Recent advances in convolutional neural networks

In the last few years, deep learning has led to very good performance on a variety of problems, such as visual recognition, speech recognition and natural language processing. Among different types of deep neural networks, convolutional neural networks have been most extensively studied. Leveraging on the rapid growth in the amount of the annotated data and the great improvements in the strengths of graphics processor units, the research on convolutional neural networks has been emerged swiftly and achieved state-of-the-art results on various tasks. In this paper, we provide a broad survey of the recent advances in convolutional neural networks. We detailize the improvements of CNN on different aspects, including layer design, activation function, loss function, regularization, optimization and fast computation. Besides, we also introduce various applications of convolutional neural networks in computer vision, speech and natural language processing.

Recent Advances in Convolutional Neural Networks

Thank you for reading introductory digital image processing. As you may know, people have search hundreds times for their chosen books like this introductory digital image processing, but end up in infectious downloads. Rather than enjoying a good book with a cup of tea in the afternoon, instead they are facing with some malicious virus inside their laptop. introductory digital image processing is available in our book collection an online access to it is set as public so you can get it instantly. Our books collection hosts in multiple locations, allowing you to get the most less latency time to download any of our books like this one. Merely said, the introductory digital image processing is universally compatible with any devices to read.

Introductory Digital Image Processing

Texture analysis is used in a very broad range of fields and applications, from texture classification (e.g., for remote sensing) to segmentation (e.g., in biomedical imaging), passing through image synthesis or pattern recognition (e.g., for image inpainting). For each of these image processing procedures, first, it is necessary to extract—from raw images—meaningful features that describe the texture properties. Various feature extraction methods have been proposed in the last decades. Each of them has its advantages and limitations: performances of some of them are not modified by translation, rotation, affine, and perspective transform; others have a low computational complexity; others, again, are easy to implement; and so on. This paper provides a comprehensive survey of the texture feature extraction methods. The latter are categorized into seven classes: statistical approaches, structural approaches, transform-based approaches, model-based approaches, graph-based approaches, learning-based approaches, and entropy-based approaches. For each method in these seven classes, we present the concept, the advantages, and the drawbacks and give examples of application. This survey allows us to identify two classes of methods that, particularly, deserve attention in the future, as their performances seem interesting, but their thorough study is not performed yet.

/pdf/texture-feature-extraction-methods-a-survey-4pjtaq24uv.pdf

Texture Feature Extraction Methods: A Survey

We present a new dataset for form understanding in noisy scanned documents (FUNSD) that aims at extracting and structuring the textual content of forms. The dataset comprises 199 real, fully annotated, scanned forms. The documents are noisy and vary widely in appearance, making form understanding (FoUn) a challenging task. The proposed dataset can be used for various tasks, including text detection, optical character recognition, spatial layout analysis, and entity labeling/linking. To the best of our knowledge, this is the first publicly available dataset with comprehensive annotations to address FoUn task. We also present a set of baselines and introduce metrics to evaluate performance on the FUNSD dataset, which can be downloaded at https://guillaumejaume.github.io/FUNSD.

FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents

https://hal.archives-ouvertes.fr/hal-01388088/document

A comprehensive survey of mostly textual document segmentation algorithms since 2008

In response to recent needs of biologists, we lay the foundations for a real-time stereo vision-based system for monitoring flying honeybees in three dimensions at the beehive entrance. Tracking bees is a challenging task as they are numerous, small, and fast-moving targets with chaotic motion. Contrary to current state-of-the-art approaches, we propose to tackle the problem in 3D space. We present a stereo vision-based system that is able to detect bees at the beehive entrance and is sufficiently reliable for tracking. Furthermore, we propose a detect-before-track approach that employs two innovating methods: hybrid segmentation using both intensity and depth images, and tuned 3D multi-target tracking based on the Kalman filter and Global Nearest Neighbor. Tests on robust ground truths for segmentation and tracking have shown that our segmentation and tracking methods clearly outperform standard 2D approaches.

/pdf/detecting-and-tracking-honeybees-in-3d-at-the-beehive-2kxl57or7g.pdf

Detecting and tracking honeybees in 3D at the beehive entrance using stereo vision

Paper documents still represent a large amount of information supports used nowadays and may contain critical data. Even though official documents are secured with techniques such as printed patterns or artwork, paper documents suffer from a lack of security. However, the high availability of cheap scanning and printing hardware allows non-experts to easily create fake documents. As the use of a watermarking system added during the document production step is hardly possible, solutions have to be proposed to distinguish a genuine document from a forged one. In this paper, we present an automatic forgery detection method based on document's intrinsic features at character level. This method is based on the one hand on outlier character detection in a discriminant feature space and on the other hand on the detection of strictly similar characters. Therefore, a feature set is computed for all characters. Then, based on a distance between characters of the same class, the character is classified as a genuine one or a fake one.

/pdf/a-system-based-on-intrinsic-features-for-fraudulent-document-5akw5z8z32.pdf

A System Based on Intrinsic Features for Fraudulent Document Detection

The use of different texture-based methods is pervasive in different subfields and tasks of document image analysis (DIA) and particularly in historical DIA (HDIA). Nevertheless, faced with a large diversity of texture-based methods used for HDIA, few questions arise. Which texture methods are firstly well suited for segmenting graphical contents from textual ones, discriminating various text fonts and scales, and separating different types of graphics? Then, which texture-based method represents a constructive compromise between the performance and the computational cost? Thus, in this article a benchmarking of the most classical and widely used texture-based feature sets has been conducted using a classical texture-based pixel-labeling scheme on a large corpus of historical documents to have satisfactory and clear answers to the above questions. We focus on determining the performance of each texture-based feature set according to the document content. The results reported in this study provide firstly a qualitative measure of which texture-based feature sets are the most appropriate and secondly a useful benchmark in terms of performance and computational cost for current and future research efforts in HDIA.

/pdf/texture-feature-benchmarking-and-evaluation-for-historical-4m5bz55djg.pdf

Texture feature benchmarking and evaluation for historical document image analysis

Texture feature analysis has undergone tremendous growth in recent years. It plays an important role for the analysis of many kinds of images. More recently, the use of texture analysis techniques for historical document image segmentation has become a logical and relevant choice in the conditions of significant document image degradation and in the context of lacking information on the document structure such as the document model and the typographical parameters. However, previous work in the use of texture analysis for segmentation of digitized historical document images has been limited to separately test one of the well-known texture-based approaches such as autocorrelation function, Grey Level Co-occurrence Matrix (GLCM), Gabor filters, gradient, wavelets, etc. In this paper we raise the question of which texture-based method could be better suited for discriminating on the one hand graphical regions from textual ones and on the other hand for separating textual regions with different sizes and fonts. The objective of this paper is to compare some of the well-known texture-based approaches: autocorrelation function, GLCM, and Gabor filters, used in a segmentation of digitized historical document images. Texture features are briefly described and quantitative results are obtained on simplified historical document images. The achieved results are very encouraging.

https://hal.archives-ouvertes.fr/hal-00934571/document

Petra Gomez-Krämer

Papers

A comprehensive survey of mostly textual document segmentation algorithms since 2008

Detecting and tracking honeybees in 3D at the beehive entrance using stereo vision

A System Based on Intrinsic Features for Fraudulent Document Detection

Texture feature benchmarking and evaluation for historical document image analysis

Texture feature evaluation for segmentation of historical document images