Evaluating retraining rules for semi-supervised learning in neural network based cursive word recognition

Training a system to recognize handwritten words is a task that requires a large amount of data with their correct transcription. However, the creation of such a training set, including the generation of the ground truth, is tedious and costly. One way of reducing the high cost of labeled training data acquisition is to exploit unlabeled data, which can be gathered easily. Making use of both labeled and unlabeled data is known as semi-supervised learning. One of the most general versions of semi-supervised learning is self-training, where a recognizer iteratively retrains itself on its own output on new, unlabeled data. In this paper we propose to apply semi-supervised learning, and in particular self-training, to the problem of cursive, handwritten word recognition. The special focus of the paper is on retraining rules that define what data are actually being used in the retraining phase. In a series of experiments it is shown that the performance of a neural network based recognizer can be significantly improved through the use of unlabeled data and self-training if appropriate retraining rules are applied.

On the use of textural features for writer identification in old handwritten music scores

Writer identification consists in determining the writer of a piece of handwriting from a set of writers. In this paper we present a system for writer identification in old handwritten music scores which uses only music notation to determine the author. The steps of the proposed system are the following. First of all, the music sheet is preprocessed for obtaining a music score without the staff lines. Afterwards, four different methods for generating texture images from music symbols are applied. Every approach uses a different spatial variation when combining the music symbols to generate the textures. Finally, Gabor filters and Grey-scale Co-ocurrence matrices are used to obtain the features. The classification is performed using a k-NN classifier based on Euclidean distance. The proposed method has been tested on a database of old music scores from the 17th to 19th centuries, achieving encouraging identification rates.

Analysis of eye and head coordination in a visual peripheral recognition task

Coordinated eye and head movements simultaneously occur to scan the visual world for relevant targets. However, measuring both eye and head movements in experiments allowing natural head movements may be challenging. This paper provides an approach to study eye-head coordination: First, we demonstra- te the capabilities and limits of the eye-head tracking system used, and compare it to other technologies. Second, a beha- vioral task is introduced to invoke eye-head coordination. Third, a method is introduced to reconstruct signal loss in video- based oculography caused by cornea reflection artifacts in order to extend the tracking range. Finally, parameters of eye- head coordination are identified using EHCA (eye-head co- ordination analyzer), a MATLAB software which was developed to analyze eye-head shifts. To demonstrate the capabilities of the approach, a study with 11 healthy subjects was performed to investigate motion behavior. The approach presented here is discussed as an instrument to explore eye-head coordination, which may lead to further insights into attentional and motor symptoms of certain neurological or psychiatric diseases, e.g., schizophrenia.

Emotion recognition: The role of featural and configural face information

Several studies investigated the role of featural and configural information when processing facial identity. A lot less is known about their contribution to emotion recognition. In this study, we addressed this issue by inducing either a featural or a configural processing strategy (Experiment 1) and by investigating the attentional strategies in response to emotional expressions (Experiment 2). In Experiment 1, participants identified emotional expressions in faces that were presented in three different versions (intact, blurred, and scrambled) and in two orientations (upright and inverted). Blurred faces contain mainly configural information, and scrambled faces contain mainly featural information. Inversion is known to selectively hinder configural processing. Analyses of the discriminability measure (A′) and response times (RTs) revealed that configural processing plays a more prominent role in expression recognition than featural processing, but their relative contribution varies depending on the emotion. In Experiment 2, we qualified these differences between emotions by investigating the relative importance of specific features by means of eye movements. Participants had to match intact expressions with the emotional cues that preceded the stimulus. The analysis of eye movements confirmed that the recognition of different emotions rely on different types of information. While the mouth is important for the detection of happiness and fear, the eyes are more relevant for anger, fear, and sadness.

Sulfamethoxazole induces a switch mechanism in T cell receptors containing TCRVβ20-1, altering pHLA recognition

T cell receptors (TCR) containing Vβ20-1 have been implicated in a wide range of T cell mediated disease and allergic reactions, making it a target for understanding these. Mechanics of T cell receptors are largely unexplained by static structures available from x-ray crystallographic studies. A small number of molecular dynamic simulations have been conducted on TCR, however are currently lacking either portions of the receptor or explanations for differences between binding and non-binding TCR recognition of respective peptide-HLA. We performed molecular dynamic simulations of a TCR containing variable domain Vβ20-1, sequenced from drug responsive T cells. These were initially from a patient showing maculopapular eruptions in response to the sulfanilamide-antibiotic sulfamethoxazole (SMX). The CDR2β domain of this TCR was found to dock SMX with high affinity. Using this compound as a perturbation, overall mechanisms involved in responses mediated by this receptor were explored, showing a chemical action on the TCR free from HLA or peptide interaction. Our simulations show two completely separate modes of binding cognate peptide-HLA complexes, with an increased affinity induced by SMX bound to the Vβ20-1. Overall binding of the TCR is mediated through a primary recognition by either the variable β or α domain, and a switch in recognition within these across TCR loops contacting the peptide and HLA occurs when SMX is present in the CDR2β loop. Large binding affinity differences are induced by summed small amino acid changes primarily by SMX modifying only three critical CDR2β loop amino acid positions. These residues, TYRβ57, ASPβ64, and LYSβ65 initially hold hydrogen bonds from the CDR2β to adjacent CDR loops. Effects from SMX binding are amplified and traverse longer distances through internal TCR hydrogen bonding networks, controlling the overall TCR conformation. Thus, the CDR2β of Vβ20-1 acts as a ligand controlled switch affecting overall TCR binding affinity.