Can we automate diagrammatic reasoning?

PATTERN RECOGNITION

卷:106

Article

Sekh, Arif Ahmed¹  Dogra, Debi Prosad³  Kar, Samarjit⁴  Roy, Partha Pratim⁵  Prasad, Dilip K.² 

[1] UiT Arctic Univ Norway, Dept Phys & Technol, Tromso, Norway

[2] UiT Arctic Univ Norway, Tromso, Norway

[3] Indian Inst Technol, Bhubaneswar, India

[4] Natl Inst Technol, Dept Math, Durgapur, India

[5] Indian Inst Technol, Roorkee, Uttar Pradesh, India

关键词: Abstract reasoning;    Raven,s Progressive Matrices (RPM);    Diagrammatic reasoning;    Visual IQ test;   

DOI  :  10.1016/j.patcog.2020.107412

来源: Elsevier

【 摘 要 】

Diagrammatic reasoning (DR) problems are well known. However, solving DR problems represented in 4 x 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 x 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 x 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. (C) 2020 The Author(s). Published by Elsevier Ltd.

【 授权许可】

Free