Eudora Welty's One Time,One Place snapped Mississippi featuring Jackson,Hinds County,Yazoo County,Utica and so on.These photographs of daily life stories,most of which were taken without the awareness of the peopl...Eudora Welty's One Time,One Place snapped Mississippi featuring Jackson,Hinds County,Yazoo County,Utica and so on.These photographs of daily life stories,most of which were taken without the awareness of the people photographed,show an aesthetic vi-sion that reveals the real life of Mississippi in the 1930 s.They also show that a fiction writer's camera records people's life and citylandscapes that are somewhat different from what we see in newspapers or geography books.The unique angles chosen and the specialmoments captured by Welty make these photographs worth a careful attention.Visual Grammar is used to examine and analyze the innerworld of the people photographed by Welty.By analyzing three photographs through action processes,reactional processes,and symbolicprocesses as well as by studying the systems of Contact and Social Distance of the photographs,representational meaning and interactivemeaning are explored.The system of information value is also studied to find out how the compositional meaning is realized in the photo-graphs.After a thorough study,the lost inner worlds of the people photographed by Welty can be exposed.展开更多
A Single Image Super-Resolution (SISR) reconstruction method that uses clustered sparse representation and adaptive patch aggregation is proposed. First, we randomly extract image patch pairs from the training images,...A Single Image Super-Resolution (SISR) reconstruction method that uses clustered sparse representation and adaptive patch aggregation is proposed. First, we randomly extract image patch pairs from the training images, and divide these patch pairs into different groups by K-means clustering. Then, we learn an over-complete sub-dictionary pair offline from corresponding group patch pairs. For a given low-resolution patch, we adaptively select one sub-dictionary to reconstruct the high resolution patch online. In addition, non-local self-similarity and steering kernel regression constraints are integrated into patch aggregation to improve the quality of the recovered images. Experiments show that the proposed method is able to realize state-of-the-art performance in terms of both objective evaluation and visual perception.展开更多
文摘Eudora Welty's One Time,One Place snapped Mississippi featuring Jackson,Hinds County,Yazoo County,Utica and so on.These photographs of daily life stories,most of which were taken without the awareness of the people photographed,show an aesthetic vi-sion that reveals the real life of Mississippi in the 1930 s.They also show that a fiction writer's camera records people's life and citylandscapes that are somewhat different from what we see in newspapers or geography books.The unique angles chosen and the specialmoments captured by Welty make these photographs worth a careful attention.Visual Grammar is used to examine and analyze the innerworld of the people photographed by Welty.By analyzing three photographs through action processes,reactional processes,and symbolicprocesses as well as by studying the systems of Contact and Social Distance of the photographs,representational meaning and interactivemeaning are explored.The system of information value is also studied to find out how the compositional meaning is realized in the photo-graphs.After a thorough study,the lost inner worlds of the people photographed by Welty can be exposed.
基金partially supported by the National Natural Science Foundation of China under Grants No. 61071146, No. 61171165the Natural Science Foundation of Jiangsu Province under Grant No. BK2010488+1 种基金sponsored by Qing Lan Project, Project 333 "The Six Top Talents" of Jiangsu Province
文摘A Single Image Super-Resolution (SISR) reconstruction method that uses clustered sparse representation and adaptive patch aggregation is proposed. First, we randomly extract image patch pairs from the training images, and divide these patch pairs into different groups by K-means clustering. Then, we learn an over-complete sub-dictionary pair offline from corresponding group patch pairs. For a given low-resolution patch, we adaptively select one sub-dictionary to reconstruct the high resolution patch online. In addition, non-local self-similarity and steering kernel regression constraints are integrated into patch aggregation to improve the quality of the recovered images. Experiments show that the proposed method is able to realize state-of-the-art performance in terms of both objective evaluation and visual perception.
