A novel generated method for high quality images

Thanks to the diversity and popularity of image acquisition technique, data driven methods for image analysis and edit become popular. However, the explosive growth of images also presents challenges. To help users retrieve expected images quickly and effectively is one of the hardest tasks. It is difficult to express the user's intention completely for a single cue, thus combining multiple cues becomes necessary. Another problem is that the content-based matching process takes a long time in the case of massive image data. In this dissertation, we propose a progressive retrieval method for high quality images, targeting on the problems that the existed retrieval methods cannot guarantee the image quality and the time consuming of the feature matching for the massive material. We start from the fastest text matching and a progressive strategy is used to evaluate the image quality from both the clarity and independence. Finally, the scene elements of these object is extracted, and the contours are matched between the user sketch and the contours of the candidate scene elements. We parallelize the whole framework in a MapReduce framework to further improve the performance. We validate the performance, accuracy of the algorithm and quality of retrieval result in various experiments. The results show that our method can improve the efficiency of the retrieval and control the image quality of the retrieve results better. Then we can rapidly create a high quality image through simple line sketch.