Workshop on Image Analysis for Multimedia Interactive Services 

About: Workshop on Image Analysis for Multimedia Interactive Services is an academic conference. The conference publishes majorly in the area(s): Feature extraction & Image retrieval. Over the lifetime, 527 publications have been published by the conference receiving 4713 citations.

FCTH: Fuzzy Color and Texture Histogram - A Low Level Feature for Accurate Image Retrieval

Abstract: This paper deals with the extraction of a new low level feature that combines, in one histogram, color and texture information. This feature is named FCTH - Fuzzy Color and Texture Histogram - and results from the combination of 3 fuzzy systems. FCTH size is limited to 72 bytes per image, rendering this descriptor suitable for use in large image databases. The proposed feature is appropriate for accurately retrieving images even in distortion cases such as deformations, noise and smoothing. It is tested on a large number of images selected from proprietary image databases or randomly retrieved from popular search engines. To evaluate the performance of the proposed feature, the averaged normalized modified retrieval rank was used. An online demo that implements the proposed feature in an image retrieval system is available at: http://orpheus.ee.duth.gr/image_retrieval.

The MUG facial expression database

Abstract: This paper presents a new extended collection of posed and induced facial expression image sequences. All sequences were captured in a controlled laboratory environment with high resolution and no occlusions. The collection consists of two parts: The first part depicts eighty six subjects performing the six basic expressions according to the “emotion prototypes” as defined in the Investigator's Guide in the FACS manual. The second part contains the same subjects recorded while they were watching an emotion inducing video. Most of the database recordings are available to the scientific community. Beyond the emotion related annotation the database contains also manual and automatic annotation of 80 facial landmark points for a significant number of frames. The database contains sufficient material for the development and the statistical evaluation of facial expression recognition systems using posed and induced expressions.

Automatically Segmenting LifeLog Data into Events

Abstract: A personal lifelog of visual information can be very helpful as a human memory aid. The SenseCam, a passively capturing wearable camera, captures an average of 1785 images per day, which equates to over 600000 images per year. So as not to overwhelm users it is necessary to deconstruct this substantial collection of images into digestable chunks of information, i.e. into distinct events or activities. This paper improves on previous work on automatic segmentation of SenseCam images into events by up to 29.2%, primarily through the introduction of intelligent threshold selection techniques, but also through improvements in the selection of normalisation, fusion, and vector distance techniques. Here we use the most extensive dataset ever used in this domain, 271163 images collected by 5 users over a time period of one month with manually groundtruthed events.

Multi-video summarization based on Video-MMR

Abstract: This paper presents a novel and effective approach for multi-video summarization: Video Maximal Marginal Relevance (Video-MMR), which extends a classical algorithm of text summarization, Maximal Marginal Relevance. Video-MMR rewards relevant keyframes and penalizes redundant keyframes, as MMR does with text fragments. Two variants of Video-MMR are suggested, and we propose a criterion to select the best combination of parameters for Video-MMR. Then, we compare two summarization strategies: Global Summarization, which summarizes all the individual videos at the same time, and Individual Summarization, which summarizes each individual video independently and concatenates the results. Finally, Video-MMR algorithm is compared with popular K-means algorithm, supported by user-made summary.

GPU acceleration for support vector machines

Abstract: This paper presents a GPU-assisted version of the LIBSVM library for Support Vector Machines. SVMs are particularly popular for classification procedures among the research community, but for large training data the processing time becomes unrealistic. The modification that is proposed is porting the computation of the kernel matrix elements to the GPU, to significantly decrease the processing time for SVM training without altering the classification results compared to the original LIBSVM. The experimental evaluation of the proposed approach highlights how the GPU-accelerated version of LIBSVM enables the more efficient handling of large problems, such as large-scale concept detection in video.