In this paper, we address the problem of acquiring guidance images for use in joint up-sampling of high dynamic range (HDR) images. A guidance image is usually an unprocessed high-resolution image that is indispensable to joint up-sampling, which is aimed at accelerating a large class of image processing operators. However, the guidance image is blank-posed in joint up-sampling of the HDR image, which involves the process where multiple low dynamic range (LDR) images with various exposure times in the same scene are synthesized into one image with a greater dynamic range; Such many-toone operations limit joint up-sampling in being applied to this field. To this end, we propose an HDR guidance image (HGI), which is an image type generated by weighted averaging LDR images into a single with rich contour information. The huge advantage of joint up-sampling is that the cost of running the original algorithm is at a greatly reduced resolution. Since HGI synthesis takes about 3-70ms, and joint up-sampling of an HDR image takes about 20-300ms, most operations can be done with GPU shaders. Compared with the conventional methods of HDR image reconstruction, using joint upsampling can achieve 3-10 times the performance acceleration. We demonstrate that joint up-sampling using our guidance images can produce high-resolution HDR images with no visible degradation compared to the image produced by the conventional method.

As an important part in the field, the natural scene text detection has been widely applied in visual navigation system, content-based image and video retrieval, instant translation system and so on. In this paper, we introduce several object detection network based on deep learning, and apply the YOLO v2 into natural scene text detection, changing the multi objects detection problems into the two classification problems. The main works in the paper include the following: prepare the datasets; we train the YOLO v2 with the optimum parameters, carry out the regression analysis of the coordinate parameters and categories of bounding boxes, obtain the detection result; according to different detection models, the detection results of different datasets are compared and analyzed, YOLO V2 model detection speed 0.105s/image has certain advantages.