No abstract

.With the wide popularity of surveillance cameras, video synopsis technology has become a research hotspot. The existing methods of surveillance video synopsis usually summarize the input video by shifting the object tube in the video on the time axis, which ignore the serious collision artifacts and chronological disorder between moving objects. To solve these problems, we propose a surveillance video synopsis methodology called “surveillance video synopsis based on spatio-temporal offset (STO)” that can simultaneously shift the moving object in the temporal domain and spatial domain. First, object detection and tracking algorithms are used to extract the object tube from the input video. Two collision relations are proposed by analyzing relationship between tubes to classify collision artifacts. Then, we present two spatial offset cases to find the optimal spatial offset of the object tube. Finally, an adaptive optimization frame density model is proposed to analyze the optimal temporal offset of the object tube. Simultaneously, the object tube and the background are stitched according to the STO to generate the synopsis video. Extensive experimental results demonstrate the effectiveness of the proposed method in improving frame compression rate and alleviating collision artifacts.

No abstract

No abstract

In the field of educational examination, automatic marking technology plays an essential role in improving the efficiency of marking and liberating the labor force. At present, the implementation of the policy of expanding erolments has caused a serious decline in the teacher-student ratio in colleges and universities. The traditional marking system based on Optical Mark Reader technology can no longer meet the requirements of liberating the labor force of teachers in small and medium-sized examinations. With the development of image processing and artificial neural network technology, the recognition of handwritten character in the field of pattern recognition has attracted the attention of many researchers. In this paper, filtering and de-noise processing and binary processing are used as preprocessing methods for handwriting recognition. Extract the pixel feature of handwritten characters through digital image processing of handwritten character pictures, and then, get the feature vector from these feature fragments and use it as the description of the character. The extracted feature values are used to train the neural network to realize the recognition of handwritten English letters and numerical characters. Experimental results on Chars74K and MNIST data sets show that the recognition accuracy of some handwritten English letters and numerical characters can reach 90% and 99%, respectively.