A Computer Vision Framework for Automatic Description of Indian Monuments

Monument recognition and description has emerged as a promising area of research. For any given image of a monument a question arises that up to what extend can a computer model describe the monument from that image?The main objective of the paper is to propose a framework which is capable of identifying multiple attributes from a single image of a monument. Four different attributes i.e. the class of the monument, the style of the architecture, the time period in which the monument was constructed and the type of the monument are taken into consideration. The paper proposes a framework that relies on Deep Convolutional Neural Networks (DCNN) for describing the monument in terms of the aforementioned attributes. The experiments have been performed on a dataset comprising of 6102 images of 117 Indian monuments. The model was able to achieve an accuracy greater than 80% for all the different set of experimentations. The results clearly indicate the usefulness of the framework.

[1]  Noah Snavely,et al.  Image matching using local symmetry features , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Titus B. Zaharia,et al.  Building recognition with adaptive interest point selection , 2017, 2017 IEEE International Conference on Consumer Electronics (ICCE).

[3]  C. V. Jawahar,et al.  Dynamic Narratives for Heritage Tour , 2016, ECCV Workshops.

[4]  Pietro Perona,et al.  Graph-Based Visual Saliency , 2006, NIPS.

[5]  Balasubramanian Raman,et al.  A Deep Learning Frame-Work for Recognizing Developmental Disorders , 2017, 2017 IEEE Winter Conference on Applications of Computer Vision (WACV).

[6]  Pavol Bezak.  Building recognition system based on deep learning , 2016, 2016 Third International Conference on Artificial Intelligence and Pattern Recognition (AIPR).

[7]  Fei-Fei Li,et al.  Large-Scale Video Classification with Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Malay S. Bhatt,et al.  Genetic programming evolved spatial descriptor for Indian monuments classification , 2015, 2015 IEEE International Conference on Computer Graphics, Vision and Information Security (CGVIS).

[9]  Alexei A. Efros,et al.  What makes Paris look like Paris? , 2015, Commun. ACM.

[10]  C. V. Jawahar,et al.  Are buildings only instances?: exploration in architectural style categories , 2012, ICVGIP '12.

[11]  Padmashree Desai,et al.  Classification of archaeological monuments for different art forms with an application to CBIR , 2013, 2013 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[12]  Claudio Gennaro,et al.  Fast Image Classification for Monument Recognition , 2015, JOCCH.

[13]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[14]  Georgios Triantafyllidis,et al.  Image based Monument Recognition using Graph based Visual Saliency , 2013 .

[15]  Daniel P. Huttenlocher,et al.  Landmark classification in large-scale image collections , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[16]  Fabrizio Falchi,et al.  Recognizing Landmarks Using Automated Classification Techniques: Evaluation of Various Visual Features , 2010, 2010 Second International Conferences on Advances in Multimedia.

[17]  SivicJosef,et al.  What makes Paris look like Paris , 2012 .