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

We are developing an automated classification and reconstruction system for archaeological fragments. The goal is to relate different fragments belonging to the same vessel based on shape, material and color, thus the color information is important in the pre-classification process. In this work a color specification technique is proposed, which exploits the fact that the spectral reflectance of materials like archaeological fragments vary slowly. We explain how the acquisition system is calibrated in order to get accurate colorimetric information with respect to archaeological requirements. Experimental results are presented for archaeological objects and for a set of test color patches.

Color classification of archaeological fragments

Motivated by the requirements of modern archaeologists, we are developing a documentation system based on structured light for acquisition of ceramics. Fragments of ceramics are daily finds at excavations and important for archaeological research, because their shape leads to information about ancient cultures. The shapes used for documentation are called profile lines and estimated by a vertical cross-section of orientated fragments. As ceramics have been produced using rotational plates for several thousands of years, the rotational axis can be used for orientation. Therefore we conducted experiments using existing methods for estimation of the rotational axis. The drawbacks of these methods are the requirement of either complete objects or industrialized quality of symmetry. Therefore we show a new method using circle templates, which has been inspired by the manual method of archaeologists. In this work we present results using previous and related work in comparison with the estimation of the rotational axis using circle templates. The results of the presented methods are shown for synthetic data, well-known fragments and real data acquired at an archaeological excavation. Finally a conclusion and an outlook is given.

Orientation of Fragments of Rotationally Symmetrical 3D-Shapes for Archaeological Documentation

This paperl describes visual landmark extraction for self localization of an auitonomolus mobile robot in at wellknown dynamic environment. The gradient based Hough transform provides the strongest groupings ofcollineair pixels having roughly the same edge orientcation. Grouips of pixels are then processed to calcuilate length and end points of line segments, which together with the length anid direction of the normcal completes the description of the line segmnents. This is followed by classification offield markinigs which are bright lines and aircs on a dark background forming double edges of opposite gradient. Corners, junctions and line intersections are determined by the interpretation of detected line segments. Simulation results illustrate the performance of the method u(sing both real and sYnthetic

Line-based landmark recognition for self-localization of soccer robots

The origin of works of art can often not be attributed to a certain artist. Likewise it is difficult to say whether paintings or drawings are originals or forgeries. In various fields of art new technical methods are used to examine the age, the state of preservation and the origin of the materials used. For the examination of paintings, radiological methods like X-ray and infra-red diagnosis, digital radiography, computer-tomography, etc. and color analyzes are employed to authenticate art. But all these methods do not relate certain characteristics in art work to a specific artist -- the artist's personal style. In order to study this personal style of a painter, experts in art history and image processing try to examine the 'structural signature' based on brush strokes within paintings, in particular in portrait miniatures. A computer-aided classification and recognition system for portrait miniatures is developed, which enables a semi- automatic classification and forgery detection based on content, color, and brush strokes. A hierarchically structured classification scheme is introduced which separates the classification into three different levels of information: color, shape of region, and structure of brush strokes.

Structural analysis of paintings based on brush strokes

An algorithm for the automatic construction of a 3D model of archaeological vessels is presented. In archeology the determination of the exact volume of arbitrary vessels is of importance since this provides information about the manufacturer and the usage of the vessel. To acquire the shape of objects with handles in 3d is complicated, since occlusions of the object's surface are introduced by the handle and can only be resolved by taking multiple views. Therefore, the 3d reconstruction is based on a sequence of images of the object taken from different viewpoints. The object's silhouette is the only feature which is extracted from an input image. Images are acquired by rotating the object on a turntable in front of a stationary camera. The algorithm uses an octree representation of the model, and builds this model incrementally, by performing limited processing of all input images for each level of the octree. Beginning from the root node at the level 0 a rough model of the object is obtained quickly and is refined as the processed level of the octree increases. Results of the algorithm developed are presented for both synthetic and real input images.

Robert Sablatnig

Papers

Color classification of archaeological fragments

Orientation of Fragments of Rotationally Symmetrical 3D-Shapes for Archaeological Documentation

Line-based landmark recognition for self-localization of soccer robots

Structural analysis of paintings based on brush strokes

3D modeling of archaeological vessels using shape from silhouette