On June 4th, Prof. Lin Jianwen from Department of Electronics and Information Engineering of the Hong Kong Polytechnic University was invited to the School of Information Science and Engineering of our university to present an academic report titled “Cascaded face alignment via intimacy definition feature”. The teachers and students of the School of Information Science and Engineering and the Key Laboratory of Intelligent Computing Technology for Network Environment in Shandong Province attended the report. The report was hosted by Dr Li Yang, Assistant Dean of the Information Institute.
At the report meeting, Prof. Lin Jianwen proposed to design a cascading regression model based on a random forest by using a novel local lightweight feature, namely, the Informed Definition Property (IDF). This feature is more discriminating than the gesture index feature, more efficient than the gradient-oriented (HOG) feature and scale-invariant feature transform (SIFT) feature histogram, and more compact than the local binary feature (LBF). After the report meeting, Professor Lin carefully answered questions from the participants and he conducted inspiring discussions with everyone from the perspective of scientific research. In the end, Dr. Li Yang summarized this report.