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

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Recurrent neural networks are powerful sequence learners. They are able to incorporate context information in a flexible way, and are robust to localised distortions of the input data. These properties make them well suited to sequence labelling, where input sequences are transcribed with streams of labels. The aim of this thesis is to advance the state-of-the-art in supervised sequence labelling with recurrent networks. Its two main contributions are (1) a new type of output layer that allows recurrent networks to be trained directly for sequence labelling tasks where the alignment between the inputs and the labels is unknown, and (2) an extension of the long short-term memory network architecture to multidimensional data, such as images and video sequences.

https://mediatum.ub.tum.de/doc/673554/file.pdf

Supervised Sequence Labelling with Recurrent Neural Networks

This paper analyzes, compares, and contrasts technical challenges, methods, and the performance of text detection and recognition research in color imagery It summarizes the fundamental problems and enumerates factors that should be considered when addressing these problems Existing techniques are categorized as either stepwise or integrated and sub-problems are highlighted including text localization, verification, segmentation and recognition Special issues associated with the enhancement of degraded text and the processing of video text, multi-oriented, perspectively distorted and multilingual text are also addressed The categories and sub-categories of text are illustrated, benchmark datasets are enumerated, and the performance of the most representative approaches is compared This review provides a fundamental comparison and analysis of the remaining problems in the field

Text Detection and Recognition in Imagery: A Survey

In recent years, along with the extraordinary diffusion of the Internet and a growing need for personal verification in many daily applications, automatic signature verification is being considered with renewed interest. This paper presents the state of the art in automatic signature verification. It addresses the most valuable results obtained so far and highlights the most profitable directions of research to date. It includes a comprehensive bibliography of more than 300 selected references as an aid for researchers working in the field.

/pdf/automatic-signature-verification-the-state-of-the-art-68njryqnhw.pdf

Automatic Signature Verification: The State of the Art

Copy-move forgery detection using multiresolution local binary patterns.

A statistical method embedded with statistical features is proposed for Farsi/Arabic handwritten zip code recognition in this paper. The numeral is first smoothed and the skeleton is obtained. A set of feature points are then detected and the skeleton is decomposed into primitives. A primitive code includes the information of each primitive and a global code is derived from the primitive codes to describe the topological structure of the skeleton. By using the average and variance of X and Y changes in each primitive, the direction and curvature of the skeleton can be statistically described. Since the global codes have different lengths, we applied PCA algorithm to normalize their lengths. Thanks to statistically description of the skeleton, we can use the nearest neighbor classifier for recognition. According to experimental results, classification rate of 94.44% is obtained for numerals on the test sets gathered from various people with different educational background and different ages. Our database includes 480 samples per digit. We used 280 samples of each digit for training and the rest [200] for test.

Structural decomposition and statistical description of Farsi/Arabic handwritten numeric characters

Perceptual image hashing finds increasing attention in several multimedia security applications such as image identification/authentication, tamper detection, and watermarking. Robust feature extraction is the main challenge in hashing schemes. Local binary pattern (LBP) is a new feature which is due to its simplicity, discriminative power, computational efficiency, and robustness to illumination changes has been used in various image applications. In this paper, we propose a robust image hashing scheme using center-symmetric local binary patterns (CSLBP). In the proposed image hashing, CSLBP features are extracted from each non-overlapping block within the original gray-scale image. For each block, the final hash code is obtained by inner product of its CSLBP feature vector and a pseudorandom weight vector. Furthermore, singular value decomposition (SVD) is combined with CSLBP to introduce a more robust hashing method called SVD-CSLBP. Performances of the proposed hashing schemes are evaluated with two groups of popular applications in perceptual image hashing schemes: image identification and image authentication. Experimental results show that the proposed methods are robust to a wide range of distortions and attacks such as additive noise, blurring, brightness changes and JPEG compression. Moreover, the proposed methods have this capability to localize the tampering area, which is not possible in all hashing schemes.

Perceptual image hashing using center-symmetric local binary patterns

This paper presents a new comprehensive database for isolated offline handwritten Farsi/Arabic numbers and characters for use in optical character recognition research. The database is freely available for academic use. So far no such a freely database in Farsi language is available. Grayscale images of 52,380 characters and 17,740 numerals are included. Each image was scanned from Iranian school entrance exam forms during the years 2004-2006 at 300 dpi. The only restriction imposed on the writers is to write each character within a rectangular box. The number of samples in each class of the database is non-uniform corresponding to their real life distributions. Also, for comparison purposes, each dataset has been properly divided into respective training and test sets.

https://hal.inria.fr/inria-00112676/document

A Comprehensive Isolated Farsi/Arabic Character Database for Handwritten OCR Research

Image encryption is an efficient technique to protect image content from unauthorized parties. In this paper a parallel image encryption method based on bitplane decomposition is proposed. The original grayscale image is converted to a set of binary images by local binary pattern (LBP) technique and bitplane decomposition (BPD) methods. Then, permutation and substitution steps are performed by genetic algorithm (GA) using crossover and mutation operations. Finally, these scrambled bitplanes are combined together to obtain encrypted image. Instead of random population selection in GA, a deterministic method with security keys is utilized to improve security level. The proposed encryption method has parallel processing capability for multiple bitplanes encryption. This distributed GA with multiple populations increases encryption speed and makes it suitable for real-time applications. Simulations and security analysis are done to demonstrate efficiency of our algorithm.

Saeed Mozaffari

Papers

Copy-move forgery detection using multiresolution local binary patterns.

Structural decomposition and statistical description of Farsi/Arabic handwritten numeric characters

Perceptual image hashing using center-symmetric local binary patterns

A Comprehensive Isolated Farsi/Arabic Character Database for Handwritten OCR Research

Parallel image encryption with bitplane decomposition and genetic algorithm