Abstract—We present a neural network-based upright frontal face detection system. A retinally connected neural network examines small windows of an image and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We present a straightforward procedure for aligning positive face examples for training. To collect negative examples, we use a bootstrap algorithm, which adds false detections into the training set as training progresses. This eliminates the difficult task of manually selecting nonface training examples, which must be chosen to span the entire space of nonface images. Simple heuristics, such as using the fact that faces rarely overlap in images, can further improve the accuracy. Comparisons with several other state-of-the-art face detection systems are presented, showing that our system has comparable performance in terms of detection and false-positive rates. Index Terms—Face detection, pattern recognition, computer vision, artificial neural networks, machine learning.

This paper provides a comprehensive survey of the technical achievements in the research area of image retrieval, especially content-based image retrieval, an area that has been so active and prosperous in the past few years. The survey includes 100+ papers covering the research aspects of image feature representation and extraction, multidimensional indexing, and system design, three of the fundamental bases of content-based image retrieval. Furthermore, based on the state-of-the-art technology available now and the demand from real-world applications, open research issues are identified and future promising research directions are suggested. C ○ 1999 Academic Press 1.

Abstract not found

This paper provides a comprehensive survey of the technical achievements in the research area of Image Retrieval, especially Content-Based Image Retrieval, an area so active and prosperous in the past few years. The survey includes 100+ papers covering the research aspects of image feature representation and extraction, multi-dimensional indexing, and system design, three of the fundamental bases of Content-Based Image Retrieval. Furthermore, based on the state-of-the-art technology available now and the demand from real-world applications, open research issues are identified, and future promising research directions are suggested. 1. INTRODUCTION Recent years have seen a rapid increase of the size of digital image collections. Everyday, both military and civilian equipment generates giga-bytes of images. Huge amount of information is out there. However, we can not access to or make use of the information unless it is organized so as to allow efficient browsing, searching and retriev...

Storage and retrieval of multimedia has become a requirement for many contemporary information systems. These systems need to provide browsing, querying, navigation and sometimes composition capabilities involving various forms of media. In this survey we review techniques and systems for image and video retrieval. We first look at visual and non-visual features for image retrieval and techniques for using them. Temporal aspects of video retrieval are discussed next. We review several research and commercial systems including WWW-based systems and conclude with future directions. 1 Introduction The increasing availability of multimedia information combined with the decreasing storage and processing costs have changed the requirements on information systems drastically. Today, general purpose database systems are incorporating support for multimedia storage and retrieval, as well as features which used to be found in specialized imaging systems or multimedia databases. Increased use of...

The objective of this work 1 is to automatically generate a large number of images for a specified object class (for example, penguin). A multi-modal approach employing both text, meta data and visual features is used to gather many, high-quality images from the web. Candidate images are obtained by a text based web search querying on the object identifier (the word penguin). The web pages and the images they contain are downloaded. The task is then to remove irrelevant images and re-rank the remainder. First, the images are re-ranked using a Bayes posterior estimator trained on the text surrounding the image and meta data features (such as the image alternative tag, image title tag, and image filename). No visual information is used at this stage. Second, the top-ranked images are used as (noisy) training data and a SVM visual classifier is learnt to improve the ranking further. The principal novelty is in combining text/meta-data and visual features in order to achieve a completely automatic ranking of the images. Examples are given for a selection of animals (e.g. camels, sharks, penguins), vehicles (cars, airplanes, bikes) and other classes (guitar, wristwatch), totalling 18 classes. The results are assessed by precision/recall curves on ground truth annotated data and by comparison to previous approaches including those of Berg et al. [5] (on an additional six classes) and Fergus et al. [9]. 1.

In this paper, we give an overview of the PicToSeek system for exploring visual information on the World Wide Web. PicToSeek automatically collects, indexes and catalogs visual information entirely on the basis of the pictorial content. PicToSeek allows for contentbased image retrieval conducted in an interactive, iterative manner guided by the user by relevance feedback. Relevance feedback can be seen as a method of feature selection and weighting. The PicToSeek system has been implemented based on the client-server paradigm. The client is a Java Applet and takes care of interactive query formulation, the display of the results, and the relevance feedback specification given by the user. The server is a Servlet using C-libraries and takes care of the image feature extraction, feature weighting from relevance feedback, k-nearest neighbour feature classification, and image sorting. The system is available at http://www.wins.uva.nl/research/isis/zomax/. 1 Introduction With the growth a...

Content based indexing of multimedia has always been a challenging task. The enormity and the diversity of the multimedia content on the web adds another dimension to this challenge. In this paper, we examine ways of combining visual and textual information for content based indexing of multimedia on the web. In particular, we examine different methods of combining evidences due to face detection, Text/HTML analysis and face recognition for identifying person images. We provide experimental evaluation of the following strategies: i) Face detection on the image followed by Text/HTML analysis of the containing page; ii) face detection followed by face recognition; iii) face detection followed by a linear combination of evidences due to text/HTML analysis and face recognition; and iv) face detection followed by a Dempster-Shafer combination of evidences due to text/HTML analysis and face recognition. These strategies were implemented in an automatic web search agent named Diogenes 1 and...

Web image search has been explored and developed in academic as well as commercial areas for over a decade. To measure the similarity between Web images and user queries, most of the existing Web image search systems try to convert an image to textual keywords by analyzing the textual information available (such as surrounding text and image filename) with or without leveraging image visual features (such as color, texture, shape). In this way, the existing systems transform “Web images ” to the “query (text) ” space so as to compare the relevance of images to the query. In this paper, we present a novel solution to Web image search-similarity space projection (SSP). This algorithm takes images and queries as two heterogeneous object peers, and projects them into a third Euclidean “similarity space ” in which their similarity can be directly measured. The rule of projection guarantees that in the new space the relevant images are kept close to the corresponding query and those irrelevant ones are away from it. Experiments on realworld Web image collections showed that the proposed algorithm significantly outperformed traditional information retrieval models (such as vector space model) in the application of image search. Besides Web image search, we demonstrate that this algorithm can also be applied to image annotation scenario, and has promising performance. Thus, this algorithm unifies Web image search and image annotation into same framework.

Using both text and image content features, a hybrid image retrieval system for Word Wide Web is developed in this paper. We first use a text-based image meta-search engine to retrieve images from the Web based on the text information on the image host pages to provide an initial image set. Because of the high-speed and low cost nature of the text-based approach, we can easily retrieve a broad coverage of images with a high recall rate and a relatively low precision. An image content based ordering is then performed on the initial image set. All the images are clustered into different folders based on the image content features. In addition, the images can be re-ranked by the content features according to the user feedback. Such a design makes it truly practical to use both text and image content for image retrieval over the Internet. Experimental results confirm the efficiency of the system.