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

Robust object recognition is a crucial skill for robots operating autonomously in real world environments. Range sensors such as LiDAR and RGBD cameras are increasingly found in modern robotic systems, providing a rich source of 3D information that can aid in this task. However, many current systems do not fully utilize this information and have trouble efficiently dealing with large amounts of point cloud data. In this paper, we propose VoxNet, an architecture to tackle this problem by integrating a volumetric Occupancy Grid representation with a supervised 3D Convolutional Neural Network (3D CNN). We evaluate our approach on publicly available benchmarks using LiDAR, RGBD, and CAD data. VoxNet achieves accuracy beyond the state of the art while labeling hundreds of instances per second.

/pdf/voxnet-a-3d-convolutional-neural-network-for-real-time-2dutg0m0bu.pdf

VoxNet: A 3D Convolutional Neural Network for real-time object recognition

An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

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?

Survey: Reservoir computing approaches to recurrent neural network training

This paper presents a new iris database that contains images with noise. This is in contrast with the existing databases, that are noise free. UBIRIS is a tool for the development of robust iris recognition algorithms for biometric proposes.

We present a detailed description of the many characteristics of UBIRIS and a comparison of several image segmentation approaches used in the current iris segmentation methods where it is evident their small tolerance to noisy images.

/pdf/ubiris-a-noisy-iris-image-database-53y36eu8mv.pdf

UBIRIS: a noisy iris image database

The iris is regarded as one of the most useful traits for biometric recognition and the dissemination of nationwide iris-based recognition systems is imminent. However, currently deployed systems rely on heavy imaging constraints to capture near infrared images with enough quality. Also, all of the publicly available iris image databases contain data correspondent to such imaging constraints and therefore are exclusively suitable to evaluate methods thought to operate on these type of environments. The main purpose of this paper is to announce the availability of the UBIRIS.v2 database, a multisession iris images database which singularly contains data captured in the visible wavelength, at-a-distance (between four and eight meters) and on on-the-move. This database is freely available for researchers concerned about visible wavelength iris recognition and will be useful in accessing the feasibility and specifying the constraints of this type of biometric recognition.

/pdf/the-ubiris-v2-a-database-of-visible-wavelength-iris-images-4rx3v9hc5o.pdf

The UBIRIS.v2: A Database of Visible Wavelength Iris Images Captured On-the-Move and At-a-Distance

This paper focuses on noncooperative iris recognition, i.e., the capture of iris images at large distances, under less controlled lighting conditions, and without active participation of the subjects. This increases the probability of capturing very heterogeneous images (regarding focus, contrast, or brightness) and with several noise factors (iris obstructions and reflections). Current iris recognition systems are unable to deal with noisy data and substantially increase their error rates, especially the false rejections, in these conditions. We propose an iris classification method that divides the segmented and normalized iris image into six regions, makes an independent feature extraction and comparison for each region, and combines each of the dissimilarity values through a classification rule. Experiments show a substantial decrease, higher than 40 percent, of the false rejection rates in the recognition of noisy iris images

/pdf/toward-noncooperative-iris-recognition-a-classification-24a984x5mr.pdf

Toward Noncooperative Iris Recognition: A Classification Approach Using Multiple Signatures

An overview of the iris image segmentation methodologies for biometric purposes is presented. The main focus is on the analysis of the ability of segmentation algorithms to process images with heterogeneous characteristics, simulating the dynamics of a non-cooperative environment. The accuracy of the four selected methodologies on the UBIRIS database is tested and, having concluded about their weak robustness when dealing with non-optimal images regarding focus, reflections, brightness or eyelid obstruction, the authors introduce a new and more robust iris image segmentation methodology. This new methodology could contribute to the aim of non-cooperative biometric iris recognition, where the ability to process this type of image is required.

/pdf/iris-segmentation-methodology-for-non-cooperative-6w1qnu962m.pdf

Iris segmentation methodology for non-cooperative recognition

Often practitioners face the issue of choosing the most adequate 3D features for their problem As with many other problems, there isn’t a “best” feature to use Nonetheless, we can gauge the relative accuracy of available features on common datasets That is what we propose to do in this paper: we describe the existing feature extraction algorithms in a public available point cloud library and perform a comparative evaluation on 3D point clouds, investigation both the object and category recognition performance The main conclusions are: increasing the number of keypoints improves recognition results at the expense of size and time; since there are big differences in terms of recognition performance, size and time requirements, the descriptor has to be matched to the desired task; one should use a descriptor that takes advantage of color; the SHOTCOLOR descriptor shows a good balance between recognition accuracy and time complexity

/pdf/3d-descriptors-for-object-and-category-recognition-a-4iblsdtfvy.pdf

Luís A. Alexandre

Papers

UBIRIS: a noisy iris image database

The UBIRIS.v2: A Database of Visible Wavelength Iris Images Captured On-the-Move and At-a-Distance

Toward Noncooperative Iris Recognition: A Classification Approach Using Multiple Signatures

Iris segmentation methodology for non-cooperative recognition

3D Descriptors for Object and Category Recognition: a Comparative Evaluation