In this paper we present S-pot, a benchmark setting for evaluating the performance of automatic spotting of signs in continuous sign language videos. The benchmark includes 5539 video files of Finnish Sign Language, ground truth sign spotting results, a tool for assessing the spottings against the ground truth, and a repository for storing information on the results. In addition we will make ou...

This paper presents a symbol spotting approach for indexing by content a database of line-drawing images. As line-drawings are digital-born documents designed by vectorial softwares, instead of using a pixel-based approach, we present a spotting method based on vector primitives. Graphical symbols are represented by a set of vectorial primitives which are described by an offthe-shelf shape desc...

Support Vector Machines (SVM) is one such machine learning technique that learns the decision surface through a process of discrimination and has a good generalization capacity [6]. SVMs have been proven to be successful classifiers on several classical pattern recogntion problems [9, 11]. In this paper, one of the first applications of Support Vector Machines (SVM) technique for the problem of...

This paper presents a method for spotting key-text in videos, based on a cascade of classifiers trained with Adaboost. The video is first reduced to a set of key-frames. Each key-frame is then analyzed for its text content. Text spotting is performed by scanning the image with a variable-size window (to account for scale) within which simple features (mean/variance of grayscale values and x/y d...

This paper describes our complete results for improved lexical llers as well as two new kinds of llers, gives their results in unlimited speech recognition as well as for keyword spotting and compares them to the acoustic-phonetic ller in the case of keyword spotting. Tests have been conducted on di erent vocabularies derived from ATIS and the Wall Street Journal database. Results for keyword s...

A speaker-independent speech recognizer for continuously spelled names, implemented for a switchboard call-routing task, is analyzed for sources of error. Results indicate most errors are due to extraneous speech and end-point detection errors. Strategies are proposed for improving the robustness of recognition, including tolerance for speech with pauses, and a letter-spotting strategy to handl...

The generation of liquid droplets at the exits of multiple capillaries coupled to a single flow source is evaluated for application to multiplexed microfluidic contact spotting. Using a simple analytic model and an iterative numerical model, relationships between applied flow rates and the number of channels which produce full droplets at their exits are determined for arbitrarily large arrays....

We present the results of a small study involving the use of keyword-filler hidden Markov models (HMM) for spotting keywords in continuous speech. The performance dependence on the amount of keyword training data and the choice of model parameters is documented. Also, we demonstrate a strong correlation between individual keyword spotting performance and median duration of that keyword. This de...

We present a novel architecture for word-spotting which is trained from a small number of examples to classify an utterance as containing a target keyword or not. The word-spotting architecture relies on a novel feature set consisting of a set of ordered spectro-temporal patches which are extracted from the exemplar mel-spectra of target keywords. A local pooling operation across frequency and ...

This paper proposes a novel method of generating statistical Korean Hangul character models in real time. From a set of grapheme average images we compose any character images, and then convert them to P2DHMMs. The nonlinear, 2D composition of letter models in Hangul is not straightforward and has not been tried for machine-print character recognition. It is obvious that the proposed method of ...