|
Statistical image analysis in quality control
Legát, David
Title: Statistical image analysis in quality control Author: David Legát Department: Department of probability and mathematical statistics Supervisor: Prof. RNDr. Jaromír Antoch, CSc. Abstract: Currently, necessity to handle unstructured data rises significantly. One important area of unstructured data manipulation is signal processing such as audio and video, for which there exist many procedures. This work deals with the statistical approach to image processing, in which the image is interpreted as a representative of a random field. It describes two problems: removing noise from an image which facilitates better interpretation of the image, and image classification, in which we try to identify and recognize objects displayed. Part of the work aimed at eliminating of noise deals primarily with the use of MCMC simulation methods. These procedures can be tested in software that is included. Part of the work dealing with the classification of the image describes various modifications of classification trees methods. An example of image processing, which is the identification of defects in woven fabrics, is presented at the end. 1
|
|
Active learning for Bayesian neural networks in image classification
Belák, Michal ; Šabata, Tomáš (advisor) ; Vomlelová, Marta (referee)
In the past few years, complex neural networks have achieved state of the art results in image classification. However, training these models requires large amounts of labelled data. Whereas unlabelled images are often readily available in large quantities, obtaining l abels takes considerable human effort. Active learning reduces the required labelling effort by selecting the most informative instances to label. The most popular active learning query strategy framework, uncertainty sampling, uses uncertainty estimates of the model being trained to select instances for labelling. However, modern classification neural networks often do not provide good uncertainty estimates. Baye sian neural networks model uncertainties over model parameters, which can be used to obtain uncertainties over model predictions. Exact Bayesian inference is intractable for neural networks, however several approximate methods have been proposed. We experiment with three such methods using various uncertainty sampling active learning query strategies.
|
|
Detecting the Occurrence of Objects in a Video
Šamánek, Jan ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
This bachelor thesis deals with detection of objects in videos by using primarily convolution neural networks and creating simple user interface, which allows user to choose classification model and use it to analyze video or train given model on own dataset. First part is dedicated to description of machine learning and neural networks. After that follows the section about image description and image classification using machine learning algorithms and data augmentation. Last part deals with describtion of own design of neural network and user interface and describing achieved results.
|
|
Vehicle Make and Model Recognition in Image
Buchta, Martin ; Špaňhel, Jakub (referee) ; Herout, Adam (advisor)
This thesis deals with classification of a car model from an image. It describes several methods, such as convolutional neural networks, methods limited to the fron/rear view and methods using 3D CAD models. From these approaches it chooses convolutional neural networks, which it further deals with. The work contains a description of the individual layers of which such a network consists. The practical part describes the procedure by which the classifier, that has an accuracy of 80.7\,\%, was created. A dataset containing 1\,034 photos was created to verify functionality. The work further experiments with different architectures and evaluates their accuracy. The work contains a program which, thanks to the car detector, finds the vehicle in the video and marks it with a square and a description of the car model in the given video.
|
|
Retinal biometry with low resolution images
Smrčková, Markéta ; Odstrčilík, Jan (referee) ; Kolář, Radim (advisor)
This thesis attempts to find an alternative method for biometric identification using retinal images. First part is focused on the introduction to biometrics, human eye anatomy and methods used for retinal biometry. The essence of neural networks and deep learning methods is described as it will be used practically. In the last part of the thesis a chosen identification algorithm and its implementation is described and the results are presented.
|
|
Deep Neural Networks Approximation
Stodůlka, Martin ; Mrázek, Vojtěch (referee) ; Vaverka, Filip (advisor)
The goal of this work is to find out the impact of approximated computing on accuracy of deep neural network, specifically neural networks for image classification. A version of framework Caffe called Ristretto-caffe was chosen for neural network implementation, which was extended for the use of approximated operations. Approximated computing was used for multiplication in forward pass for convolution. Approximated components from Evoapproxlib were chosen for this work.
|
|
The effect of the background and dataset size on training of neural networks for image classification
Mikulec, Vojtěch ; Kolařík, Martin (referee) ; Rajnoha, Martin (advisor)
This bachelor thesis deals with the impact of background and database size on training of neural networks for image classification. The work describes techniques of image processing using convolutional neural networks and the influence of background (noise) and database size on training. The work proposes methods which can be used to achieve faster and more accurate training process of convolutional neural networks. A binary classification of Labeled Faces in the Wild dataset is selected where the background is modified with color change or cropping for each experiment. The size of dataset is crucial for training convolutional neural networks, there are experiments with the size of training set in this work, which simulate a real problem with the lack of data when training convolutional neural networks for image classification.
|
|
Deep Learning for Image Classification
Ziková, Jana ; Veľas, Martin (referee) ; Hradiš, Michal (advisor)
This bachelor thesis deals with electronic commerce website products classification using product's photographs. For this purpose we use already implemented models of deep convolutional neural networks. Tho goal of this theses is to design experiments that will lead to the best possible results in product images classification.
|
|
Image Classification Using Genetic Programming
Jašíčková, Karolína ; Vašíček, Zdeněk (referee) ; Sekanina, Lukáš (advisor)
This thesis deals with image classification based on genetic programming and coevolution. Genetic programming algorithms make generating executable structures possible, which allows us to design solutions in form of programs. Using coevolution with the fitness prediction lowers the amount of time consumed by fitness evaluation and, therefore, also the execution time. The thesis describes a theoretical background of evolutionary algorithms and, in particular, cartesian genetic programming. We also describe coevolutionary algorithms properties and especially the proposed method for the image classifier evolution using coevolution of fitness predictors, where the objective is to find a good compromise between the classification accuracy, design time and classifier complexity. A part of the thesis is implementation of the proposed method, conducting the experiments and comparison of obtained results with other methods.
|
|
Texture modeling applied to medical images
Remeš, Václav ; Haindl, Michal (advisor)
and contributions This thesis presents novel descriptive multidimensional Markovian textural models applied to computer aided diagnosis in the field of X-ray mammogra- phy. These general mathematical models, applicable in wide areas of texture modeling outside X-ray mammography as well, provide ideal visual verification using synthesis of the corresponding measured data spaces, contrary to stan- dard discriminative models. All achieved results in the thesis are extensively benchmarked. The thesis presents two methods for breast density classification in X-ray mammography. The methods were tested on the widely known MIAS database and the state-of-the art INbreast database, with competitive results. Several methods for completely automatic mammogram texture enhance- ment are presented. These methods are based on the descriptive textural mod- els developed in the thesis which automatically adapt to the analyzed X-ray texture, thus being universal for any type of input without the need of further manual tuning of specific parameters. The methods' outputs highlight regions of interest, detected as textural abnormalities. The methods provide the pos- sibility of enhancement tuned to specific types of mammogram tissue. Hence, the enhanced mammograms can help radiologists to decrease their false negative...
|