Towards No-Reference Image Quality Assessment Based on Multi-Scale Convolutional Neural Network

Image quality assessment has become increasingly important in image quality monitoring and reliability assuring of image processing systems.Most of the existing no-reference image quality assessment methods mainly exploit the global information of image while ignoring vital local information.Actually,the introduced distortion depends on a slight difference in details between the distorted image and the non-distorted reference image.In light of this,we propose a no-reference image quality assessment method based on a multi-scale convolutional neural network,which integrates both global information and local information of an image.We first adopt the image pyramid method to generate four scale images required for network input and then provide two network models by respectively using two fusion strategies to evaluate image quality.In order to better adapt to the quality assessment of the entire image,we use two different loss functions in the training and validation phases.The superiority of the proposed method is verified by several different experiments on the LIVE datasets and TID2008 datasets.

Medical Image Edge Detection Based on EMD Method

As a new image analysis technique, Empirical Mode Decomposition （EMD） has been drawn more attention in recent years. In this paper, we proposed a fast EMD method for the edge detection of medical images. We implemented the method in the following steps： a） Decompose the original medical image with the image pyramid technique; b） Implement the EMD at the low resolution level image; c） Map the Intrinsic Mode Functions （IMFs） into the original image; d） Use the edge detector in a coarse IMF at the beginning of the procedure; e） Trace the detected result to the finest IMF to obtain the final image edge. Experimental results demonstrated the effectiveness of the proposed method.

Reformatted method for two-dimensional detector arrays measurement data in proton pencil beam scanning

The spatial resolution of a commercial two-dimensional(2D)ionization chamber(IC)array is limited by the size of the individual detector and the center-to-center distance between sensors.For dose distributions with areas of steep dose gradients,inter-detector dose values are derived by the interpolation of nearby detector readings in the conventional mathematical interpolation of 2D IC array measurements.This may introduce significant errors,particularly in proton spot scanning radiotherapy.In this study,by combining logfile-based reconstructed dose values and detector measurements with the Laplacian pyramid image blending method,a novel method is proposed to obtain a reformatted dose distribution that provides an improved estimation of the delivered dose distribution with high spatial resolution.Meanwhile,the similarity between the measured original data and the downsampled logfilebased reconstructed dose is regarded as the confidence of the reformatted dose distribution.Furthermore,we quantify the performance benefits of this new approach by directly comparing the reformatted dose distributions with 2D IC array detector mathematically interpolated measurements and original low-resolution measurements.The result shows that this new method is better than the mathematical interpolation and achieves gamma pass rates similar to those of the original low-resolution measurements.The reformatted dose distributions generally yield a confidence exceeding 95%.

Cross-talk-free integral imaging three-dimensional display based on a pyramid pinhole array

We propose a cross-talk-free integral imaging 3D display based on a pyramid pinhole array. The pyramid pinhole array is used to provide a point light source array. Since the generated point light source array is behind a transmission-type display panel that displays an elemental image array, the pseudoscopic problem can be resolved. By setting the appropriate parameters for the pyramid pinhole array, the cross talk can be eliminated.We experimentally verify the reconstruction of the orthoscopic and cross-talk-free 3D images using the proposed 3D display.

A pyramid-based approach to visual exploration of a large volume of vehicle trajectory data

Advances in positioning and wireless commu- nicating technologies make it possible to collect large volumes of trajectory data of moving vehicles in a fast and convenient fashion. These data can be applied to traffic studies. Behind this application, a methodological issue that still requires particular attention is the way these data should be spatially visualized. Trajectory data physically consists of a large number of positioning points. With the dramatic increase of data volume, it becomes a challenge to display and explore these data. Existing commercial software often employs vector-based indexing structures to facilitate the display of a large volume of points, but their performance downgrades quickly when the number of points is very large, for example, tens of millions. In this paper, a pyramid-based approach is proposed. A pyramid method initially is invented to facilitate the display of raster images through the tradeoff between storage space and display time. A pyramid is a set of images at different levels with different resolutions. In this paper, we convert vector-based point data into raster data, and build a grid- based indexing structure in a 2D plane. Then, an image pyramid is built. Moreover, at the same level of a pyramid, image is segmented into mosaics with respect to the requirements of data storage and management. Algorithms or procedures on grid-based indexing structure, image pyramid, image segmentation, and visualization operations are given in this paper. A case study with taxi trajectory data in Shanghai is conducted. Results demonstrate that the proposed method outperforms the existing commercial software.