Minh-Son Dao

Edge Potential Functions (EPF) and Genetic Algorithms (GA) for Edge-Based Matching of Visual Objects

Edges are known to be a semantically rich representation of the contents of a digital image. Nevertheless, their use in practical applications is sometimes limited by computation and complexity constraints. In this paper, a new approach is presented that addresses the problem of matching visual objects in digital images by combining the concept of edge potential functions (EPF) with a powerful matching tool based on genetic algorithms (GAs). EPFs can be easily calculated starting from an edge map and provide a kind of attractive pattern for a matching contour, which is conveniently exploited by GAs. Several tests were performed in the framework of different image matching applications. The results achieved clearly outline the potential of the proposed method as compared to state of the art methodologies

Video retrieval using video object-trajectory and edge potential function

A novel video retrieval tool, based on video objects (VOs) and objects trajectories is presented. The algorithm extends the concept of edge potential functions (EPF), already used in shape-based image retrieval, tailored to work on shapes extracted from video object planes (VOP). First, the initial model is detected by using local motion and global motion information. After the moving object is initialized, object tracking is performed to construct its trajectory features. Then, the VOP is extracted and the key-VOP, which is used as visual summarization, is detected. Finally, the special measure, based on EPF, is constructed and used as the main measure to perform video retrieval. Experimental results demonstrate that the proposed algorithm is efficient and fast in indexing a video sequence according to the presence of specific video objects and their trajectories.

Edge potential functions and genetic algorithms for shape-based image retrieval

In this paper, a new approach to the image retrieval problem is presented, that uses edge potential functions (EPF) and genetic algorithms (GA). The method allows a user to draw a rough sketch of the shape and to find or rank the images in a database that contain a similar shape at any position, rotation and scaling factor. It is explained how GAs allow to exploit the capability of EPFs to attract a sketch contour as a result, the algorithm provides the set of geometrical transformations corresponding to the best match, and a confidence factor about the presence of a matching object. The method has been widely tested achieving very satisfactory results.

Jointly exploiting visual and non-visual information for event-related social media retrieval

In this contribution, we propose a watershed-based method with support from external data sources and visual information to detect social events in web multimedia. The idea is based on two main observations: (1) people cannot be involved in more than one event at the same time, and (2) people tend to introduce similar annotations for all images associated to the same event. Based on these observations, the metadata is turned to an image so that each row contains all records belonging to one user; and these records are sorted by time. Thus, the social event detection is turned to watershed-based image segmentation, where Markers are generated by using (keyword, location, visual) features with support of external data sources, and the Flood progress is carried on by taking into account (tags set, time, visual) features. We test our algorithm on the MediaEval 2012 dataset both using only external data but also introducing visual information.

Robust event discovery from photo collections using Signature Image Bases (SIBs)

Analyzing personal photo albums for understanding the related events is an emerging trend. A reliable event recognition tool could suggest appropriate annotation of pictures, provide the context for single image classification and tagging, achieve automatic selection and summarization, ease organization and sharing of media among users. In this paper, a novel method for fast and reliable event-type classification of personal photo albums is presented. Differently from previous approaches, the proposed method does not process photos individually but as a whole, exploiting three main features, namely Saliency, Gist, and Time, to extract an event signature, which is characteristic for a specific event type. A highly challenging database containing more than 40.000 photos belonging to 19 diverse event-types was crawled from photo-sharing websites for the purpose of modeling and performance evaluation. Experimental results showed that the proposed approach meets superior classification accuracy with limited computational complexity.

Discovering inherent event taxonomies from social media collections

Events are becoming very popular as a tool to organize and access large media collections. An unsolved problem however, is how to define event models. Most part of the approaches so far proposed in the literature are based on a-priori knowledge, and translate into hierarchical data structures or taxonomies a more or less intuitive definition of what a given type of event is. The association of media and event models is then a consequent process, in which one tries to learn the distinctive characteristics of media associated to a certain event or sub-event. In this paper, we attempt to reverse this paradigm, inferring from a set of media collections belonging to the same event class the underlying taxonomy in an unconstrained way. As a result we obtain a hierarchy of natural clusters, largely shared by the different collections, which capture the essence of the event itself. Although it is not possible to compare the proposed approach with state-of-the-art method based on a-priori event structures, experimental results demonstrate that this approach may become an effective support for discovering and defining event models and managing event-related data collections.

A new spatio-temporal method for event detection and personalized retrieval of sports video

In this paper, a new spatio-temporal method for adaptively detecting events based on Allen temporal algebra and external information support is presented. The temporal information is captured by presenting events as the temporal sequences using a lexicon of non-ambiguous temporal patterns. These sequences are then exploited to mine undiscovered sequences with external text information supports by using class associate rules mining technique. By modeling each pattern with linguistic part and perceptual part those work independently and connect together via transformer, it is easy to deploy this method to any new domain (e.g baseball, basketball, tennis, etc.) with a few changes in perceptual part and transformer. Thus the proposed method not only can work well in unwell structured environments but also can be able to adapt itself to new domains without the need (or with a few modification) for external re-programming, re-configuring and re-adjusting. Results of automatic event detection progress are tailored to personalized retrieval via click-and-see style using either conceptual or conceptual-visual query scheme. Experimental results carried on more than 30 hours of soccer video corpus captured at different broadcasters and conditions as well as compared with well-known related methods, demonstrated the efficiency, effectiveness, and robustness of the proposed method in both offline and online processes.

Signature-image-based event analysis for personal photo albums

Quick reorganizing and draft annotating personal photo albums under event scheme is an emerging trend. In this research, a method has been developed to meet such requirements using the idea of gist and mosaic art so that viewers could understand the meaning of a whole scene without paying much attention in individual details. First, given a photo album, all chronologically ordered images are normalized to a smaller size, and then mosaicked side-by-side to create a signature image representing for that album. Next, by integrating the optimized linear programming with the color descriptor of the signature image, not only the event-type of the album but also all sub-event-types of the sub-sequence photos are decided. More than 19,000 images of five varied event-types have been used to evaluate the proposed method. Experimental results show that the proposed method could detect events towards annotation and re-organization of personal photo albums with high accuracy at a rapid speed.

Mining temporal information and web-casting text for automatic sports event detection

In this paper, the generic framework for automatically detecting event based on Allen temporal algebra and external text information support is presented. The motivation of the proposed method is (1) to relax the need of domain knowledge that requires significant human interference; and (2) to take into account the temporal information that has been paid less attention though it is critical to convey event meaning. In order to solve two these problems, in the proposed method, the temporal information is captured by presenting events as the temporal sequences using a lexicon of Allen-based non-ambiguous temporal patterns. These sequences are then used to mine temporal patterns with web-casting text supports by using technique of mining class association rules. Then, the results of previous steps are tailored to build the event detector. Thorough experimental results and comparisons that are carried on more than 30 hours of soccer video corpus captured at different broadcasters and conditions demonstrates that the proposed method meets two aforementioned motivations with high efficiency, effectiveness, and robustness.

Efficient shape matching using weighted edge potential functions

An efficient approach to shape matching in digital images is presented. The method, called Weighted Edge Potential Function, is a significant improvement of the EPF similarity measure, which models the image edges as charged elements in order to generate a field of attraction over similarly shaped objects. Experimental results and comparisons demonstrate that WEPF enhances the properties of EPF and outperforms traditional similarity metrics in shape matching applications, in particular in the presence of noise and clutter.