We have witnessed great interest and a wealth of promise in content-based image retrieval as an emerging technology. While the last decade laid foundation to such promise, it also paved the way for a large number of new techniques and systems, got many new people involved, and triggered stronger association of weakly related fields. In this article, we survey almost 300 key theoretical and empirical contributions in the current decade related to image retrieval and automatic image annotation, and in the process discuss the spawning of related subfields. We also discuss significant challenges involved in the adaptation of existing image retrieval techniques to build systems that can be useful in the real world. In retrospect of what has been achieved so far, we also conjecture what the future may hold for image retrieval research.

/pdf/image-retrieval-ideas-influences-and-trends-of-the-new-age-51whw4w7su.pdf

Image retrieval: Ideas, influences, and trends of the new age

IEEE Transactions on Pattern Analysis and Machine Intelligence

Computer and Robot Vision Vol. 1, by R.M. Haralick and Linda G. Shapiro, Addison-Wesley, 1992, ISBN 0-201-10887-1.

Computer and Robot Vision

While research on articulated human motion and pose estimation has progressed rapidly in the last few years, there has been no systematic quantitative evaluation of competing methods to establish the current state of the art. We present data obtained using a hardware system that is able to capture synchronized video and ground-truth 3D motion. The resulting HumanEva datasets contain multiple subjects performing a set of predefined actions with a number of repetitions. On the order of 40,000 frames of synchronized motion capture and multi-view video (resulting in over one quarter million image frames in total) were collected at 60 Hz with an additional 37,000 time instants of pure motion capture data. A standard set of error measures is defined for evaluating both 2D and 3D pose estimation and tracking algorithms. We also describe a baseline algorithm for 3D articulated tracking that uses a relatively standard Bayesian framework with optimization in the form of Sequential Importance Resampling and Annealed Particle Filtering. In the context of this baseline algorithm we explore a variety of likelihood functions, prior models of human motion and the effects of algorithm parameters. Our experiments suggest that image observation models and motion priors play important roles in performance, and that in a multi-view laboratory environment, where initialization is available, Bayesian filtering tends to perform well. The datasets and the software are made available to the research community. This infrastructure will support the development of new articulated motion and pose estimation algorithms, will provide a baseline for the evaluation and comparison of new methods, and will help establish the current state of the art in human pose estimation and tracking.

/pdf/humaneva-synchronized-video-and-motion-capture-dataset-and-4dx3ly40om.pdf

HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion

In this paper the main problems and the available solutions are addressed for the generation of 3D models from terrestrial images. Close range photogrammetry has dealt for many years with manual or automatic image measurements for precise 3D modelling. Nowadays 3D scanners are also becoming a standard source for input data in many application areas, but image-based modelling still remains the most complete, economical, portable, flexible and widely used approach. In this paper the full pipeline is presented for 3D modelling from terrestrial image data, considering the different approaches and analysing all the steps involved.

/pdf/image-based-3d-modelling-a-review-5msqumyd5o.pdf

Image-based 3d modelling: a review

This paper presents image acquisition and readability enhancement techniques for historical manuscripts developed in the interdisciplinary project “The Enigma of the Sinaitic Glagolitic Tradition” (Sinai II Project).1 We are mainly dealing with parchment documents originating from the 10th to the 12th centuries from St. Cather- ine’s Monastery on Mount Sinai. Their contents are being analyzed, fully or partly transcribed and edited in the course of the project. For comparison also other mss. are taken into consideration. The main challenge derives from the fact that some of the manuscripts are in a bad condition due to various damages, e.g. mold, washed out or faded text, etc. or contain palimpsest (=overwritten) parts. Therefore, the manuscripts investigated are imaged with a portable multispectral imaging system. This non-invasive conservation technique has proven extremely useful for the exami- nation and reconstruction of vanished text areas and erased or washed o palimpsest texts. Compared to regular white light, the illumination with speci c wavelengths highlights particular details of the documents, i.e. the writing and writing material, ruling, and underwritten text. In order to further enhance the contrast of the de- graded writings, several Blind Source Separation techniques are applied onto the multispectral images, including Principal Component Analysis (PCA), Independent Component Analysis (ICA) and others. Furthermore, this paper reports on other latest developments in the Sinai II Project, i.e. Document Image Dewarping, Automatic Layout Analysis, the recent result of another project related to our work: the image processing tool Paleo Toolbar, and the launch of the series Glagolitica Sinaitica.

Readability Enhancement and Palimpsest Decipherment of Historical Manuscripts

This paper deals with the enhancement of the readability in historic texts written on parchment. Due to mold, air, humidity, water, etc. parchment and text are partially damaged and consequently hard to read. In order to enhance the readability of the text, the manuscript pages are imaged in different spectral bands ranging from 360 to 1000 nm. The readability enhancement is based on a spectral and spatial analysis of the multivariate image data by multivariate spatial correlation. The main advantage of the method is that especially the text regions are enhanced which is provided by generating a mask image. This mask is based on the automatic reconstruction of the ruling scheme of the text pages. The method is tested on two medieval Slavonic manuscripts written on parchment.

Contrast Enhancement in Multispectral Images by Emphasizing Text Regions

Acquisition Evaluation on Outdoor Scanning for Archaeological Artifact Digitalization.

Model-based classification of painted portraits

Color Analysis.- On Determining the Color of the Illuminant Using the Dichromatic Reflection Model.- Probabilistic Color Optical Flow.- Illumination Invariant Color Texture Analysis Based on Sum- and Difference-Histograms.- Color Image Compression: Early Vision and the Multiresolution Representations.- Stereo Vision.- Optic Flow Goes Stereo: A Variational Method for Estimating Discontinuity-Preserving Dense Disparity Maps.- Lens Model Selection for Visual Tracking.- Omnidirectional Vision with Frontal Stereo.- Stereo Vision Based Reconstruction of Huge Urban Areas from an Airborne Pushbroom Camera (HRSC).- Calibration-Free Hand-Eye Calibration: A Structure-from-Motion Approach.- Invited Paper.- Simple Solvers for Large Quadratic Programming Tasks.- Segmentation and Grouping.- Voxel-Wise Gray Scale Invariants for Simultaneous Segmentation and Classification.- Automatic Foreground Propagation in Image Sequences for 3D Reconstruction.- Agglomerative Grouping of Observations by Bounding Entropy Variation.- Three-Dimensional Shape Knowledge for Joint Image Segmentation and Pose Estimation.- Goal-Directed Search with a Top-Down Modulated Computational Attention System.- Automatic Speech Understanding.- Telephone-Based Speech Dialog Systems.- Robust Parallel Speech Recognition in Multiple Energy Bands.- Pronunciation Feature Extraction.- Multi-lingual and Multi-modal Speech Processing and Applications.- 3D View Registration and Surface Modeling.- Cluster-Based Point Cloud Analysis for Rapid Scene Interpretation.- A Novel Parameter Decomposition Approach to Faithful Fitting of Quadric Surfaces.- 3D Surface Reconstruction by Combination of Photopolarimetry and Depth from Defocus.- Vision-Based 3D Object Localization Using Probabilistic Models of Appearance.- Projective Model for Central Catadioptric Cameras Using Clifford Algebra.- A New Methodology for Determination and Correction of Lens Distortion in 3D Measuring Systems Using Fringe Projection.- A Method for Fast Search of Variable Regions on Dynamic 3D Point Clouds.- 6D-Vision: Fusion of Stereo and Motion for Robust Environment Perception.- A Method for Determining Geometrical Distortion of Off-The-Shelf Wide-Angle Cameras.- Motion and Tracking.- A System for Marker-Less Human Motion Estimation.- A Fast Algorithm for Statistically Optimized Orientation Estimation.- A Direct Method for Real-Time Tracking in 3-D Under Variable Illumination.- Efficient Combination of Histograms for Real-Time Tracking Using Mean-Shift and Trust-Region Optimization.- Spiders as Robust Point Descriptors.- A Comparative Evaluation of Template and Histogram Based 2D Tracking Algorithms.- Bayesian Method for Motion Segmentation and Tracking in Compressed Videos.- Nonlinear Body Pose Estimation from Depth Images.- Computational Learning.- Conservative Visual Learning for Object Detection with Minimal Hand Labeling Effort.- Rapid Online Learning of Objects in a Biologically Motivated Recognition Architecture.- Semidefinite Clustering for Image Segmentation with A-priori Knowledge.- Separable Linear Discriminant Classification.- Improving a Discriminative Approach to Object Recognition Using Image Patches.- Comparison of Multiclass SVM Decomposition Schemes for Visual Object Recognition.- Shape Priors and Online Appearance Learning for Variational Segmentation and Object Recognition in Static Scenes.- Over-Complete Wavelet Approximation of a Support Vector Machine for Efficient Classification.- Regularization on Discrete Spaces.- Recognition of 3D Objects by Learning from Correspondences in a Sequence of Unlabeled Training Images.- Self-learning Segmentation and Classification of Cell-Nuclei in 3D Volumetric Data Using Voxel-Wise Gray Scale Invariants.- Applications.- License Plate Character Segmentation Using Hidden Markov Chains.- Digital Subtraction CT Lung Perfusion Image Based on 3D Affine Registration.- Combination of Tangent Distance and an Image Distortion Model for Appearance-Based Sign Language Recognition.- Volumetric Analysis of a Sinter Process in Time.- Network Snakes-Supported Extraction of Field Boundaries from Imagery.- Structure Features for Content-Based Image Retrieval.- Blind Background Subtraction in Dental Panoramic X-Ray Images: An Application Approach.- Robust Head Detection and Tracking in Cluttered Workshop Environments Using GMM.- Uncertainity and Robustness.- Stability and Local Feature Enhancement of Higher Order Nonlinear Diffusion Filtering.- Estimation of Geometric Entities and Operators from Uncertain Data.- Wiener Channel Smoothing: Robust Wiener Filtering of Images.- Signal and Noise Adapted Filters for Differential Motion Estimation.- Variational Deblurring of Images with Uncertain and Spatially Variant Blurs.- Energy Tensors: Quadratic, Phase Invariant Image Operators.- Invited Paper.- Object Categorization and the Need for Many-to-Many Matching.

Robert Sablatnig

Papers

Readability Enhancement and Palimpsest Decipherment of Historical Manuscripts

Contrast Enhancement in Multispectral Images by Emphasizing Text Regions

Acquisition Evaluation on Outdoor Scanning for Archaeological Artifact Digitalization.

Model-based classification of painted portraits

Pattern recognition : 27th DAGM Symposium, Vienna, Austria, August 31 - Sepember 2, 2005 : proceedings