In recent years, fast neural networks for object/face detection have been introduced based on cross correlation in the frequency domain between the input matrix and the hidden weights of neural networks. In our previous papers [3,4], fast neural networks for certain code detection was introduced. It was proved in [10] that for fast neural networks to give the same correct results as conventiona...

Individuals with autism spectrum disorders (ASD) have documented deficits in face processing, face memory and abnormal activation of the neural circuitry that supports these functions. To examine speed of processing of faces in ASD, high density event-related brain potentials were recorded to images of faces, inverted faces and non-face objects from 32 high-functioning adults with ASD and contr...

We investigated the influence of saccadic eye movements on the magnitude of functional MRI (fMRI) activation in brain regions known to participate in object and face perception. In separate runs, subjects viewed a static image of a uniform gray field, a face, or a flower. Every 500 ms a small fixation cross made a discrete jump within the image and subjects were required to make a saccade and f...

Repetition priming (RP) has been employed as a measure of implicit processing in patients suffering from a breakdown of semantic memory, as in the case of semantic dementia (SD), a subtype of frontotemporal lobar degeneration (FTLD). Here, we investigated face-name representation in a case of SD using a paradigm of within- and cross-domain repetition priming. Compared to ten healthy participant...

We approach the task of person identification based on face and gait cues. The cues are derived from multiple simultaneous camera views, combined through the visual hull algorithm to create imagery in canonical pose prior to recognition. These view-normalized sequences, containing frontal images of face and profile silhouettes, are separately used for face and gait recognition, and the results ...

The question whether the recognition of individual faces is mandatory or task-dependent is still controversial. We employed the N250r component of the event-related potential as a marker of the activation of representations of facial identity in visual memory, in order to find out whether identity-related information from faces is encoded and maintained even when facial identity is task-irrelev...

In this article, we propose a hybrid framework for cross-resolution 3D face recognition which utilizes Streamed Attention Network (SAN) that combines handcrafted features with Convolutional Neural Networks (CNNs). It consists of two main stages: first, process the depth images to extract low-level surface descriptors and derive corresponding Descriptor Images (DIs), represented as four-channel ...