Video Signature Research Articles

Content based image hashing using companding and gray code

AbstractEasily processing, storing, and propagating of digital images demand efficient and automatic techniques to identify and verify image contents. Image hashing is such a promising technique to represent and authenticate images without changing the content of images. The new robust image feature we use is the Morlet wavelet coefficients at feature points with the k‐largest local total variations in images. The Morlet wavelet coefficients are pseudo randomly permutated such that image hashes have a small collision rate and are difficult to analyze by attackers. The Morlet wavelet coefficients are further quantized using companding technique and binarily coded using Gray code to form the final hash. Experimental results show the effectiveness and robustness of our method. The proposed image hash could have applications in image authentication and video signature. Copyright © 2010 John Wiley & Sons, Ltd.

T1220 Endomicroscopic Video Retrieval Approach to Support Diagnostic Differentiation Between Neoplastic and Non-Neoplastic Colonic Polyps

Background: Probe-based confocal laser endomicroscopy (pCLE) enables dynamic imaging of the gastrointestinal epithelium In Vivo during ongoing endoscopy and, as of today, relies on the endoscopist for image understanding. The subjective nature of pCLE video semantics suggests the need for a standardized and more automated method for image sequence interpretation. Aims: To support the diagnosis of a newly acquired pCLE video, we aim at retrieving from a training database videos that have a similar appearance to the video of interest and that have been previously diagnosed by expert physicians with confirmed histology. As a model system, we used distinction of adenomatous and hyperplastic colorectal polyps. Methods: 68 patients underwent colonoscopy with pCLE for fluorescein-aided imaging of suspicious colonic polyps before their removal. The resulting database is composed of 121 videos (36 non-neoplastic, 85 neoplastic) and 499 edited video sub-sequences (231 non-neoplastic, 268 neoplastic) annotated by clinical experts with a pathological diagnosis. To quantify the relevance of video retrieval, we performed an unbiased classification with leave-one-patient-out cross-validation, based on the voting of the k most similar videos. The Bag-of-Visual-Words method from computer vision extracts local continuous image features and clusters them into a finite number of visual words to build an efficient image signature. In order to retrieve videos and not only isolated images, we revisited this method and analyzed the impact of including spatial overlap between time-related images. We first used the results of a video-mosaicing technique to weight the contribution of each local image region to its visual word. Then, we computed the video signatures with a histogram summation technique, which reduces both retrieval runtime and training memory. Results: Video classification results show that our method achieves, when using the votes of the k=9 most similar videos, a sensitivity of 97.7% and a specificity of 86.1% for a resulting accuracy of 94.2%. When compared to using the still images independently, using video data improves the results in a statistically significant manner (McNemar's test: p-value=0.021 when using the votes of the k=3 most similar videos). Moreover, fewer similar videos are necessary to classify the query at a given accuracy, which is clinically relevant for the physician. Conclusion: Our method using the results of video-mosaicing for content-based video retrieval appears to be highly accurate for pCLE videos. It may provide the endoscopist with diagnostic decision support and avoid unnecessary polypectomy of non-neoplastic lesions.

방송콘텐츠 저작권 식별관리를 위한 UCI 표준식별체계와 내용기반 식별정보의 상호연계 연구

본 논문에서는 방송콘텐츠 저작권 식별관리를 위한 방송콘텐츠의 Video Signature와 국가표준콘텐츠식별체계인 UCI(Universal Content Identifier)의 연계 방안을 제시한다. Video Signature는 UCI와 같은 식별자의 인위적인 부여 과정이 없더라도 동영상 콘텐츠 자체에서 직접 특징정보를 추출할 수 있기 때문에, 이미 배포 유통된 콘텐츠에 대해서도 식별 확인이 가능하다. 따라서, 본 연구에서는 최근 국가표준콘텐츠식별체계로 통합, 단일화된 UCI 식별체계와 내용기반 식별정보인 Video Signature의 지속적인 연계를 위하여, 바이너리로 표현된 Video Signature를 포함하는 UCI 응용메타데이터를 정의한다. 그리고 UCI 표준식별체계 기반 Video Signature 전송 및 관리 메카니즘에 기반한 방송콘텐츠의 저작권 식별관리 및 부가서비스 시나리오를 제시한다. In this paper, we propose a scheme to associate content-based video signature with Universal Content Identifier (UCI) system of broadcast content for copyright identification and management. Note that content-based video signature can identify a previously distributed content since it is directly extracted from content itself without allocation process of identifier such as UCI. Thus, we design the schema of UCI application metadata, which provides a video signature in order to consistently maintain a systemic link between UCI and the video signature. Also, we present the scenarios of copyright identification, management and additional service, which are based on transmission and management mechanism of video signature with UCI identification system.

Face-Based Digital Signatures for Video Retrieval

The characterization of a video segment by a digital signature is a fundamental task in video processing. It is necessary for video indexing and retrieval, copyright protection, and other tasks. Semantic video signatures are those that are based on high-level content information rather than on low-level features of the video stream. The major advantage of such signatures is that they are highly invariant to nearly all types of distortion. A major semantic feature of a video is the appearance of specific persons in specific video frames. Because of the great amount of research that has been performed on the subject of face detection and recognition, the extraction of such information is generally tractable, or will be in the near future. We have developed a method that uses the pre-extracted output of face detection and recognition to perform fast semantic query-by-example retrieval of video segments. We also give the results of the experimental evaluation of our method on a database of real video. One advantage of our approach is that the evaluation of similarity is convolution-based, and is thus resistant to perturbations in the signature and independent of the exact boundaries of the query segment.

Detection of video sequences using compact signatures

Digital representations are widely used for audiovisual content, enabling the creation of large online repositories of video, allowing access such as video on demand. However, the ease of copying and distribution of digital video makes piracy a growing concern for content owners. We investigate methods for identifying coderivative video content---that is, video clips that are derived from the same original source. By using dynamic programming to identify regions of similarity in video signatures, it is possible to efficiently and accurately identify coderivatives, even when these regions constitute only a small section of the clip being searched. We propose four new methods for producing compact video signatures, based on the way in which the video changes over time. The intuition is that such properties are likely to be preserved even when the video is badly degraded. We demonstrate that these signatures are insensitive to dramatic changes in video bitrate and resolution, two parameters that are often altered when reencoding. In the presence of mild degradations, our methods can accurately identify copies of clips that are as short as 5 s within a dataset 140 min long. These methods are much faster than previously proposed techniques; using a more compact signature, this query can be completed in a few milliseconds.

Fast similarity search and clustering of video sequences on the world-wide-web

We define similar video content as video sequences with almost identical content but possibly compressed at different qualities, reformatted to different sizes and frame-rates, undergone minor editing in either spatial or temporal domain, or summarized into keyframe sequences. Building a search engine to identify such similar content in the World-Wide Web requires: 1) robust video similarity measurements; 2) fast similarity search techniques on large databases; and 3) intuitive organization of search results. In a previous paper, we proposed a randomized technique called the video signature (ViSig) method for video similarity measurement. In this paper, we focus on the remaining two issues by proposing a feature extraction scheme for fast similarity search, and a clustering algorithm for identification of similar clusters. Similar to many other content-based methods, the ViSig method uses high-dimensional feature vectors to represent video. To warrant a fast response time for similarity searches on high dimensional vectors, we propose a novel nonlinear feature extraction scheme on arbitrary metric spaces that combines the triangle inequality with the classical Principal Component Analysis (PCA). We show experimentally that the proposed technique outperforms PCA, Fastmap, Triangle-Inequality Pruning, and Haar wavelet on signature data. To further improve retrieval performance, and provide better organization of similarity search results, we introduce a new graph-theoretical clustering algorithm on large databases of signatures. This algorithm treats all signatures as an abstract threshold graph, where the distance threshold is determined based on local data statistics. Similar clusters are then identified as highly connected regions in the graph. By measuring the retrieval performance against a ground-truth set, we show that our proposed algorithm outperforms simple thresholding, single-link and complete-link hierarchical clustering techniques.

Efficient video similarity measurement with video signature

The proliferation of video content on the Web makes similarity detection an indispensable tool in Web data management, searching, and navigation. We propose a number of algorithms to efficiently measure video similarity. We define video as a set of frames, which are represented as high dimensional vectors in a feature space. Our goal is to measure ideal video similarity (IVS), defined as the percentage of clusters of similar frames shared between two video sequences. Since IVS is too complex to be deployed in large database applications, we approximate it with Voronoi video similarity (VVS), defined as the volume of the intersection between Voronoi cells of similar clusters. We propose a class of randomized algorithms to estimate VVS by first summarizing each video with a small set of its sampled frames, called the video signature (ViSig), and then calculating the distances between corresponding frames from the two ViSigs. By generating samples with a probability distribution that describes the video statistics, and ranking them based upon their likelihood of making an error in the estimation, we show analytically that ViSig can provide an unbiased estimate of IVS. Experimental results on a large dataset of Web video and a set of MPEG-7 test sequences with artificially generated similar versions are provided to demonstrate the retrieval performance of our proposed techniques.

Computer Vision Detection System for Network Model Validation

A computer vision-based traffic detection system has been developed and tested that is capable of uniquely identifying vehicles in a traffic network from video images and later reidentifying them at other detection sites in the network. This capability may serve as the basis for deterministic validation of microscopic network flow models, origin-destination tables, and travel-time tables. The system is referred to as the video-based vehicle signature analysis and tracking system. With video cameras used as primary sensors, detection modules generate a numeric video signature vector (VSV) for each vehicle and transmit them to a central Internet-connected correlation computer via a public low-power wireless network. The correlation computer attempts to match vehicles, as represented by their VSVs, generated at successive detection sites to enable a sampled real-time microscopic flow representation of a freeway network. Test results indicate 93.6 percent accuracy in correctly reidentifying vehicles at successive sites. The tendency of the system to incorrectly match different vehicles at successive sites was measured at 0.0116 percent. Potential advantages are low cost in widespread deployment, simplicity and reliability of detection, minimal bandwidth and storage requirements for transmission of the VSV, and reasonable identification ability without violation of privacy rights. The primary disadvantages are the requirement to place video cameras above each traffic lane and video imaging limitations related to reliance on ambient illumination.