1,720,983 research outputs found
Performing content-based retrieval of humans using gait biometrics
No full textIn order to analyse surveillance video, we need to efficiently explore large datasets containing videos of walking humans. Effective analysis of such data relies on retrieval of video data which has been enriched using semantic annotations. A manual annotation process is time-consuming and prone to error due to subject bias however, at surveillance-image resolution, the human walk (their gait) can be analysed automatically. We explore the content-based retrieval of videos containing walking subjects, using semantic queries. We evaluate current research in gait biometrics, unique in its effectiveness at recognising people at a distance. We introduce a set of semantic traits discernible by humans at a distance, outlining their psychological validity. Working under the premise that similarity of the chosen gait signature implies similarity of certain semantic traits we perform a set of semantic retrieval experiments using popular Latent Semantic Analysis techniques. We perform experiments on a dataset of 2000 videos of people walking in laboratory conditions and achieve promising retrieval results for features such as Sex (mAP= 14% above random), Age (mAP=10% above random) and Ethnicity (mAP=9% above random
Semantic biometrics
No full textGait and face biometrics have a unique advantage in that they can be used when images are acquired at a distance and signals are at too low a resolution to be perceived by other biometrics. Given such situations, some traits can be difficult to extract automatically but can still be perceived semantically using human vision. It is contended that such semantic annotations are usable as soft biometric signatures, useful for identification tasks. Feature subset selection techniques are employed to compare the distinguishing ability of individual semantically described physical traits. Their identification ability is also explored, both in isolation and in the improvement of the recognition rates of some associated gait biometric signatures using fusion techniques.This is the first approach to explore semantic descriptions of physiological human traits as used alone or to complement primary biometric techniques to facilitate recognition and analysis of surveillance video. Potential traits to be described are explored and justified against their psychological and practical merits. A novel dataset of semantic annotations is gathered describing subjects in two existing biometric datasets. Two applications of these semantic features and their associated biometric signatures are explored using the data gathered. We also draw on our experiments as a whole to highlight those traits thought to be most useful in assisting biometric recognition overall.Effective analysis of surveillance data by humans relies on semantic retrieval of the data which has been enriched by semantic annotations. A manual annotation process is time-consuming and prone to error due to various factors. We explore the semantic content-based retrieval of surveillance captured subjects. Working under the premise that similarity of the chosen biometric signature implies similarity of certain semantic traits, a set of semantic retrieval experiments are performed using well established Latent Semantic Analysis techniques.<br/
OpenIMAJ and ImageTerrier: Java Libraries and Tools for Scalable Multimedia Analysis and Indexing of Images
No full textOpenIMAJ and ImageTerrier are recently released open-source libraries and tools for experimentation and development of multimedia applications using Java-compatible programming languages. OpenIMAJ (the Open toolkit for Intelligent Multimedia Analysis in Java) is a collection of libraries for multimedia analysis. The image libraries contain methods for processing images and extracting state- of-the-art features, including SIFT. The video and audio libraries support both cross-platform capture and processing. The clustering and nearest-neighbour libraries contain efficient, multi-threaded implementations of clustering algorithms. The clustering library makes it possible to easily create BoVW representations for images and videos. OpenI-MAJ also incorporates a number of tools to enable extremely- large-scale multimedia analysis using distributed computing with Apache Hadoop. ImageTerrier is a scalable, high-performance search engine platform for content-based image retrieval applications using features extracted with the OpenIMAJ library and tools. The ImageTerrier platform provides a comprehensive test-bed for experimenting with image retrieval techniques. The platform incorporates a state-of-the-art implementation of the single-pass indexing technique for constructing inverted indexes and is capable of producing highly compressed index data structures
Performing content-based retrieval of humans using gait biometrics
Full text linkIn order to analyse surveillance video, we need to efficiently explore large datasets containing videos of walking humans. At surveillance-image resolution, the human walk (their gait) can be determined automatically, and more readily than other features such as the face. Effective analysis of such data relies on retrieval of video data which has been enriched using semantic annotations. A manual annotation process is time-consuming and prone to error due to subject bias. We explore the content-based retrieval of videos containing walking subjects, using semantic queries. We evaluate current biometric research using gait, unique in its effectiveness at recognising people at a distance. We introduce a set of semantic traits discernible by humans at a distance, outlining their psychological validity. Working under the premise that similarity of the chosen gait signature implies similarity of certain semantic traits we perform a set of semantic retrieval experiments using popular latent semantic analysis techniques from the information retrieval community
Efficient clustering and quantisation of SIFT features: Exploiting characteristics of the SIFT descriptor and interest region detectors under image inversion
No full textThe SIFT keypoint descriptor is a powerful approach to encoding local image description using edge orientation histograms. Through codebook construction via k-means clustering and quantisation of SIFT features we can achieve image retrieval treating images as bags-of-words. Intensity inversion of images results in distinct SIFT features for a single local image patch across the two images. Intensity inversions notwithstanding these two patches are structurally identical. Through careful reordering of the SIFT feature vectors, we can construct the SIFT feature that would have been generated from a non-inverted image patch starting with those extracted from an inverted image patch. Furthermore, through examination of the local feature detection stage, we can estimate whether a given SIFT feature belongs in the space of inverted features, or non-inverted features. Therefore we can consistently separate the space of SIFT features into two distinct subspaces. With this knowledge, we can demonstrate reduced time complexity of codebook construction via clustering by up to a factor of four and also reduce the memory consumption of the clustering algorithms while producing equivalent retrieval results
On Semantic Soft-Biometric Labels
Full text linkA new approach to soft biometrics aims to use human labelling as part of the process. This is consistent with analysis of surveillance video where people might be imaged at too low resolution or quality for conventional biometrics to be deployed. In this manner, people use anatomical descriptions of subjects to achieve recognition, rather than the usual measurements of personal characteristics used in biometrics. As such the labels need careful consideration in their construction, and should demonstrate correlation consistent with known human physiology. We describe our original process for generating these labels and analyse relationships between them. This gives insight into the perspicacity of using a human labelling system for biometric purposes
On Acquisition and Analysis of a Dataset Comprising of Gait, Ear and Semantic data
No full textIn outdoor scenarios such as surveillance where there is very little control over the environments, complex computer vision algorithms are often required for analysis. However constrained environments, such as walkways in airports where the surroundings and the path taken by individuals can be controlled, provide an ideal application for such systems. Figure 1.1 depicts an idealised constrained environment. The path taken by the subject is restricted to a narrow path and once inside is in a volume where lighting and other conditions are controlled to facilitate biometric analysis. The ability to control the surroundings and the flow of people greatly simplifies the computer vision task, compared to typical unconstrained environments. Even though biometric datasets with greater than one hundred people are increasingly common, there is still very little known about the inter and intra-subject variation in many biometrics. This information is essential to estimate the recognition capability and limits of automatic recognition systems. In order to accurately estimate the inter- and the intra- class variance, substantially larger datasets are required [40]. Covariates such as facial expression, headwear, footwear type, surface type and carried items are attracting increasing attention; although considering the potentially large impact on an individuals biometrics, large trials need to be conducted to establish how much variance results. This chapter is the first description of the multibiometric data acquired using the University of Southampton's Multi-Biometric Tunnel [26, 37]; a biometric portal using automatic gait, face and ear recognition for identification purposes. The tunnel provides a constrained environment and is ideal for use in high throughput security scenarios and for the collection of large datasets. We describe the current state of data acquisition of face, gait, ear, and semantic data and present early results showing the quality and range of data that has been collected. The main novelties of this dataset in comparison with other multi-biometric datasets are: 1. gait data exists for multiple views and is synchronised, allowing 3D reconstruction and analysis; 2. the face data is a sequence of images allowing for face recognition in video; 3. the ear data is acquired in a relatively unconstrained environment, as a subject walks past; and 4. the semantic data is considerably more extensive than has been available previously. We shall aim to show the advantages of this new data in biometric analysis, though the scope for such analysis is considerably greater than time and space allows for here
- …
