Michał Grega

Automated qualitative assessment of multi-modal distortions in digital images based on GLZ

This paper introduces a novel approach to a qualitative assessment of images affected by multi-modal distortions. The idea is to assess the image quality perceived by an end user in an automatic way in order to avoid the usual time-consuming, costly and non-repeatable method of collecting subjective scores during a psycho-physical experiment. This is achieved by computing quantitative image distortions and mapping results on qualitative scores. Useful mapping models have been proposed and constructed using the generalised linear model (GLZ), which is a generalisation of the least squares regression in statistics for ordinal data. Overall qualitative image distortion is computed based on partial quantitative distortions from component algorithms operating on specified image features. Seven such algorithms are applied to successfully analyse the seven image distortions in relation to the original image. A survey of over 12,000 subjective quality scores has been carried out in order to determine the influence of these features on the perceived image quality. The results of quantitative assessments are mapped on the surveyed scores to obtain an overall quality score of the image. The proposed models have been validated in order to prove that the above technique can be applied to automatic image quality assessment.

Automated Detection of Firearms and Knives in a CCTV Image

Closed circuit television systems (CCTV) are becoming more and more popular and are being deployed in many offices, housing estates and in most public spaces. Monitoring systems have been implemented in many European and American cities. This makes for an enormous load for the CCTV operators, as the number of camera views a single operator can monitor is limited by human factors. In this paper, we focus on the task of automated detection and recognition of dangerous situations for CCTV systems. We propose algorithms that are able to alert the human operator when a firearm or knife is visible in the image. We have focused on limiting the number of false alarms in order to allow for a real-life application of the system. The specificity and sensitivity of the knife detection are significantly better than others published recently. We have also managed to propose a version of a firearm detection algorithm that offers a near-zero rate of false alarms. We have shown that it is possible to create a system that is capable of an early warning in a dangerous situation, which may lead to faster and more effective response times and a reduction in the number of potential victims.

INACT--INDECT Advanced Image Cataloguing Tool

Child pornography possession and distribution are crimes which are prosecuted in most countries around the world. In some cases the law is so strict that even police forces are not allowed to gather and catalogue evidence for future reference. This paper presents an innovative solution to this problem. The authors present tools for cataloguing high- and low-level metadata of the evidence material. Furthermore, a tool for fast and accurate search for such evidence in suspects’ file systems is proposed.

Prototype Software for Video Summary of Bronchoscopy Procedures with the Use of Mechanisms Designed to Identify, Index and Search

Individual bronchoscopy test event takes about 20 minutes. Most of this time is the video recording process, placing and removing bronchoscope endings in the patient’s airways. A sizable part of the record is unreadable because of obstruction by secretion of physiological image. The analysis of such recordings for teaching purposes or diagnostic tests is time-consuming — the doctor or student is forced to view a large number recordings of little value to find the fragments of interest — those showing lesions. In research, we develop a prototype system to create shortcuts (called summaries or abstracts) of bronchoscopy research recordings. Such a system, based on the model described in the preceding paper paragraphs uses image analysis methods to delete the recording fragments of the bronchoscopy test which have no diagnostic value for teaching and create a few minute-long, valuable video sequences.

Video Summarization Framework for Newscasts and Reports – Work in Progress

This paper presents a framework for summarization for newscasts and reports, that is a part of an ongoing research towards multilingual opinion analysis system conducted under the CHIST-ERA project “Access Multilingual Information opinionS” (AMIS). We present the results of qualitative analysis of newscast and reports published in the Internet by leading English, French and Arabic TV channels. We show the method used for creation of a database that contains 300 h of such content on controversial topics. Finally, we show the design and operation of our summarization framework. The framework is designed in such a way, that it allows for easy experimentation with different approaches to video summarization. The description is followed by a presentation of high- and low-level metadata extraction algorithms that include detection of the anchorperson, recognition of day and night shots and extraction of low-level video quality indicators.

Practical Application of Near Duplicate Detection for Image Database

Traditional program guides, TV applications, and online portals alone are no longer sufficient to expose all content, let alone offer the content that consumers want, at the times they are most likely to want it. DEEP, (Data Enrichment and Engagement Platform) by Orca Interactive, a comprehensive new content discovery solution, combines search, recommendation, and second-screen devices into a single immersive experience which invites exploration. The automated generation (using internet sources) of digital magazines for movies, TV shows, cast members and topics is a key value of DEEP. Unfortunately, using the internet as a source for pictures can result in the acquisition of so-called “Near Duplicate” (ND) images – similar images from a specific display context - for example, multiple red carpet images showing an actor from very similar angles or degrees of zoom on him/her. Therefore, in this paper we present a practical application of ND detection for image databases. The algorithm used is based on the MPEG-7 Colour Structure descriptor. For images that were provided by the developers of the DEEP software the algorithm performs very well, and the results are almost identical to those obtained during the training phase.

Algorithms for Automatic Recognition of Non-informative Frames in Video Recordings of Bronchoscopic Procedures

The video recordings of endoscopic procedures performed within respiratory tract include both frames of adequate and inadequate quality for the assessment by the endoscopist. The frames of inadequate quality were called by some authors blurred or “non-informative”. The fraction of blurred frames within video recording of bronchofiberoscopy may be considerable and it varies from case to case. Therefore, the function of automatic exclusion of “non-informative” frames would bring substantial benefits in terms of the volume of the archived video recordings of bronchofiberoscopic procedures. Furthermore, it could also save the time of users accessing medical video library established with archived resources. In this paper, the authors have proposed, tested and compared several algorithms for detecting blurred video frames. The main focus of this paper is to compare various, independent algorithms for automatic recognition of “non-informative” frames in video recordings of bronchoscopic procedures. The results demonstrated in the paper show that the proposed methods achieve F-measure, sensitivity, specificity and accuracy of at least 87% or higher.

Ground-Truth-Less Comparison of Selected Content-Based Image Retrieval Measures

The paper addresses the issue of finding the best content-based image retrieval measures. First, the authors describe several image descriptors that have been used for image feature extraction. Then, the detailed description of a query by example psycho-physical experiment is presented. The paper concludes with the analysis of the results obtained.

OASIS Archive --- Open Archiving System with Internet Sharing

OASIS Archive project aimed at developing a system for the universal presentation of Media Art works independent of location. The goal was to establish a user-friendly search system in order to ensure the preservation and availability (sustainability) of cultural heritage in the field of Media Art. The metadata system interlinking databases of all participating institutions can be accessed by individual users (both researchers and general public) through an on-line interface, by multimedia archive servers engaged in exchange within a distributed system and by various play out media. Access permission is scalable depending on whether the access takes place within the system or from the outside.

Compression and distribution of panoramic videos utilising MPEG-7-based image registration

This paper describes an innovative compression method of panoramic images based on MPEG-7 descriptors. The proposed solution employs a detection of a series of individual video frame overlaps in order to produce concatenated panoramic images. The presented method is easy to implement even in simple devices such as low power consuming chipsets installed in remote cameras having limited power supplies. Under subjective tests it has been proved that the concatenation method allows for achieving lower transmission rates while sustaining picture quality.