L
Liu Yi
Researcher at Hebei University of Technology
Publications - 18
Citations - 181
Liu Yi is an academic researcher from Hebei University of Technology. The author has contributed to research in topics: Feature (computer vision) & Woven fabric. The author has an hindex of 8, co-authored 18 publications receiving 170 citations.
Papers
More filters
Patent
Vehicle license plate recognition method
TL;DR: In this paper, a vehicle license plate recognition method was proposed for image recognition. The method comprises the following steps of preprocessing an image; partitioning a vehicle region according to color and texture characteristics; extracting a remarkable factor graph of a vehicle Region diagram; extracting candidate vehicle license plates by an Adaboost classifier based on expanded Harr-like characteristic; determining the position of a real vehicle License Plate from the candidate Vehicle License Placement (VPLP) plates, and partitioning the marked vehicle License plate from the corresponding vehicle region original diagram; carrying out character segment
Patent
Small-sample face recognition method
Liu Yi,Yan Gang,Shi Shuo,Mao Yongbo,Liu Shuai,Guo Tuantuan,Li Weiqiang,Yang Feifei,Ge Ruixue,Liu Shuangling +9 more
TL;DR: In this article, a small-sample face recognition method is proposed, where a single-layer multi-scale convolutional neural network structure is used for performing multi-characteristic fusion and classification.
Patent
Method for recognizing human face micro-expressions in video sequence
TL;DR: In this article, a method for extracting dynamic spatial-temporal textural characteristics of human face micro-expression sequences based on the HLACLF-TOP algorithm is provided.
Patent
Image scaling method based on content awareness
TL;DR: In this article, a hybrid feature model fusing a salient map, an edge line map and a gradient map is adopted to obtain an energy function, and according to the energy function a line clipping operation is carried out to complete image scaling.
Patent
Binocular visual image stereo matching method
TL;DR: In this paper, a binocular visual image stereo matching method is presented, which consists of the steps of the acquisition and pre-processing of a binary image, the image gradient matrix solution of the binocular image, obtainment of an initial disparity map, and the obtainment and output of a final disparity map.