Open Access Open Access  Restricted Access Subscription or Fee Access

Deep Learning based CNN Architecture ‘NavNet’ For the Identification of Object Class and Qualities in Real Images

Dr. N. K. Darwante

Abstract


Identification of object in an image is the important issue in computer vision applications and afterward-subsequent task is to categorize these objects in suitable classes. The majority of the visualization work fundamentally based on the ability to identify objects, pictures, and subsequently categorize. Computer vision categorization itself has a variety of probable applications with the purpose to cover up many fields of machine learning and data mining and a range of applications for instance content-based image retrieval, video image retrieval, or object identification for movable robots etc.

I have tried many techniques to investigate optimum method to improve the convolutional neural network based image recognition and classification of given object. Here I present a simple, easy yet strong formulation of object identification and classification as a regression problem to object bounding box, and define a multi-scale inference procedure, which is able to produce object identification and classification with high resolution at a low cost by network applications. This method is based on deep learning convolution neural network and now becoming the state of the art technique in objects classification and image processing. 


Keywords


Object Classification, Deep Learning, Regression, CNN.

Full Text:

PDF

References


J. M. Buhmann, J. Malik, and P. Perona, “Image recognition: Visual grouping, recognition, and learning,” Proc. Natl. Acad. Sci., vol. 96, no. 25, pp. 14203–14204, 1999.

P. M. Roth and M. Winter, “Survey of Appearance-Based Methods for Object Recognition,” Technical report on computer graphics and vision, no. ICG- TR-01/08, p. 66, 2008.

M. Sonka, V. Hlavac, and R. Boyle, “Image Processing, Analysis, and Machine Vision Second Edition,” pp 312-427, January, 2014.

H. Motoda and H. Liu, “Feature selection, extraction and construction,” Commun. IICM, vol. 5, pp. 67–72, 2002.

S. Keypoints and D. G. Lowe, “Distinctive Image Features from,” Int. J. Comput. Vis., vol. 60, no. 2, pp. 91–110, 2004.

H. Bay, T. Tuytelaars, and L. Van Gool, “SURF: Speeded Up Robust Features,” Computer Vision and Image Understanding, Volume 110 Issue 3, pp. 346-359, June 2008.

C. Liu, L. Sharan, E. H. Adelson, and R. Rosenholtz, “Exploring features in a Bayesian framework for material recognition,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 239–246, 2010.

L. Zhi-Jie, “Image Classification Method Based on Visual Saliency and Bag of Words Model,” 2015 8th Int. Conf. Intell. Comput. Technol. Autom., pp. 466–469, Jun. 2015.

K. E. A van de Sande, C. G. M Snoek, and A. W. M Smeulders, “Fisher and VLAD with FLAIR” IEEE Conference on Computer Vision and Pattern Recognition, doi: 10.1109/CVPR.2014.304, pp. 2377-2384,2014

C. Szegedy et al., “Going Deeper with Convolutions,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, doi: 10.1109/CVPR.2015.7298594, pp. 1–9, 2015.

R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 580–587, 2014.

J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” 2015 IEEE Conf. Comput. Vis. Pattern Recognit., pp. 3431–3440, 2015.

M. D. Zeiler and R. Fergus, “Visualizing and Understanding Convolutional Networks arXiv: 1311.2901v3 [cs.CV] 28 Nov 2013,” Comput. Vision–ECCV 2014, vol. 8689, pp. 818–833, 2014.

N. K. Darwante and U. B. Shinde, “Identification of Objects Class and Qualities using Deep CNN Based Architecture,” World J. Technol. Eng. Res., vol. 2, no. 1, pp. 93–101, 2017.

P. Decker, S. Thierfelder, D. Paulus, and M. Grzegorzek, “Dense statistic versus sparse feature-based approach for 3D object recognition,” Pattern Recognit. Image Anal., vol. 21, no. 2, pp. 238–241, 2011.

N. K. Darwante and U. B. Shinde, “ Comparison of Self Developed Deep CNN Architecture with State of Art Existing Techniques,” CiiT International Journal of Artificial Intelligent Systems and Machine Learning, vol. 10, no. 3, 2018.


Refbacks

  • There are currently no refbacks.