Skip navigation
Please use this identifier to cite or link to this item:
Title: Can we automate diagrammatic reasoning?
Authors: Sekh A.A.
Dogra D.P.
Kar S.
Pratim Roy, Partha
Prasad D.K.
Published in: Pattern Recognition
Abstract: Diagrammatic reasoning (DR) problems are well known. However, solving DR problems represented in 4 × 1 Raven's Progressive Matrix (RPM) form using computer vision and pattern recognition has not yet been tried. Emergence of deep learning techniques aided by advanced computing can be exploited to solve such DR problems. In this paper, we propose a new learning framework by combining LSTM and Convolutional LSTM to solve 4 × 1 DR problems. Initially, the elementary geometrical shapes in such problems are detected using a typical CNN-based detector. Next, relations of various shapes are analyzed and a high-level feature set is produced and processed in the LSTM framework. A new 4 × 1 DR dataset has been prepared and made available to the research community. We believe, it will be helpful in advancing this research further. We have compared our method with some of the existing frameworks that can be used for solving RPM-guided DR problems. We have recorded 18–20% increase in the average prediction accuracy as compared to the prior frameworks when applied to RPM-guided DR problems. We believe the CV research community will be interested to carry out similar research, particularly to investigate the feasibility of solving other types of known DR problems. © 2020 The Author(s)
Citation: Pattern Recognition, 106
Issue Date: 2020
Publisher: Elsevier Ltd
Keywords: Abstract reasoning
Diagrammatic reasoning
Raven,s Progressive Matrices (RPM)
Visual IQ test
ISSN: 313203
Author Scopus IDs: 57216801662
Author Affiliations: Sekh, A.A., UiT The Arctic University of Norway, Tromsø, Norway
Dogra, D.P., Indian Institute of Technology, Bhubaneswar, India
Kar, S., National Institute of Technology, Durgapur, India
Roy, P.P., Indian Institute of Technology, Roorkee, India
Prasad, D.K., UiT The Arctic University of Norway, Tromsø, Norway
Funding Details: We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Quadro P5000 GPU used for this research. Nvidia
Corresponding Author: Sekh, A.A.; UiT The Arctic University of NorwayNorway; email:
Appears in Collections:Journal Publications [CS]

Files in This Item:
There are no files associated with this item.
Show full item record

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.