Barbara L. Loeding

Handling Movement Epenthesis and Hand Segmentation Ambiguities in Continuous Sign Language Recognition Using Nested Dynamic Programming

We consider two crucial problems in continuous sign language recognition from unaided video sequences. At the sentence level, we consider the movement epenthesis (me) problem and at the feature level, we consider the problem of hand segmentation and grouping. We construct a framework that can handle both of these problems based on an enhanced, nested version of the dynamic programming approach. To address movement epenthesis, a dynamic programming (DP) process employs a virtual me option that does not need explicit models. We call this the enhanced level building (eLB) algorithm. This formulation also allows the incorporation of grammar models. Nested within this eLB is another DP that handles the problem of selecting among multiple hand candidates. We demonstrate our ideas on four American Sign Language data sets with simple background, with the signer wearing short sleeves, with complex background, and across signers. We compared the performance with conditional random fields (CRF) and latent dynamic-CRF-based approaches. The experiments show more than 40 percent improvement over CRF or LDCRF approaches in terms of the frame labeling rate. We show the flexibility of our approach when handling a changing context. We also find a 70 percent improvement in sign recognition rate over the unenhanced DP matching algorithm that does not accommodate the me effect.

Enhanced Level Building Algorithm for the Movement Epenthesis Problem in Sign Language Recognition

One of the hard problems in automated sign language recognition is the movement epenthesis (me) problem. Movement epenthesis is the gesture movement that bridges two consecutive signs. This effect can be over a long duration and involve variations in hand shape, position, and movement, making it hard to explicitly model these intervening segments. This creates a problem when trying to match individual signs to full sign sentences since for many chunks of the sentence, corresponding to these mes, we do not have models. We present an approach based on version of a dynamic programming framework, called Level Building, to simultaneously segment and match signs to continuous sign language sentences in the presence of movement epenthesis (me). We enhance the classical Level Building framework so that it can accommodate me labels for which we do not have explicit models. This enhanced Level Building algorithm is then coupled with a trigram grammar model to optimally segment and label sign language sentences. We demonstrate the efficiency of the algorithm using a single view video dataset of continuous sign language sentences. We obtain 83% word level recognition rate with the enhanced Level Building approach, as opposed to a 20% recognition rate using a classical Level Building framework on the same dataset. The proposed approach is novel since it does not need explicit models for movement epenthesis.

Progress in Automated Computer Recognition of Sign Language

This paper reviews the extensive state of the art in automated recognition of continuous signs, from different languages, based on the data sets used, features computed, technique used, and recognition rates achieved. We find that, in the past, most work has been done in finger-spelled words and isolated sign recognition, however recently, there has been significant progress in the recognition of signs embedded in short continuous sentences. We also find that researchers are starting to address the important problem of extracting and integrating non-manual information that is present in face and head movement. We present results from our own experiments integrating non-manual features.

Distribution-Based Dimensionality Reduction Applied to Articulated Motion Recognition

Some articulated motion representations rely on frame-wise abstractions of the statistical distribution of low-level features such as orientation, color, or relational distributions. As configuration among parts changes with articulated motion, the distribution changes, tracing a trajectory in the latent space of distributions, which we call the configuration space. These trajectories can then be used for recognition using standard techniques such as dynamic time warping. The core theory in this paper concerns embedding the frame-wise distributions, which can be looked upon as probability functions, into a low-dimensional space so that we can estimate various meaningful probabilistic distances such as the Chernoff, Bhattacharya, Matusita, Kullback-Leibler (KL) or symmetric-KL distances based on dot products between points in this space. Apart from computational advantages, this representation also affords speed-normalized matching of motion signatures. Speed normalized representations can be formed by interpolating the configuration trajectories along their arc lengths, without using any knowledge of the temporal scale variations between the sequences. We experiment with five different probabilistic distance measures and show the usefulness of the representation in three different contexts - sign recognition (with large number of possible classes), gesture recognition (with person variations), and classification of human-human interaction sequences (with segmentation problems). We find the importance of using the right distance measure for each situation. The low-dimensional embedding makes matching two to three times faster, while achieving recognition accuracies that are close to those obtained without using a low-dimensional embedding. We also empirically establish the robustness of the representation with respect to low-level parameters, embedding parameters, and temporal-scale parameters.

Automated extraction of signs from continuous sign language sentences using Iterated Conditional Modes

Recognition of signs in sentences requires a training set constructed out of signs found in continuous sentences. Currently, this is done manually, which is a tedious process. In this work, we consider a framework where the modeler just provides multiple video sequences of sign language sentences, constructed to contain the vocabulary of interest. We learn the models of the recurring signs, automatically. Specifically, we automatically extract the parts of the signs that are present in most occurrences of the sign in context. These parts of the signs that is stable with respect to adjacent signs, are referred to as signemes. Each video is first transformed into a multidimensional time series representation, capturing the motion and shape aspects of the sign. We then extract signemes from multiple sentences, concurrently, using Iterated Conditional Modes (ICM). We show results by learning multiple instances of 10 different signs from a set of 136 sign language sentences. We classify the extracted signemes as correct, partially correct or incorrect depending on whether both the start and end locations are correct, only one of them is correct or both are incorrect, respectively. Out of the 136 extracted video signemes, 98 were correct, 20 were partially correct and 18 were incorrect. To demonstrate the generality of the unsupervised modeling idea, we also show the ability to automatically extract common spoken words in audio. We consider the English glosses (spoken) corresponding to the sign language sentences and extract the audio counterparts of the signs. Of the 136 such instances, we recovered 127 correct, 8 partially correct, and 1 incorrect representation of the words.

Unsupervised Modeling of Signs Embedded in Continuous Sentences

The common practice in sign language recognition is to ?rst construct individual sign models, in terms of discrete state transitions, mostly represented using Hidden Markov Models, from manually isolated sign samples and then to use it to recognize signs in continuous sentences. In this paper we (i) propose a continuous state space model, where the states are based on purely image-based features, without the use of special gloves, and (ii) present an unsupervised approach to both extract and learn models for continuous basic units of signs, which we term as signemes, from continuous sentences. Given a set of sentences with a common sign, we can automatically learn the model for part of the sign, or signeme, that is least affected by coarticulation effects. While there are coarticulation effects in speech recognition, these effects are even stronger in sign language. The model itself is in term of traces in a space of Relational Distributions. Each point in this space represents a Relational Distribution, capturing the spatial relationships between low-level features, such as edge points. We perform speed normalization and then incrementally extract the common sign between sentences, or signemes, with a dynamic programming framework at the core to compute warped distance between two subsentences. We test our idea using the publicly available Boston SignStream Dataset by building signeme models of 18 signs. We test the quality of the models by considering how well we can localize the sign in a new sentence. We also present preliminary results for the ability to generalize across signers.

Finding recurrent patterns from continuous sign language sentences for automated extraction of signs

We present a probabilistic framework to automatically learn models of recurring signs from multiple sign language video sequences containing the vocabulary of interest. We extract the parts of the signs that are present in most occurrences of the sign in context and are robust to the variations produced by adjacent signs. Each sentence video is first transformed into a multidimensional time series representation, capturing the motion and shape aspects of the sign. Skin color blobs are extracted from frames of color video sequences, and a probabilistic relational distribution is formed for each frame using the contour and edge pixels from the skin blobs. Each sentence is represented as a trajectory in a low dimensional space called the space of relational distributions. Given these time series trajectories, we extract signemes from multiple sentences concurrently using iterated conditional modes (ICM). We show results by learning single signs from a collection of sentences with one common pervading sign, multiple signs from a collection of sentences with more than one common sign, and single signs from a mixed collection of sentences. The extracted signemes demonstrate that our approach is robust to some extent to the variations produced within a sign due to different contexts. We also show results whereby these learned sign models are used for spotting signs in test sequences.

Efficient generation of large amounts of training data for sign language recognition: a semi-automatic tool

We have developed a video hand segmentation tool which can help with generating hands ground truth from sign language image sequences. This tool may greatly facilitate research in the area of sign language recognition. In this tool, we offer a semi automatic scheme to assist with the localization of hand pixels, which is important for the purpose of recognition. A candidate hand generator is applied by using the mean shift image segmentation algorithm and a greedy seeds growing algorithm. After a number of hand candidates is generated, the user can reduce the candidates by simple mouse clicks. The tool also provides a hand tracking function for faster processing and a face detection function for groundtruthing non manual signals. In addition, we provided a two-passes groundtruthing scheme unlike other tools that only does one-pass. Our first pass processing is automatic and does not need user interaction. The experiment results demonstrate that based on the first passs result, one can groundtruth 10,000+ frames of sign language within 8 hours

A “Working Party” approach to planning in-service training in manual signs for an entire public school staff

A working party, composed of elementary school personnel (administrator, regular and special education staff, and parent) and university special education personnel (faculty and graduate students) worked cooperatively to develop and implement a manual sign in-service training package to improve the communication environment for severely disabled students attending that elementary school. A series of four, half-day workshops were planned during which school staff (teachers, aides, custodians, support staff, food handlers, and bus drivers) would learn manual signs for a functional core vocabulary selected from a list generated by the public school staff and students. These signs were carefully sequenced using existing research findings to facilitate successful acquisition. The process of planning and conducting the in-service training workshops has yielded valuable lessons in several areas. The use of a working party, selection of vocabulary, development of the workshop format, activities, materials, and de...

Segmentation-robust representations, matching, and modeling for sign language

Distinguishing true signs from transitional, extraneous movements as the signer moves from one sign to the next is a serious hurdle in the design of continuous sign language recognition systems. This problem is further compounded by the ambiguity of segmentation and occlusions. This short paper provides an overview of our experience with representations and matching methods, particularly those that can handle errors in low-level segmentation and uncertainties of sign boundaries in sentences. We have formulated a novel framework that can address both these problems using a nested, level-building based dynamic programming approach that works for matching two instances of signs as well as for matching an instance to an abstracted statistical model in the form of a Hidden Markov Model (HMM). We also present our approach to sign recognition that does not need hand tracking over frames, but rather abstracts and uses the global configuration of low-level features from hands and faces. These global representations are used not only for recognition, but also to extract and to automatically learn models of signs from continuous sentences in a weakly unsupervised manner. Our publications that discuss these issues and solutions in more detail can be found at http://marathon.csee.usf.edu/ASL/