screener in this study has not performed well on the dataset and has not improved the performance of the U-Net. The U-Nets ability to extrapolate the location of features not explicitly drawn on the map was not clearly established. The results of this study show that the U-Net CNN could be an invaluable tool for quickly extracting data from this typically cumbersome data source, allowing for easier access to a wealth of data. The fields of archeology and climate science would find this especially useful.

No description available.