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

Modeling visual attention-particularly stimulus-driven, saliency-based attention-has been a very active research area over the past 25 years. Many different models of attention are now available which, aside from lending theoretical contributions to other fields, have demonstrated successful applications in computer vision, mobile robotics, and cognitive systems. Here we review, from a computational perspective, the basic concepts of attention implemented in these models. We present a taxonomy of nearly 65 models, which provides a critical comparison of approaches, their capabilities, and shortcomings. In particular, 13 criteria derived from behavioral and computational studies are formulated for qualitative comparison of attention models. Furthermore, we address several challenging issues with models, including biological plausibility of the computations, correlation with eye movement datasets, bottom-up and top-down dissociation, and constructing meaningful performance measures. Finally, we highlight current research trends in attention modeling and provide insights for future.

State-of-the-Art in Visual Attention Modeling

Visual attention is a process that enables biological and machine vision systems to select the most relevant regions from a scene. Relevance is determined by two components: 1) top-down factors driven by task and 2) bottom-up factors that highlight image regions that are different from their surroundings. The latter are often referred to as “visual saliency.” Modeling bottom-up visual saliency has been the subject of numerous research efforts during the past 20 years, with many successful applications in computer vision and robotics. Available models have been tested with different datasets (e.g., synthetic psychological search arrays, natural images or videos) using different evaluation scores (e.g., search slopes, comparison to human eye tracking) and parameter settings. This has made direct comparison of models difficult. Here, we perform an exhaustive comparison of 35 state-of-the-art saliency models over 54 challenging synthetic patterns, three natural image datasets, and two video datasets, using three evaluation scores. We find that although model rankings vary, some models consistently perform better. Analysis of datasets reveals that existing datasets are highly center-biased, which influences some of the evaluation scores. Computational complexity analysis shows that some models are very fast, yet yield competitive eye movement prediction accuracy. Different models often have common easy/difficult stimuli. Furthermore, several concerns in visual saliency modeling, eye movement datasets, and evaluation scores are discussed and insights for future work are provided. Our study allows one to assess the state-of-the-art, helps to organizing this rapidly growing field, and sets a unified comparison framework for gauging future efforts, similar to the PASCAL VOC challenge in the object recognition and detection domains.

http://ilab.usc.edu/publications/doc/Borji_etal12tip.pdf

Quantitative Analysis of Human-Model Agreement in Visual Saliency Modeling: A Comparative Study

Dimensions of Reinforcement Learning

Soft Computing is an emerging field that consists of complementary elements of fuzzy logic, neural computing and evolutionary computation. Soft computing techniques have found wide applications. One of the most important applications is image segmentation. The process of partitioning a digital image into multiple regions or sets of pixels is called image segmentation. Segmentation is an essential step in image processing since it conditions the quality of the resulting interpretation. Lots of approaches have been proposed and a dense literature is available In order to extract as much information as possible from an environment, multicomponent images can be used. In the last decade, multicomponent images segmentation has received a great deal of attention for soft computing applications because it significantly improves the discrimination and the recognition capabilities compared with gray-level image segmentation methods. In this paper, the main aim is to understand the soft computing approach to image segmentation.

Image Segmentation - A Survey of Soft Computing Approaches

Online learning of task-driven object-based visual attention control

This paper focuses on the applicability of the features inspired by the visual ventral stream for handwritten character recognition. A set of scale and translation invariant C2 features are first extracted from all images in the dataset. Three standard classifiers kNN, ANN and SVM are then trained over a training set and then compared over a separate test set. In order to achieve higher recognition rate, a two stage classifier was designed with different preprocessing in the second stage. Experiments performed to validate the method on the well-known MNIST database, standard Farsi digits and characters, exhibit high recognition rates and compete with some of the best existing approaches. Moreover an analysis is conducted to evaluate the robustness of this approach to orientation, scale and translation distortions.

/pdf/robust-handwritten-character-recognition-with-features-46d3snmzmn.pdf

Robust Handwritten Character Recognition with Features Inspired by Visual Ventral Stream

In this paper we examine the use of global texture analysis based approaches for the purpose of Persian font recognition in machine-printed document images. Most existing methods for font recognition make use of local typographical features and connected component analysis. However derivation of such features is not an easy task. Gabor filters are appropriate tools for texture analysis and are motivated by human visual system. Here we consider document images as textures and use Gabor filter responses for identifying the fonts. The method is content independent and involves no local feature analysis. Two different classifiers Weighted Euclidean Distance and SVM are used for the purpose of classification. Experiments on seven different type faces and four font styles show average accuracy of 85% with WED and 82% with SVM classifier over typefaces

/pdf/support-vector-machine-for-persian-font-recognition-4xscjs8l8n.pdf

Support Vector Machine for Persian Font Recognition

Humans are very efficient in recognizing alphanumeric characters, even in the presence of significant image distortions. Recent advances in visual neuroscience have led to a solid model of object and shape recognition in the visual ventral stream which competes with the state-of-the-art computer vision systems on some standard recognition tasks. A modification of this model is also proposed by adding more biologically inspired properties such as sparsification of features, lateral inhibition and feature localization to enhance its performance. In this study, we show that using features proposed by the modified model results in higher handwritten digit recognition rates compared with the original model over English and Farsi handwritten digit datasets. Our analyses also demonstrate higher invariance of the modified model to various image distortions.

/pdf/invariance-analysis-of-modified-c2-features-case-study-3qyygj0isg.pdf

Invariance analysis of modified C2 features: case study—handwritten digit recognition

A new method for color image segmentation using fuzzy logic is proposed in this paper. Our aim here is to automatically produce a fuzzy system for color classification and image segmentation with least number of rules and minimum error rate. Particle swarm optimization is a sub class of evolutionary algorithms that has been inspired from social behavior of fishes, bees, birds, etc, that live together in colonies. We use comprehensive learning particle swarm optimization (CLPSO) technique to find optimal fuzzy rules and membership functions because it discourages premature convergence. Here each particle of the swarm codes a set of fuzzy rules. During evolution, a population member tries to maximize a fitness criterion which is here high classification rate and small number of rules. Finally, particle with the highest fitness value is selected as the best set of fuzzy rules for image segmentation. Our results, using this method for soccer field image segmentation in Robocop contests shows 89% performance. Less computational load is needed when using this method compared with other methods like ANFIS, because it generates a smaller number of fuzzy rules. Large train dataset and its variety, makes the proposed method invariant to illumination noise

/pdf/evolving-a-fuzzy-rule-base-for-image-segmentation-21l6rymkxt.pdf

Mandana Hamidi

Papers

Online learning of task-driven object-based visual attention control

Robust Handwritten Character Recognition with Features Inspired by Visual Ventral Stream

Support Vector Machine for Persian Font Recognition

Invariance analysis of modified C2 features: case study—handwritten digit recognition

Evolving a Fuzzy Rule-Base for Image Segmentation