Pattern Recognition and Tracking XXXIII / edited by Mohammad S. Alam, Vijayan K. Asari.

Format:

Book

Contributor:

Asari, Vijayan K., editor.

Alam, Mohammad S., editor.

Language:

English

Subjects (All):

Pattern recognition systems--Congresses.

Pattern recognition systems.

Physical Description:

1 online resource (6 pages)

Place of Publication:

[Place of publication not identified] : SPIE, 2022.

Summary:

The papers in this volume were part of the technical conference cited on the cover and title page. Papers were selected and subject to review by the editors and conference program committee. Some conference presentations may not be available for publication. Additional papers and presentation recordings may be available online in the SPIE Digital Library at SPIEDigitalLibrary.org. The papers reflect the work and thoughts of the authors and are published herein as submitted. The publisher is not responsible for the validity of the information or for any outcomes resulting from reliance thereon.

Contents:

v Conference Committee

SESSION 1 IMAGE QUALITY AND TRACKING TECHNIQUES

12101 02 Medical image segmentation using U-Net and progressive neuron expansion (Invited Paper)

[12101-1]

12101 03 Understanding the relationship between image quality and convolutional neural network

performance [12101-2]

12101 04 Geosynchronous satellite detection and tracking with WFOV camera arrays using

spatio-temporal neural networks (GEO-SPANN) [12101-3]

12101 05 Smart system for blurring undesirable objects in road applications [12101-4]

12101 06 Late fusion of pre-trained networks for satellite image classification [12101-5]

SESSION 2 TRENDS IN PATTERN RECOGNITION

12101 07 A new approach for removing point cloud outliers using the standard score [12101-8]

12101 08 A new approach for removing point cloud outliers using box plot [12101-9]

12101 09 Voronoi diagram based handwritten word segmentation [12101-10]

SESSION 3 NOVEL DEEP LEARNING TECHNIQUES

12101 0A Investigating the performance of an artificial neural network for selecting priority rules for

solving the resource-constrained project scheduling problem (RCPSP) [12101-12]

SESSION 4 DETECTION AND TRACKING

12101 0B Marker-less motion capture system using OpenPose [12101-16]

12101 0C Virtual assistant for first responders using natural language understanding and optical

character recognition [12101-17]

SESSION 5 ARTIFICIAL-INTELLIGENCE-BASED TRACKING

12101 0D TruePAL: an AI assistant for first responder safety (Invited Paper) [12101-19]

12101 0E Re-defining radiology quality assurance (QA): artificial intelligence (AI)-based QA by

restricted investigation of unequal scores (AQUARIUS) [12101-22]

12101 0F Can simpler be better? Review of methods for the detection of GAN-generated imagery

[12101-39]

SESSION 6 MACHINE LEARNING BASED RECOGNITION

12101 0G Neurosymbolic hybrid approach to driver collision warning [12101-24]

SESSION 7 DEEP NEURAL LEARNING BASED RECOGNITION

12101 0H Crowd detection and estimation for an earthquake early warning system using deep learning

[12101-32]

12101 0I Improving face recognition by pose-aware quality assessment and judgement [12101-33]

12101 0J Facial expression recognition robust to occlusion using spatial transformer network with triplet

loss function [12101-36]

POSTER SESSION

12101 0K RA-MISNet: multilevel information sharing network based on residual attention for crowd

counting [12101-11]

12101 0L Formation of a method and algorithm for automated analysis of the degree of attention and

concentration of an operator [12101-34].

Notes:

Description based on online resource; title from PDF title page (SPIE, viewed May 6, 2023).

ISBN:

1-5106-5079-2