Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Data Mining - Concepts and Techniques.

Training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence. A promising alternative is to fine-tune a CNN that has been pre-trained using, for instance, a large set of labeled natural images. However, the substantial differences between natural and medical images may advise against such knowledge transfer. In this paper, we seek to answer the following central question in the context of medical image analysis: Can the use of pre-trained deep CNNs with sufficient fine-tuning eliminate the need for training a deep CNN from scratch? To address this question, we considered four distinct medical imaging applications in three specialties (radiology, cardiology, and gastroenterology) involving classification, detection, and segmentation from three different imaging modalities, and investigated how the performance of deep CNNs trained from scratch compared with the pre-trained CNNs fine-tuned in a layer-wise manner. Our experiments consistently demonstrated that 1) the use of a pre-trained CNN with adequate fine-tuning outperformed or, in the worst case, performed as well as a CNN trained from scratch; 2) fine-tuned CNNs were more robust to the size of training sets than CNNs trained from scratch; 3) neither shallow tuning nor deep tuning was the optimal choice for a particular application; and 4) our layer-wise fine-tuning scheme could offer a practical way to reach the best performance for the application at hand based on the amount of available data.

Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?

MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

Обнаружение транспортных средств на изображениях загородных шоссе на основе метода Single shot multibox Detector

The interpretation of medical images depends on physicians' experience. Over time, physicians develop their ability to examine the images, and this is usually reflected on gaze patterns they follow to observe visual cues, which lead them to diagnostic decisions. In the context of gaze prediction, graph and machine learning methods have been proposed for the visual saliency estimation on generic images. In this work we preset a novel and robust gaze estimation methodology based on physicians' eye fixations, using convolutional neural networks combined with regularization methods, on medical images taken during Wireless Capsule Endoscopy (WCE). Furthermore, we present a novel dataset of physicians' eye fixation patterns which was used for the training of the neural network model. The model was able to achieve 68.5% Judd's Area Under the receiver operating Characteristic (AUC-J).

MedGaze: Gaze Estimation on WCE Images Based on a CNN Autoencoder

The huge amount of video data produced daily by camera-based systems, such as surveilance, medical and telecommunication systems, emerges the need for effective video summarization (VS) methods. These methods should be capable of creating an overview of the video content. In this paper, we propose a novel VS method based on a Generative Adversarial Network (GAN) model pre-trained with human eye fixations. The main contribution of the proposed method is that it can provide perceptually compatible video summaries by combining both perceived color and spatiotemporal visual attention cues in a unsupervised scheme. Several fusion approaches are considered for robustness under uncertainty, and personalization. The proposed method is evaluated in comparison to state-of-the-art VS approaches on the benchmark dataset VSUMM. The experimental results conclude that SalSum outperforms the state-of-the-art approaches by providing the highest f-measure score on the VSUMM benchmark.

SalSum: Saliency-based Video Summarization using Generative Adversarial Networks.

Conventional Content-Based Image Retrieval (CBIR) systems make use of similarity measures estimated directly from low-level image features, involving multidimensional and exhaustive, nearest neighbor searching. In this paper we present an image retrieval methodology suited for efficient search in cultural heritage images that utilizes similarity measures defined over higher-level patterns associated with clusters of low-level image features. The similarity between two patterns is estimated as a function of the similarity between both the structure and the measure components of the patterns. We evaluate our system using cultural heritage images derived from the repository of the Foundation of Hellenic World (FHW). For the experiments we use Local Binary Pattern (LBP) and contrast distributions as image features and the results show that the proposed pattern-based approach efficiently retrieves images compared to commonly employed methods.

/pdf/pattern-based-retrieval-of-cultural-heritage-images-39gt1hw6iy.pdf

Pattern-Based Retrieval of Cultural Heritage Images

This paper presents a novel methodology for unsupervised mining of patterns of pulmonary infections from plain chest radiographs. The methodology is based on a hierarchical scheme of partitional clusterings fusing information represented by non-negative intensity and textural image features. Partitional clustering is realized by factorization of the feature matrices under non-negativity constraints. In order to enhance its clustering performance a dyadic cluster merging approach has been devised. The spatial distribution of the mined radiographic patterns comprises a cue for the assessment of the extent of an infection. The results of the comprehensive experimentation performed show that the proposed approach achieves an accuracy of 94.1 %, outperforming both representative unsupervised and supervised mining approaches.

Dimitris K. Iakovidis

Papers

MedGaze: Gaze Estimation on WCE Images Based on a CNN Autoencoder

SalSum: Saliency-based Video Summarization using Generative Adversarial Networks.

Pattern-Based Retrieval of Cultural Heritage Images

Unsupervised mining of radiografic pulmonary infection patterns

Digital Twin for Simulation and Evaluation of Assistive Navigation Systems