A framework for rapid visual image search using single-trial brain evoked responses

Huang, Yonghong; Erdoğmuş, Deni̇z; Pavel, Misha; Mathan, Santosh; Hild, Kenneth E.

doi:10.1016/j.neucom.2010.12.025

Cited by 73 publications

(56 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This technology has been tested in a large variety of applications, most typically to allow people with severe motor disabilities to communicate and operate actuators of different kinds [19], [20], [21], [22], [23]. In the last few years, however, BCIs have been developed also for the cognitive augmentation of able-bodied individuals, e.g., to improve human decision accuracy or speed [24], [25], [26].…”

Section: Collaborative Brain-computer Interfacesmentioning

confidence: 99%

Enhancement of Group Perception via a Collaborative Brain–Computer Interface

Valeriani

Poli

Cinel

2017

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Abstract-Objective. We aimed at improving group performance in a challenging visual search task via a hybrid Collaborative Brain-Computer Interface (cBCI). Methods. Ten participants individually undertook a visual search task where a display was presented for 250 ms, and they had to decide whether a target was present or not. Local Temporal Correlation Common Spatial Pattern (LTCCSP) was used to extract neural features from response-and stimulus-locked EEG epochs. The resulting feature vectors were extended by including response times and features extracted from eye movements. A classifier was trained to estimate the confidence of each group member. cBCI-assisted group decisions were then obtained using a confidence-weighted majority vote. Results. Participants were combined in groups of different sizes to assess the performance of the cBCI. Results show that LTCCSP neural features and eye movements features significantly improve the accuracy of the cBCI over what we achieved with previous systems. For most group sizes, our hybrid cBCI yields group decisions that are significantly better than majority-based group decisions. Conclusion. The visual task considered here was much harder than a task we used in previous research. However, thanks to a range of technological enhancements, our cBCI has delivered a significant improvement over group decisions made by a standard majority vote. Significance. With previous cBCIs groups may perform better than single non-BCI users. Here, cBCI-assisted groups are more accurate than identically-sized non-BCI groups. This paves the way to a variety of real-world applications of cBCIs where reducing decision errors is vital.

show abstract

Section: Collaborative Brain-computer Interfacesmentioning

confidence: 99%

Enhancement of Group Perception via a Collaborative Brain–Computer Interface

Valeriani

Poli

Cinel

2017

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…{amatra,rpoli}@essex.ac.uk [10], [11], [12], [13], [14]. This problem is particularly important in counter intelligence and policing, where large numbers of images are screened in search for threats on a daily basis [13], [15]. However, other real-life applications of this technology include the screening of mammograms [16] and geoscientific images [17] by trained experts.…”

Section: Introductionmentioning

confidence: 99%

Brain–Computer Interfaces for Detection and Localization of Targets in Aerial Images

Matran-Fernandez

Poli

2017

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Abstract-Objective. The N2pc event-related potential (ERP) appears on the opposite side of the scalp with respect to the visual hemisphere where an object of interest is located. We explored the feasibility of using it to extract information on the spatial location of targets in aerial images shown by means of a rapid serial visual presentation (RSVP) protocol using single-trial classification. Methods. Images were shown to 11 participants at a presentation rate of 5 Hz while recording electroencephalographic signals.With the resulting ERPs we trained linear classifiers for singletrial detection of target presence and location. We analysed the classifiers' decisions and their raw output scores on independent test sets as well as the averages and voltage distributions of the ERPs. Results. The N2pc is elicited in RSVP presentation of complex images and can be recognised in single trials (the median area under the receiver operating characteristic curve was 0.76 for left vs right classification). Moreover, the peak amplitude of this ERP correlates with the horizontal position of the target within an image. The N2pc varies significantly depending on handedness, and these differences can be used for discriminating participants in terms of their preferred hand. Conclusion and Significance. The N2pc is elicited during RSVP presentation of real complex images and contains analogue information that can be used to roughly infer the horizontal position of targets. Furthermore, differences in the N2pc due to handedness should be taken into account when creating collaborative brain-computer interfaces.

show abstract

“…Previous works combining BCI and computer vision [9,25,12] have been focused primarily on image retrieval and object detection. In such work images are presented to participants according to the oddball paradigm.…”

Section: Related Workmentioning

confidence: 99%

Improving object segmentation by using EEG signals and rapid serial visual presentation

Mohedano

Healy

McGuinness

et al. 2015

Multimed Tools Appl

View full text Add to dashboard Cite

This paper extends our previous work on the potential of EEGbased brain computer interfaces to segment salient objects in images. The proposed system analyzes the Event Related Potentials (ERP) generated by the rapid serial visual presentation of windows on the image. The detection of the P300 signal allows estimating a saliency map of the image, which is used to seed a semi-supervised object segmentation algorithm. Thanks to the new contributions presented in this work, the average Jaccard index was improved from 0.47 to 0.66 when processed in our publicly available dataset of images, object masks and captured EEG signals. This work also studies alternative architectures to the original one, the impact of object occupation in each image window, and a more robust evaluation based on statistical analysis and a weighted F-score.

show abstract

A framework for rapid visual image search using single-trial brain evoked responses

Cited by 73 publications

References 25 publications

Enhancement of Group Perception via a Collaborative Brain–Computer Interface

Enhancement of Group Perception via a Collaborative Brain–Computer Interface

Brain–Computer Interfaces for Detection and Localization of Targets in Aerial Images

Improving object segmentation by using EEG signals and rapid serial visual presentation

Contact Info

Product

Resources

About