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

The PASCAL Visual Object Classes Challenge

A survey of content-based image retrieval with high-level semantics

Exploring and identifying structure is even more important for multivariate data than univariate data, given the difficulties in graphically presenting multivariate data and the comparative lack of parametric models to represent it. Unfortunately, such exploration is also inherently more difficult.

Multivariate Density Estimation

▶ Addresses the accessibility, usability, and, ultimately, acceptability of Information Society Technologies by anyone, anywhere, at anytime, and through any media and device. ▶ Focuses on theoretical, methodological, and empirical research, of both technological and non-technological nature. ▶ Features papers that report on theories, methods, tools, empirical results, reviews, case studies, and best-practice examples.

Universal access in the information society

In this paper we propose a novel color image retrieval technique based on Gaussian modelling of multichannel spatio-chromatic information. The query image is represented using a number of images expressing its similarity to a set of colors derived using the median cut quantization method. Having the image decomposed into multiple channels describing its similarity to image representative colors, the dimensionality of image representation is reduced using the Principal Components Analysis (PCA). The image data, transformed to a new coordinate system forms a new, reduced in number, set of channels which are modelled using a Gaussian Mixture Models (GMM) to preserve not only the color structure of the image but also its spatial color arrangement.

Color image retrieval based on spatio-chromatic multichannel Gaussian mixture modelling

Human face depicts what happens in the soul, therefore correct recognition of emotion on the basis of facial display is of high importance. This work concentrates on the problem of optimal classification technique selection for solving the issue of smiling versus neutral face recognition. There are compared most frequently applied classification techniques: k-nearest neighbourhood, support vector machines, and template matching. Their performance is evaluated on facial images from several image datasets, but with similar image description methods based on local binary patterns. According to the experiments results the linear support vector machine gives the most satisfactory outcomes for all conditions.

http://jmit.us.edu.pl/cms/jmitjrn/23/30_Nurzynska_3.pdf

Optimal classification method for smiling vs neutral facial display recognition

We provide a new non-motion compensated adaptive multichannel filter for the detection and removal of impulsive noise, bit errors and outliers in color video or color image sequences. The proposed nonlinear filter takes the advantages of the concept of the local entropy contrast and the robust order-statistics theory. The new entropy based vector median is computationally attractive, robust for a wide range of the impulsive noise corruption and significantly improves the signal-detail preservation capability of standard vector median filter. Because the precision of statistical operators such as mean or entropy increases with the increased number of observed samples, the used spatiotemporal cube filter window guarantees a high accuracy of the proposed method that is able to achieve excellent results in terms of commonly used objective measures and clearly outperforms standard vector filtering schemes© (2003) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Three-dimensional entropy vector median filter for color video filtering

Emotions are one of the most important cues of non-verbal communication, therefore are easily recognized by people. However, correct identification of intentions causes many problems, because telling apart the true emotion expression from the fake one is difficult. Therefore, there is a wide search nowadays for automatic techniques, which use computers to analyze behavior of people and learn the differences between spontaneous and posed emotional gestures. In this research we concentrate on the analysis of facial expressions in order to recognize between Duchenne (real) and fake smiles. Our approach treats the input movie as a dynamic texture and exploits LBP-TOP technique for its description. Additionally, the average facial image is removed from consideration as it is assumed, that only tiny changes differ the smile characters. The results obtained on UVA-NEMO dataset proved that it is possible to classify accurately between the spontaneous and posed smiles. Moreover, the influence of facial parts as well as changes due to a phase of smile are investigated.

Smile veracity recognition using 3D texture features for image sequence processing

This paper focuses on genetic optimization and filtering efficiency of a recently developed class of Weighted Vector Directional Filters (WVDFs), which minimize the aggregated weighted angular distances between the samples contained in a sliding filtering window. As shown in the paper, the proposed genetically optimized WVDFs hold excellent detail preserving characteristics and are able to remove impulsive noise affecting color images.

Bogdan Smolka

Papers

Color image retrieval based on spatio-chromatic multichannel Gaussian mixture modelling

Optimal classification method for smiling vs neutral facial display recognition

Three-dimensional entropy vector median filter for color video filtering

Smile veracity recognition using 3D texture features for image sequence processing

Weighted Vector Directional Filters optimized by genetic algorithms