Zhaohui Sun

TL;DR: In this article, foreground and background segmentation is used for clustering images from a group into similar events, where each image is divided into a plurality of blocks, and each block-based image is segmented into regions comprising at least a foreground and a background.

TL;DR: In this paper, a system for the detection of abnormalities in a medical image of a subject is presented, which includes an examination bundle, a learning engine, and a detecting engine.

TL;DR: A method of automated content-based grouping of digital images without using auxiliary metadata and training data set, comprises the steps of computing a color correlogram from image pixel values for each of the digital images, grouping the color correlograms into groups within a hierarchical structure based on relative similarities of the color correlations, and assigning the images to the groups based on the hierarchical structure of the colour correlograms as mentioned in this paper.

TL;DR: In this paper, the authors propose a preferred embodiment of a multimedia slide show, which comprises the steps of: selecting a plurality of digital images, encoding each of the plurality of images to generate a normal resolution image portion and a high resolution image part, multiplexing each corresponding normal and high-resolution image portion to generate one high resolution still image, determining a time parameter for each of these high resolution images, selecting an audio portion for at least one of the images, and concatenating the video bitstream and audio bitstream by encoding the audio portion.

TL;DR: In this paper, an anomaly detection method is proposed to acquire image data corresponding to nondestructive testing (NDT) of a scanned object, where the NDT image data comprises at least one inspection test image of the scanned object and multiple reference images for the object.