Text Detection by DCT energy localization
The original method described in [1] computes an energy measure of a set of DCT coefficients of intra-coded blocks as a texture measure.
The energy computation code came from the text detection baseline algorithm provided in [2].
[1] N. Chaddha, R. Sharma, A. Agrawal, and A. Gupta. "Text Segmentation in Mixed–Mode Images," In 28th Asilomar Conference on Signals, Systems and Computers, pages 1356–1361, October 1994.
[2] R. Kasturi, D. Goldgof, P. Soundararajan, V. Manohar, J. Garofolo, R. Bowers, M. Boonstra, V. Korzhova, and J. Zhang, "Framework for performance evaluation of face, text, and vehicle detection and tracking in video: Data, metrics, and protocol," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 2, pp. 319–336, 2009.