A Preliminary Study on Color and Grayscale Images Object Recognition and Scene Classification Tasks on Amazon Mechanical Turk Crowdsourcing Platform
Nowadays most of the information on the Internet is displayed in color images. When it comes to image-related tasks, it becomes critical for us to understand how efficiently the color images are processed for fulfilling the targeted tasks in terms of accuracy and time. Thus, in this study we conducted an initial study to explore how color and grayscale images were likely to affect the results of the crowdsourcing works by using the novel crowdsourcing platform, Amazon Mechanical Turk, so as to better improve the efficiency of the works for image design and to better utilize database space for enterprises at the same time. Eventually some significant findings, suggestions and suggestions for future study will be presented at the end of this paper.
KeywordsHuman-Centered design Human computer interaction Object recognition Scene classification
- 1.Ostergaard, A.L., Davidoff, J.B.: Some effects of color on naming and recognition of objects. J. Exp. Psychol. Learn. Mem. Cogn. 11(3), 579 (1985)Google Scholar
- 2.Wurm, L.H., et al.: Color improves object recognition in normal and low vision. J. Exp. Psychol. Hum. Percept. Perform. 19(4), 899 (1993)Google Scholar
- 6.Li, L.-J., et al.: Object bank: a high-level image representation for scene classification & semantic feature sparsification. In: Advances in Neural Information Processing Systems, pp. 1378–1386 (2010)Google Scholar