The combination of a CNN detector and a search framework forms the basis for local object/pattern detection. To handle the waste of regional information and the defective compromise between efficiency and accuracy, this paper proposes a probabilistic model with a powerful search framework. By mapping an image into a probabilistic distribution of objects, this new model gives more informative outputs with less computation. The setting and analytic traits are elaborated in this paper, followed by a series of experiments carried out on FDDB, which show that the proposed model is sound, efficient and analytic.
@article{arxiv.1808.08272,
title = {Probabilistic Model of Object Detection Based on Convolutional Neural Network},
author = {Fang-Qi Li and Xu-Die Ren and Hao-Nan Guo},
journal= {arXiv preprint arXiv:1808.08272},
year = {2018}
}
Comments
8 pages, 8 figures, International Conference on Communication, Signal Processing and Systems (CSPS 2017)